ZF/insightface
1
0
Fork 0
mirror of https://github.com/deepinsight/insightface.git synced 2025-12-29 23:52:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

a big tree refine

Browse Source
This commit is contained in:
nttstar
2021-06-19 23:37:10 +08:00
parent 5ca3f995d5
commit ce3600a742
167 changed files with 3747 additions and 16144 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@@ -99,3 +99,5 @@ ENV/
# mypy
.mypy_cache/
.DS_Store

317
README.md
View File

@@ -1,6 +1,10 @@
# InsightFace: 2D and 3D Face Analysis Project
<div align="left">
<img src="https://insightface.ai/assets/img/custom/logo3.jpg" width="240"/>
</div>
By [Jia Guo](mailto:guojia@gmail.com?subject=[GitHub]%20InsightFace%20Project) and [Jiankang Deng](https://jiankangdeng.github.io/)
## Top News
@@ -21,244 +25,62 @@ The training data containing the annotation (and the models trained with these d
## Introduction
InsightFace is an open source 2D&3D deep face analysis toolbox, mainly based on MXNet and PyTorch.
[InsightFace](https://insightface.ai) is an open source 2D&3D deep face analysis toolbox, mainly based on PyTorch and MXNet. Please check our [website](https://insightface.ai) for detail.
The master branch works with **MXNet 1.2 to 1.6**, **PyTorch 1.6+**, with **Python 3.x**.
The master branch works with **PyTorch 1.6+** and/or **MXNet=1.6-1.8**, with **Python 3.x**.
InsightFace efficiently implements a rich variety of state of the art algorithms of face recognition, face detection and face alignment, which optimized for both training and deployment.
## ArcFace Video Demo
### ArcFace Video Demo
[![ArcFace Demo](https://github.com/deepinsight/insightface/blob/master/resources/facerecognitionfromvideo.PNG)](https://www.youtube.com/watch?v=y-D1tReryGA&t=81s)
Please click the image to watch the Youtube video. For Bilibili users, click [here](https://www.bilibili.com/video/av38041494?from=search&seid=11501833604850032313).
## Recent Update
**`2021-06-05`**: We launch a [Masked Face Recognition Challenge & Workshop](https://github.com/deepinsight/insightface/tree/master/challenges/iccv21-mfr) on ICCV 2021.
**`2021-05-15`**: We released an efficient high accuracy face detection approach called [SCRFD](https://github.com/deepinsight/insightface/tree/master/detection/scrfd).
**`2021-04-18`**: We achieved Rank-4th on NIST-FRVT 1:1, see [leaderboard](https://pages.nist.gov/frvt/html/frvt11.html).
**`2021-03-13`**: We have released our official ArcFace PyTorch implementation, see [here](https://github.com/deepinsight/insightface/tree/master/recognition/arcface_torch).
**`2021-03-09`**: [Tips](https://github.com/deepinsight/insightface/issues/1426) for training large-scale face recognition model, such as millions of IDs(classes).
**`2021-02-21`**: We provide a simple face mask renderer [here](https://github.com/deepinsight/insightface/tree/master/recognition/tools) which can be used as a data augmentation tool while training face recognition models.
**`2021-01-20`**: [OneFlow](https://github.com/Oneflow-Inc/oneflow) based implementation of ArcFace and Partial-FC, [here](https://github.com/deepinsight/insightface/tree/master/recognition/oneflow_face).
**`2020-10-13`**: A new training method and one large training set(360K IDs) were released [here](https://github.com/deepinsight/insightface/tree/master/recognition/partial_fc) by DeepGlint.
**`2020-10-09`**: We opened a large scale recognition test benchmark [IFRT](https://github.com/deepinsight/insightface/tree/master/challenges/IFRT)
**`2020-08-01`**: We released lightweight facial landmark models with fast coordinate regression(106 points). See detail [here](https://github.com/deepinsight/insightface/tree/master/alignment/coordinateReg).
**`2020-04-27`**: InsightFace pretrained models and MS1M-Arcface are now specified as the only external training dataset, for iQIYI iCartoonFace challenge, see detail [here](http://challenge.ai.iqiyi.com/detail?raceId=5def71b4e9fcf68aef76a75e).
**`2020.02.21`**: Instant discussion group created on QQ with group-id: 711302608. For English developers, see install tutorial [here](https://github.com/deepinsight/insightface/issues/1069).
**`2020.02.16`**: RetinaFace now can detect faces with mask, for anti-CoVID19, see detail [here](https://github.com/deepinsight/insightface/tree/master/detection/RetinaFaceAntiCov)
**`2019.08.10`**: We achieved 2nd place at [WIDER Face Detection Challenge 2019](http://wider-challenge.org/2019.html).
**`2019.05.30`**: [Presentation at cvmart](https://pan.baidu.com/s/1v9fFHBJ8Q9Kl9Z6GwhbY6A)
**`2019.04.30`**: Our Face detector ([RetinaFace](https://github.com/deepinsight/insightface/tree/master/detection/RetinaFace)) obtains state-of-the-art results on [the WiderFace dataset](http://shuoyang1213.me/WIDERFACE/WiderFace_Results.html).
**`2019.04.14`**: We will launch a [Light-weight Face Recognition challenge/workshop](https://github.com/deepinsight/insightface/tree/master/challenges/iccv19-lfr) on ICCV 2019.
**`2019.04.04`**: Arcface achieved state-of-the-art performance (7/109) on the NIST Face Recognition Vendor Test (FRVT) (1:1 verification)
[report](https://www.nist.gov/sites/default/files/documents/2019/04/04/frvt_report_2019_04_04.pdf) (name: Imperial-000 and Imperial-001). Our solution is based on [MS1MV2+DeepGlintAsian, ResNet100, ArcFace loss].
**`2019.02.08`**: Please check [https://github.com/deepinsight/insightface/tree/master/recognition/ArcFace](https://github.com/deepinsight/insightface/tree/master/recognition/ArcFace) for our parallel training code which can easily and efficiently support one million identities on a single machine (8* 1080ti).
**`2018.12.13`**: Inference acceleration [TVM-Benchmark](https://github.com/deepinsight/insightface/wiki/TVM-Benchmark).
**`2018.10.28`**: Light-weight attribute model [Gender-Age](https://github.com/deepinsight/insightface/tree/master/gender-age). About 1MB, 10ms on single CPU core. Gender accuracy 96% on validation set and 4.1 age MAE.
**`2018.10.16`**: We achieved state-of-the-art performance on [Trillionpairs](http://trillionpairs.deepglint.com/results) (name: nttstar) and [IQIYI_VID](http://challenge.ai.iqiyi.com/detail?raceId=5afc36639689443e8f815f9e) (name: WitcheR).
## Contents
[Deep Face Recognition](#deep-face-recognition)
- [Introduction](#introduction)
- [Training Data](#training-data)
- [Train](#train)
- [Pretrained Models](#pretrained-models)
- [Verification Results On Combined Margin](#verification-results-on-combined-margin)
- [Test on MegaFace](#test-on-megaface)
- [512-D Feature Embedding](#512-d-feature-embedding)
- [Third-party Re-implementation](#third-party-re-implementation)
## Projects
[Face Detection](#face-detection)
- [RetinaFace](#retinaface)
- [RetinaFaceAntiCov](#retinafaceanticov)
The [page](https://insightface.ai/projects) on InsightFace website also describes all supported projects in InsightFace.
[Face Alignment](#face-alignment)
- [DenseUNet](#denseunet)
- [CoordinateReg](#coordinatereg)
You may also interested in some [challenges](https://insightface.ai/challenges) hold by InsightFace.
[Citation](#citation)
[Contact](#contact)
## Deep Face Recognition
## Face Recognition
### Introduction
In this module, we provide training data, network settings and loss designs for deep face recognition.
The training data includes, but not limited to the cleaned MS1M, VGG2 and CASIA-Webface datasets, which were already packed in MXNet binary format.
The network backbones include ResNet, MobilefaceNet, MobileNet, InceptionResNet_v2, DenseNet, etc..
The loss functions include Softmax, SphereFace, CosineFace, ArcFace, Sub-Center ArcFace and Triplet (Euclidean/Angular) Loss.
You can check the detail page of our work [ArcFace](https://github.com/deepinsight/insightface/tree/master/recognition/ArcFace)(which accepted in CVPR-2019) and [SubCenter-ArcFace](https://github.com/deepinsight/insightface/tree/master/recognition/SubCenter-ArcFace)(which accepted in ECCV-2020).
The supported methods are as follows:
![margin penalty for target logit](https://github.com/deepinsight/insightface/raw/master/resources/arcface.png)
- [x] [ArcFace_mxnet (CVPR'2019)](recognition/arcface_mxnet)
- [x] [ArcFace_torch (CVPR'2019)](recognition/arcface_torch)
- [x] [SubCenter ArcFace (ECCV'2020)](recognition/subcenter_arcface)
- [x] [PartialFC_mxnet (Arxiv'2020)](recognition/partial_fc)
- [x] [PartialFC_torch (Arxiv'2020)](recognition/arcface_torch)
- [x] [VPL (CVPR'2021)](recognition/vpl)
- [x] [OneFlow_face](recognition/oneflow_face)
Our method, ArcFace, was initially described in an [arXiv technical report](https://arxiv.org/abs/1801.07698). By using this module, you can simply achieve LFW 99.83%+ and Megaface 98%+ by a single model. This module can help researcher/engineer to develop deep face recognition algorithms quickly by only two steps: download the binary dataset and run the training script.
### Training Data
All face images are aligned by ficial five landmarks and cropped to 112x112:
Please check [Dataset-Zoo](https://github.com/deepinsight/insightface/wiki/Dataset-Zoo) for detail information and dataset downloading.
Commonly used network backbones are included in most of the methods, such as IResNet, MobilefaceNet, MobileNet, InceptionResNet_v2, DenseNet, etc..
* Please check *recognition/tools/face2rec2.py* on how to build a binary face dataset. You can either choose *MTCNN* or *RetinaFace* to align the faces.
### Datasets
### Train
The training data includes, but not limited to the cleaned MS1M, VGG2 and CASIA-Webface datasets, which were already packed in MXNet binary format. Please [dataset](recognition/_dataset_) page for detail.
1. Install `MXNet` with GPU support (Python 3.X).
```
pip install mxnet-cu101 # which should match your installed cuda version
```
2. Clone the InsightFace repository. We call the directory insightface as *`INSIGHTFACE_ROOT`*.
```
git clone --recursive https://github.com/deepinsight/insightface.git
```
3. Download the training set (`MS1M-Arcface`) and place it in *`$INSIGHTFACE_ROOT/recognition/datasets/`*. Each training dataset includes at least following 6 files:
```Shell
faces_emore/
train.idx
train.rec
property
lfw.bin
cfp_fp.bin
agedb_30.bin
```
The first three files are the training dataset while the last three files are verification sets.
4. Train deep face recognition models.
In this part, we assume you are in the directory *`$INSIGHTFACE_ROOT/recognition/ArcFace/`*.
Place and edit config file:
```Shell
cp sample_config.py config.py
vim config.py # edit dataset path etc..
```
We give some examples below. Our experiments were conducted on the Tesla P40 GPU.
(1). Train ArcFace with LResNet100E-IR.
```Shell
CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train.py --network r100 --loss arcface --dataset emore
```
It will output verification results of *LFW*, *CFP-FP* and *AgeDB-30* every 2000 batches. You can check all options in *config.py*.
This model can achieve *LFW 99.83+* and *MegaFace 98.3%+*.
(2). Train CosineFace with LResNet50E-IR.
```Shell
CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train.py --network r50 --loss cosface --dataset emore
```
(3). Train Softmax with LMobileNet-GAP.
```Shell
CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train.py --network m1 --loss softmax --dataset emore
```
(4). Fine-turn the above Softmax model with Triplet loss.
```Shell
CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train.py --network m1 --loss triplet --lr 0.005 --pretrained ./models/m1-softmax-emore,1
```
(5). Training in model parallel acceleration.
```Shell
CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train_parall.py --network r100 --loss arcface --dataset emore
```
5. Verification results.
*LResNet100E-IR* network trained on *MS1M-Arcface* dataset with ArcFace loss:
| Method | LFW(%) | CFP-FP(%) | AgeDB-30(%) |
| ------- | ------ | --------- | ----------- |
| Ours | 99.80+ | 98.0+ | 98.20+ |
### Evaluation
We provide standard IJB and Megaface evaluation pipelines in [evaluation](recognition/_evaluation_)
### Pretrained Models
You can use `$INSIGHTFACE_ROOT/recognition/arcface_torch/eval/verification.py` to test all the pre-trained models.
**Please check [Model-Zoo](https://github.com/deepinsight/insightface/wiki/Model-Zoo) for more pretrained models.**
### Verification Results on Combined Margin
A combined margin method was proposed as a function of target logits value and original `θ`:
```
COM(θ) = cos(m_1*θ+m_2) - m_3
```
For training with `m1=1.0, m2=0.3, m3=0.2`, run following command:
```
CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train.py --network r100 --loss combined --dataset emore
```
Results by using ``MS1M-IBUG(MS1M-V1)``
| Method | m1 | m2 | m3 | LFW | CFP-FP | AgeDB-30 |
| ---------------- | ---- | ---- | ---- | ----- | ------ | -------- |
| W&F Norm Softmax | 1 | 0 | 0 | 99.28 | 88.50 | 95.13 |
| SphereFace | 1.5 | 0 | 0 | 99.76 | 94.17 | 97.30 |
| CosineFace | 1 | 0 | 0.35 | 99.80 | 94.4 | 97.91 |
| ArcFace | 1 | 0.5 | 0 | 99.83 | 94.04 | 98.08 |
| Combined Margin | 1.2 | 0.4 | 0 | 99.80 | 94.08 | 98.05 |
| Combined Margin | 1.1 | 0 | 0.35 | 99.81 | 94.50 | 98.08 |
| Combined Margin | 1 | 0.3 | 0.2 | 99.83 | 94.51 | 98.13 |
| Combined Margin | 0.9 | 0.4 | 0.15 | 99.83 | 94.20 | 98.16 |
### Test on MegaFace
Please check *`$INSIGHTFACE_ROOT/evaluation/megaface/`* to evaluate the model accuracy on Megaface. All aligned images were already provided.
### 512-D Feature Embedding
In this part, we assume you are in the directory *`$INSIGHTFACE_ROOT/deploy/`*. The input face image should be generally centre cropped. We use *RNet+ONet* of *MTCNN* to further align the image before sending it to the feature embedding network.
1. Prepare a pre-trained model.
2. Put the model under *`$INSIGHTFACE_ROOT/models/`*. For example, *`$INSIGHTFACE_ROOT/models/model-r100-ii`*.
3. Run the test script *`$INSIGHTFACE_ROOT/deploy/test.py`*.
For single cropped face image(112x112), total inference time is only 17ms on our testing server(Intel E5-2660 @ 2.00GHz, Tesla M40, *LResNet34E-IR*).
### Third-party Re-implementation
### Third-party Re-implementation of ArcFace
- TensorFlow: [InsightFace_TF](https://github.com/auroua/InsightFace_TF)
- TensorFlow: [tf-insightface](https://github.com/AIInAi/tf-insightface)
@@ -272,39 +94,43 @@ For single cropped face image(112x112), total inference time is only 17ms on our
## Face Detection
### RetinaFace
### Introduction
RetinaFace is a practical single-stage [SOTA](http://shuoyang1213.me/WIDERFACE/WiderFace_Results.html) face detector which is initially introduced in [arXiv technical report](https://arxiv.org/abs/1905.00641) and then accepted by [CVPR 2020](https://openaccess.thecvf.com/content_CVPR_2020/html/Deng_RetinaFace_Single-Shot_Multi-Level_Face_Localisation_in_the_Wild_CVPR_2020_paper.html). We provide training code, training dataset, pretrained models and evaluation scripts.
![demoimg1](https://github.com/deepinsight/insightface/blob/master/resources/11513D05.jpg)
Please check [RetinaFace](https://github.com/deepinsight/insightface/tree/master/detection/RetinaFace) for detail.
### RetinaFaceAntiCov
RetinaFaceAntiCov is an experimental module to identify face boxes with masks. Please check [RetinaFaceAntiCov](https://github.com/deepinsight/insightface/tree/master/detection/RetinaFaceAntiCov) for detail.
![demoimg1](https://github.com/deepinsight/insightface/blob/master/resources/cov_test.jpg)
<div align="left">
<img src="https://insightface.ai/assets/img/github/11513D05.jpg" width="640"/>
</div>
In this module, we provide training data with annotation, network settings and loss designs for face detection training, evaluation and inference.
The supported methods are as follows:
- [x] [RetinaFace (CVPR'2020)](detection/retinaface)
- [x] [SCRFD (Arxiv'2021)](detection/scrfd)
[RetinaFace](detection/retinaface) is a practical single-stage face detector which is accepted by [CVPR 2020](https://openaccess.thecvf.com/content_CVPR_2020/html/Deng_RetinaFace_Single-Shot_Multi-Level_Face_Localisation_in_the_Wild_CVPR_2020_paper.html). We provide training code, training dataset, pretrained models and evaluation scripts.
[SCRFD](detection/scrfd) is an efficient high accuracy face detection approach which is initialy described in [Arxiv](https://arxiv.org/abs/2105.04714). We provide an easy-to-use pipeline to train high efficiency face detectors with NAS supporting.
## Face Alignment
### DenseUNet
### Introduction
Please check the [Menpo](https://github.com/jiankangdeng/MenpoBenchmark) Benchmark and our [Dense U-Net](https://github.com/deepinsight/insightface/tree/master/alignment/heatmapReg) for detail. We also provide other network settings such as classic hourglass. You can find all of training code, training dataset and evaluation scripts there.
### CoordinateReg
On the other hand, in contrast to heatmap based approaches, we provide some lightweight facial landmark models with fast coordinate regression. The input of these models is loose cropped face image while the output is the direct landmark coordinates. See detail at [alignment-coordinateReg](https://github.com/deepinsight/insightface/tree/master/alignment/coordinateReg). Now only pretrained models available.
<div align="center">
<img src="https://github.com/nttstar/insightface-resources/blob/master/alignment/images/t1_out.jpg" alt="imagevis" width="800">
<div align="left">
<img src="https://insightface.ai/assets/img/custom/thumb_sdunet.png" width="600"/>
</div>
In this module, we provide datasets and training/inference pipelines for face alignment.
<div align="center">
<img src="https://github.com/nttstar/insightface-resources/blob/master/alignment/images/C_jiaguo.gif" alt="videovis" width="240">
</div>
Supported methods:
- [x] [SDUNets (BMVC'2018)](alignment/heatmap)
- [x] [SimpleRegression](alignment/coordinate_reg)
[SDUNets](alignment/heatmap) is a heatmap based method which accepted on [BMVC](http://bmvc2018.org/contents/papers/0051.pdf).
[SimpleRegression](alignment/coordinate_reg) provides very lightweight facial landmark models with fast coordinate regression. The input of these models is loose cropped face image while the output is the direct landmark coordinates.
## Citation
@@ -312,11 +138,34 @@ For single cropped face image(112x112), total inference time is only 17ms on our
If you find *InsightFace* useful in your research, please consider to cite the following related papers:
```
@inproceedings{deng2019retinaface,
title={RetinaFace: Single-stage Dense Face Localisation in the Wild},
author={Deng, Jiankang and Guo, Jia and Yuxiang, Zhou and Jinke Yu and Irene Kotsia and Zafeiriou, Stefanos},
booktitle={arxiv},
year={2019}
@article{guo2021sample,
title={Sample and Computation Redistribution for Efficient Face Detection},
author={Guo, Jia and Deng, Jiankang and Lattas, Alexandros and Zafeiriou, Stefanos},
journal={arXiv preprint arXiv:2105.04714},
year={2021}
}
@inproceedings{an2020partical_fc,
title={Partial FC: Training 10 Million Identities on a Single Machine},
author={An, Xiang and Zhu, Xuhan and Xiao, Yang and Wu, Lan and Zhang, Ming and Gao, Yuan and Qin, Bin and
Zhang, Debing and Fu Ying},
booktitle={Arxiv 2010.05222},
year={2020}
}
@inproceedings{deng2020subcenter,
title={Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces},
author={Deng, Jiankang and Guo, Jia and Liu, Tongliang and Gong, Mingming and Zafeiriou, Stefanos},
booktitle={Proceedings of the IEEE Conference on European Conference on Computer Vision},
year={2020}
}
@inproceedings{Deng2020CVPR,
title = {RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild},
author = {Deng, Jiankang and Guo, Jia and Ververas, Evangelos and Kotsia, Irene and Zafeiriou, Stefanos},
booktitle = {CVPR},
year = {2020}
}
@inproceedings{guo2018stacked,

42
alignment/README.md
View File

@@ -1,4 +1,42 @@
You can now find heatmap based approaches under ``heatmapReg`` directory.
## Face Alignment
<div align="left">
<img src="https://insightface.ai/assets/img/custom/logo3.jpg" width="240"/>
</div>
## Introduction
These are the face alignment methods of [InsightFace](https://insightface.ai)
<div align="left">
<img src="https://insightface.ai/assets/img/custom/thumb_sdunet.png" width="600"/>
</div>
### Datasets
Please refer to [datasets](_datasets_) page for the details of face alignment datasets used for training and evaluation.
### Evaluation
Please refer to [evaluation](_evaluation_) page for the details of face alignment evaluation.
## Methods
Supported methods:
- [x] [SDUNets (BMVC'2018)](heatmap)
- [x] [SimpleRegression](coordinate_reg)
## Contributing
We appreciate all contributions to improve the face alignment model zoo of InsightFace.
You can now find coordinate regression approaches under ``coordinateReg`` directory.

0
alignment/coordinateReg/README.md → alignment/coordinate_reg/README.md
View File

0
alignment/coordinateReg/image_infer.py → alignment/coordinate_reg/image_infer.py
View File

0
alignment/heatmapReg/README.md → alignment/heatmap/README.md
View File

0
alignment/heatmapReg/data.py → alignment/heatmap/data.py
View File

0
alignment/heatmapReg/img_helper.py → alignment/heatmap/img_helper.py
View File

0
alignment/heatmapReg/metric.py → alignment/heatmap/metric.py
View File

0
alignment/heatmapReg/optimizer.py → alignment/heatmap/optimizer.py
View File

0
alignment/heatmapReg/sample_config.py → alignment/heatmap/sample_config.py
View File

0
alignment/heatmapReg/symbol/sym_heatmap.py → alignment/heatmap/symbol/sym_heatmap.py
View File

0
alignment/heatmapReg/test.py → alignment/heatmap/test.py
View File

0
alignment/heatmapReg/test_rec_nme.py → alignment/heatmap/test_rec_nme.py
View File

0
alignment/heatmapReg/train.py → alignment/heatmap/train.py
View File

41
attribute/README.md Normal file
View File

@@ -0,0 +1,41 @@
## Face Alignment
<div align="left">
<img src="https://insightface.ai/assets/img/custom/logo3.jpg" width="320"/>
</div>
## Introduction
These are the face attribute methods of [InsightFace](https://insightface.ai)
<div align="left">
<img src="https://insightface.ai/assets/img/github/t1_genderage.jpg" width="600"/>
</div>
### Datasets
Please refer to [datasets](_datasets_) page for the details of face attribute datasets used for training and evaluation.
### Evaluation
Please refer to [evaluation](_evaluation_) page for the details of face attribute evaluation.
## Methods
Supported methods:
- [x] [Gender_Age](gender_age)
## Contributing
We appreciate all contributions to improve the face attribute model zoo of InsightFace.

14
deploy/test.py → attribute/gender_age/test.py
View File

@@ -4,25 +4,21 @@ import sys
import numpy as np
import insightface
from insightface.app import FaceAnalysis
from insightface.data import get_image as ins_get_image
assert insightface.__version__>='0.2'
parser = argparse.ArgumentParser(description='insightface test')
parser = argparse.ArgumentParser(description='insightface gender-age test')
# general
parser.add_argument('--ctx', default=0, type=int, help='ctx id, <0 means using cpu')
args = parser.parse_args()
app = FaceAnalysis(name='antelope')
app = FaceAnalysis(allowed_modules=['detection', 'genderage'])
app.prepare(ctx_id=args.ctx, det_size=(640,640))
img = cv2.imread('../sample-images/t1.jpg')
img = ins_get_image('t1')
faces = app.get(img)
assert len(faces)==6
rimg = app.draw_on(img, faces)
cv2.imwrite("./t1_output.jpg", rimg)
print(len(faces))
for face in faces:
print(face.bbox)
print(face.kps)
print(face.embedding.shape)
print(face.sex, face.age)

31
challenges/README.md Normal file
View File

@@ -0,0 +1,31 @@
## Challenges
<div align="left">
<img src="https://insightface.ai/assets/img/custom/logo3.jpg" width="240"/>
</div>
## Introduction
These are challenges hold by [InsightFace](https://insightface.ai)
<div align="left">
<img src="https://insightface.ai/assets/img/custom/thumb_ifrt.png" width="480"/>
</div>
## List
Supported methods:
- [LFR19 (ICCVW'2019)](iccv19-lfr)
- [MFR21 (ICCVW'2021)](iccv21-mfr)
- [IFRT](ifrt)

2
challenges/iccv19-lfr/README.md
View File

@@ -31,7 +31,7 @@ insightface.challenge@gmail.com
*For Chinese:*
![wechat](https://github.com/deepinsight/insightface/blob/master/resources/lfr19_wechat1.jpg)
![wechat](https://insightface.ai/assets/img/github/lfr19_wechat1.jpg)
*For English:*

8
deploy/README.md
View File

@@ -1,8 +0,0 @@
InsightFace deployment README
---
For insightface pip-package <= 0.1.5, we use MXNet as inference backend, please download all models from [onedrive](https://1drv.ms/u/s!AswpsDO2toNKrUy0VktHTWgIQ0bn?e=UEF7C4), and put them all under `~/.insightface/models/` directory.
Starting from insightface>=0.2, we use onnxruntime as inference backend, please download our **antelope** model release from [onedrive](https://1drv.ms/u/s!AswpsDO2toNKrU0ydGgDkrHPdJ3m?e=iVgZox), and put it under `~/.insightface/models/`, so there're onnx models at `~/.insightface/models/antelope/*.onnx`.
The **antelope** model release contains `ResNet100@Glint360K recognition model` and `SCRFD-10GF detection model`. Please check `test.py` for detail.

40
deploy/convert_onnx.py
View File

@@ -1,40 +0,0 @@
import sys
import os
import argparse
import onnx
import mxnet as mx
print('mxnet version:', mx.__version__)
print('onnx version:', onnx.__version__)
#make sure to install onnx-1.2.1
#pip uninstall onnx
#pip install onnx==1.2.1
assert onnx.__version__ == '1.2.1'
import numpy as np
from mxnet.contrib import onnx as onnx_mxnet
parser = argparse.ArgumentParser(
description='convert insightface models to onnx')
# general
parser.add_argument('--prefix',
default='./r100-arcface/model',
help='prefix to load model.')
parser.add_argument('--epoch',
default=0,
type=int,
help='epoch number to load model.')
parser.add_argument('--input-shape', default='3,112,112', help='input shape.')
parser.add_argument('--output-onnx',
default='./r100.onnx',
help='path to write onnx model.')
args = parser.parse_args()
input_shape = (1, ) + tuple([int(x) for x in args.input_shape.split(',')])
print('input-shape:', input_shape)
sym_file = "%s-symbol.json" % args.prefix
params_file = "%s-%04d.params" % (args.prefix, args.epoch)
assert os.path.exists(sym_file)
assert os.path.exists(params_file)
converted_model_path = onnx_mxnet.export_model(sym_file, params_file,
[input_shape], np.float32,
args.output_onnx)

67
deploy/face_model.py
View File

@@ -1,67 +0,0 @@
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import sys
import os
import argparse
import numpy as np
import mxnet as mx
import cv2
import insightface
from insightface.utils import face_align
def do_flip(data):
for idx in range(data.shape[0]):
data[idx, :, :] = np.fliplr(data[idx, :, :])
def get_model(ctx, image_size, prefix, epoch, layer):
print('loading', prefix, epoch)
sym, arg_params, aux_params = mx.model.load_checkpoint(prefix, epoch)
all_layers = sym.get_internals()
sym = all_layers[layer + '_output']
model = mx.mod.Module(symbol=sym, context=ctx, label_names=None)
#model.bind(data_shapes=[('data', (args.batch_size, 3, image_size[0], image_size[1]))], label_shapes=[('softmax_label', (args.batch_size,))])
model.bind(data_shapes=[('data', (1, 3, image_size[0], image_size[1]))])
model.set_params(arg_params, aux_params)
return model
class FaceModel:
def __init__(self, ctx_id, model_prefix, model_epoch, use_large_detector=False):
if use_large_detector:
self.detector = insightface.model_zoo.get_model('retinaface_r50_v1')
else:
self.detector = insightface.model_zoo.get_model('retinaface_mnet025_v2')
self.detector.prepare(ctx_id=ctx_id)
if ctx_id>=0:
ctx = mx.gpu(ctx_id)
else:
ctx = mx.cpu()
image_size = (112,112)
self.model = get_model(ctx, image_size, model_prefix, model_epoch, 'fc1')
self.image_size = image_size
def get_input(self, face_img):
bbox, pts5 = self.detector.detect(face_img, threshold=0.8)
if bbox.shape[0]==0:
return None
bbox = bbox[0, 0:4]
pts5 = pts5[0, :]
nimg = face_align.norm_crop(face_img, pts5)
return nimg
def get_feature(self, aligned):
a = cv2.cvtColor(aligned, cv2.COLOR_BGR2RGB)
a = np.transpose(a, (2, 0, 1))
input_blob = np.expand_dims(a, axis=0)
data = mx.nd.array(input_blob)
db = mx.io.DataBatch(data=(data, ))
self.model.forward(db, is_train=False)
emb = self.model.get_outputs()[0].asnumpy()[0]
norm = np.sqrt(np.sum(emb*emb)+0.00001)
emb /= norm
return emb

32
deploy/model_slim.py
View File

@@ -1,32 +0,0 @@
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import sys
import os
import argparse
import numpy as np
import mxnet as mx
parser = argparse.ArgumentParser(description='face model slim')
# general
parser.add_argument('--model',
default='../models/model-r34-amf/model,60',
help='path to load model.')
args = parser.parse_args()
_vec = args.model.split(',')
assert len(_vec) == 2
prefix = _vec[0]
epoch = int(_vec[1])
print('loading', prefix, epoch)
sym, arg_params, aux_params = mx.model.load_checkpoint(prefix, epoch)
all_layers = sym.get_internals()
sym = all_layers['fc1_output']
dellist = []
for k, v in arg_params.iteritems():
if k.startswith('fc7'):
dellist.append(k)
for d in dellist:
del arg_params[d]
mx.model.save_checkpoint(prefix + "s", 0, sym, arg_params, aux_params)

BIN
deploy/mtcnn-model/det1-0001.params
View File

Binary file not shown.

266
deploy/mtcnn-model/det1-symbol.json
View File

@@ -1,266 +0,0 @@
{
"nodes": [
{
"op": "null",
"param": {},
"name": "data",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv1_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv1_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "10",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv1",
"inputs": [[0, 0], [1, 0], [2, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu1_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu1",
"inputs": [[3, 0], [4, 0]],
"backward_source_id": -1
},
{
"op": "Pooling",
"param": {
"global_pool": "False",
"kernel": "(2,2)",
"pad": "(0,0)",
"pool_type": "max",
"pooling_convention": "full",
"stride": "(2,2)"
},
"name": "pool1",
"inputs": [[5, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv2_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv2_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "16",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv2",
"inputs": [[6, 0], [7, 0], [8, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu2_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu2",
"inputs": [[9, 0], [10, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv3_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv3_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "32",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv3",
"inputs": [[11, 0], [12, 0], [13, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu3_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu3",
"inputs": [[14, 0], [15, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_2_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_2_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(1,1)",
"no_bias": "False",
"num_filter": "4",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv4_2",
"inputs": [[16, 0], [17, 0], [18, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_1_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_1_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(1,1)",
"no_bias": "False",
"num_filter": "2",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv4_1",
"inputs": [[16, 0], [20, 0], [21, 0]],
"backward_source_id": -1
},
{
"op": "SoftmaxActivation",
"param": {"mode": "channel"},
"name": "prob1",
"inputs": [[22, 0]],
"backward_source_id": -1
}
],
"arg_nodes": [
0,
1,
2,
4,
7,
8,
10,
12,
13,
15,
17,
18,
20,
21
],
"heads": [[19, 0], [23, 0]]
}

BIN
deploy/mtcnn-model/det1.caffemodel
View File

Binary file not shown.

177
deploy/mtcnn-model/det1.prototxt
View File

@@ -1,177 +0,0 @@
name: "PNet"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 12
input_dim: 12
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 10
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "PReLU1"
type: "PReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 16
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "PReLU2"
type: "PReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "conv3"
type: "Convolution"
bottom: "conv2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 32
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "PReLU3"
type: "PReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4-1"
type: "Convolution"
bottom: "conv3"
top: "conv4-1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 2
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv4-2"
type: "Convolution"
bottom: "conv3"
top: "conv4-2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 4
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prob1"
type: "Softmax"
bottom: "conv4-1"
top: "prob1"
}

BIN
deploy/mtcnn-model/det2-0001.params
View File

Binary file not shown.

324
deploy/mtcnn-model/det2-symbol.json
View File

@@ -1,324 +0,0 @@
{
"nodes": [
{
"op": "null",
"param": {},
"name": "data",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv1_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv1_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "28",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv1",
"inputs": [[0, 0], [1, 0], [2, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu1_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu1",
"inputs": [[3, 0], [4, 0]],
"backward_source_id": -1
},
{
"op": "Pooling",
"param": {
"global_pool": "False",
"kernel": "(3,3)",
"pad": "(0,0)",
"pool_type": "max",
"pooling_convention": "full",
"stride": "(2,2)"
},
"name": "pool1",
"inputs": [[5, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv2_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv2_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "48",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv2",
"inputs": [[6, 0], [7, 0], [8, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu2_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu2",
"inputs": [[9, 0], [10, 0]],
"backward_source_id": -1
},
{
"op": "Pooling",
"param": {
"global_pool": "False",
"kernel": "(3,3)",
"pad": "(0,0)",
"pool_type": "max",
"pooling_convention": "full",
"stride": "(2,2)"
},
"name": "pool2",
"inputs": [[11, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv3_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv3_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(2,2)",
"no_bias": "False",
"num_filter": "64",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv3",
"inputs": [[12, 0], [13, 0], [14, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu3_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu3",
"inputs": [[15, 0], [16, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "128"
},
"name": "conv4",
"inputs": [[17, 0], [18, 0], [19, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu4_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu4",
"inputs": [[20, 0], [21, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv5_2_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv5_2_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "4"
},
"name": "conv5_2",
"inputs": [[22, 0], [23, 0], [24, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv5_1_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv5_1_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "2"
},
"name": "conv5_1",
"inputs": [[22, 0], [26, 0], [27, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prob1_label",
"inputs": [],
"backward_source_id": -1
},
{
"op": "SoftmaxOutput",
"param": {
"grad_scale": "1",
"ignore_label": "-1",
"multi_output": "False",
"normalization": "null",
"use_ignore": "False"
},
"name": "prob1",
"inputs": [[28, 0], [29, 0]],
"backward_source_id": -1
}
],
"arg_nodes": [
0,
1,
2,
4,
7,
8,
10,
13,
14,
16,
18,
19,
21,
23,
24,
26,
27,
29
],
"heads": [[25, 0], [30, 0]]
}

BIN
deploy/mtcnn-model/det2.caffemodel
View File

Binary file not shown.

228
deploy/mtcnn-model/det2.prototxt
View File

@@ -1,228 +0,0 @@
name: "RNet"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 24
input_dim: 24
##########################
######################
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
convolution_param {
num_output: 28
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1"
type: "PReLU"
bottom: "conv1"
top: "conv1"
propagate_down: true
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
convolution_param {
num_output: 48
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2"
type: "PReLU"
bottom: "conv2"
top: "conv2"
propagate_down: true
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
####################################
##################################
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
convolution_param {
num_output: 64
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3"
type: "PReLU"
bottom: "conv3"
top: "conv3"
propagate_down: true
}
###############################
###############################
layer {
name: "conv4"
type: "InnerProduct"
bottom: "conv3"
top: "conv4"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
inner_product_param {
num_output: 128
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4"
type: "PReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5-1"
type: "InnerProduct"
bottom: "conv4"
top: "conv5-1"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
inner_product_param {
num_output: 2
#kernel_size: 1
#stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv5-2"
type: "InnerProduct"
bottom: "conv4"
top: "conv5-2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 4
#kernel_size: 1
#stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prob1"
type: "Softmax"
bottom: "conv5-1"
top: "prob1"
}

BIN
deploy/mtcnn-model/det3-0001.params
View File

Binary file not shown.

418
deploy/mtcnn-model/det3-symbol.json
View File

@@ -1,418 +0,0 @@
{
"nodes": [
{
"op": "null",
"param": {},
"name": "data",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv1_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv1_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "32",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv1",
"inputs": [[0, 0], [1, 0], [2, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu1_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu1",
"inputs": [[3, 0], [4, 0]],
"backward_source_id": -1
},
{
"op": "Pooling",
"param": {
"global_pool": "False",
"kernel": "(3,3)",
"pad": "(0,0)",
"pool_type": "max",
"pooling_convention": "full",
"stride": "(2,2)"
},
"name": "pool1",
"inputs": [[5, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv2_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv2_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "64",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv2",
"inputs": [[6, 0], [7, 0], [8, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu2_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu2",
"inputs": [[9, 0], [10, 0]],
"backward_source_id": -1
},
{
"op": "Pooling",
"param": {
"global_pool": "False",
"kernel": "(3,3)",
"pad": "(0,0)",
"pool_type": "max",
"pooling_convention": "full",
"stride": "(2,2)"
},
"name": "pool2",
"inputs": [[11, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv3_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv3_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "64",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv3",
"inputs": [[12, 0], [13, 0], [14, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu3_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu3",
"inputs": [[15, 0], [16, 0]],
"backward_source_id": -1
},
{
"op": "Pooling",
"param": {
"global_pool": "False",
"kernel": "(2,2)",
"pad": "(0,0)",
"pool_type": "max",
"pooling_convention": "full",
"stride": "(2,2)"
},
"name": "pool3",
"inputs": [[17, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(2,2)",
"no_bias": "False",
"num_filter": "128",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv4",
"inputs": [[18, 0], [19, 0], [20, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu4_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu4",
"inputs": [[21, 0], [22, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv5_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv5_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "256"
},
"name": "conv5",
"inputs": [[23, 0], [24, 0], [25, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu5_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu5",
"inputs": [[26, 0], [27, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv6_3_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv6_3_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "10"
},
"name": "conv6_3",
"inputs": [[28, 0], [29, 0], [30, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv6_2_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv6_2_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "4"
},
"name": "conv6_2",
"inputs": [[28, 0], [32, 0], [33, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv6_1_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv6_1_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "2"
},
"name": "conv6_1",
"inputs": [[28, 0], [35, 0], [36, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prob1_label",
"inputs": [],
"backward_source_id": -1
},
{
"op": "SoftmaxOutput",
"param": {
"grad_scale": "1",
"ignore_label": "-1",
"multi_output": "False",
"normalization": "null",
"use_ignore": "False"
},
"name": "prob1",
"inputs": [[37, 0], [38, 0]],
"backward_source_id": -1
}
],
"arg_nodes": [
0,
1,
2,
4,
7,
8,
10,
13,
14,
16,
19,
20,
22,
24,
25,
27,
29,
30,
32,
33,
35,
36,
38
],
"heads": [[31, 0], [34, 0], [39, 0]]
}

BIN
deploy/mtcnn-model/det3.caffemodel
View File

Binary file not shown.

294
deploy/mtcnn-model/det3.prototxt
View File

@@ -1,294 +0,0 @@
name: "ONet"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 48
input_dim: 48
##################################
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 32
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1"
type: "PReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2"
type: "PReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 3
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3"
type: "PReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "pool3"
type: "Pooling"
bottom: "conv3"
top: "pool3"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv4"
type: "Convolution"
bottom: "pool3"
top: "conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 128
kernel_size: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4"
type: "PReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "InnerProduct"
bottom: "conv4"
top: "conv5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
#kernel_size: 3
num_output: 256
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "drop5"
type: "Dropout"
bottom: "conv5"
top: "conv5"
dropout_param {
dropout_ratio: 0.25
}
}
layer {
name: "prelu5"
type: "PReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "conv6-1"
type: "InnerProduct"
bottom: "conv5"
top: "conv6-1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
#kernel_size: 1
num_output: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv6-2"
type: "InnerProduct"
bottom: "conv5"
top: "conv6-2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
#kernel_size: 1
num_output: 4
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv6-3"
type: "InnerProduct"
bottom: "conv5"
top: "conv6-3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
#kernel_size: 1
num_output: 10
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prob1"
type: "Softmax"
bottom: "conv6-1"
top: "prob1"
}

BIN
deploy/mtcnn-model/det4-0001.params
View File

Binary file not shown.

1392
deploy/mtcnn-model/det4-symbol.json
View File

File diff suppressed because it is too large Load Diff

BIN
deploy/mtcnn-model/det4.caffemodel
View File

Binary file not shown.

995
deploy/mtcnn-model/det4.prototxt
View File

@@ -1,995 +0,0 @@
name: "LNet"
input: "data"
input_dim: 1
input_dim: 15
input_dim: 24
input_dim: 24
layer {
name: "slicer_data"
type: "Slice"
bottom: "data"
top: "data241"
top: "data242"
top: "data243"
top: "data244"
top: "data245"
slice_param {
axis: 1
slice_point: 3
slice_point: 6
slice_point: 9
slice_point: 12
}
}
layer {
name: "conv1_1"
type: "Convolution"
bottom: "data241"
top: "conv1_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 28
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1_1"
type: "PReLU"
bottom: "conv1_1"
top: "conv1_1"
}
layer {
name: "pool1_1"
type: "Pooling"
bottom: "conv1_1"
top: "pool1_1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2_1"
type: "Convolution"
bottom: "pool1_1"
top: "conv2_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 48
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2_1"
type: "PReLU"
bottom: "conv2_1"
top: "conv2_1"
}
layer {
name: "pool2_1"
type: "Pooling"
bottom: "conv2_1"
top: "pool2_1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3_1"
type: "Convolution"
bottom: "pool2_1"
top: "conv3_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3_1"
type: "PReLU"
bottom: "conv3_1"
top: "conv3_1"
}
##########################
layer {
name: "conv1_2"
type: "Convolution"
bottom: "data242"
top: "conv1_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 28
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1_2"
type: "PReLU"
bottom: "conv1_2"
top: "conv1_2"
}
layer {
name: "pool1_2"
type: "Pooling"
bottom: "conv1_2"
top: "pool1_2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2_2"
type: "Convolution"
bottom: "pool1_2"
top: "conv2_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 48
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2_2"
type: "PReLU"
bottom: "conv2_2"
top: "conv2_2"
}
layer {
name: "pool2_2"
type: "Pooling"
bottom: "conv2_2"
top: "pool2_2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3_2"
type: "Convolution"
bottom: "pool2_2"
top: "conv3_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3_2"
type: "PReLU"
bottom: "conv3_2"
top: "conv3_2"
}
##########################
##########################
layer {
name: "conv1_3"
type: "Convolution"
bottom: "data243"
top: "conv1_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 28
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1_3"
type: "PReLU"
bottom: "conv1_3"
top: "conv1_3"
}
layer {
name: "pool1_3"
type: "Pooling"
bottom: "conv1_3"
top: "pool1_3"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2_3"
type: "Convolution"
bottom: "pool1_3"
top: "conv2_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 48
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2_3"
type: "PReLU"
bottom: "conv2_3"
top: "conv2_3"
}
layer {
name: "pool2_3"
type: "Pooling"
bottom: "conv2_3"
top: "pool2_3"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3_3"
type: "Convolution"
bottom: "pool2_3"
top: "conv3_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3_3"
type: "PReLU"
bottom: "conv3_3"
top: "conv3_3"
}
##########################
##########################
layer {
name: "conv1_4"
type: "Convolution"
bottom: "data244"
top: "conv1_4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 28
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1_4"
type: "PReLU"
bottom: "conv1_4"
top: "conv1_4"
}
layer {
name: "pool1_4"
type: "Pooling"
bottom: "conv1_4"
top: "pool1_4"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2_4"
type: "Convolution"
bottom: "pool1_4"
top: "conv2_4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 48
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2_4"
type: "PReLU"
bottom: "conv2_4"
top: "conv2_4"
}
layer {
name: "pool2_4"
type: "Pooling"
bottom: "conv2_4"
top: "pool2_4"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3_4"
type: "Convolution"
bottom: "pool2_4"
top: "conv3_4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3_4"
type: "PReLU"
bottom: "conv3_4"
top: "conv3_4"
}
##########################
##########################
layer {
name: "conv1_5"
type: "Convolution"
bottom: "data245"
top: "conv1_5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 28
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1_5"
type: "PReLU"
bottom: "conv1_5"
top: "conv1_5"
}
layer {
name: "pool1_5"
type: "Pooling"
bottom: "conv1_5"
top: "pool1_5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2_5"
type: "Convolution"
bottom: "pool1_5"
top: "conv2_5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 48
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2_5"
type: "PReLU"
bottom: "conv2_5"
top: "conv2_5"
}
layer {
name: "pool2_5"
type: "Pooling"
bottom: "conv2_5"
top: "pool2_5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3_5"
type: "Convolution"
bottom: "pool2_5"
top: "conv3_5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3_5"
type: "PReLU"
bottom: "conv3_5"
top: "conv3_5"
}
##########################
layer {
name: "concat"
bottom: "conv3_1"
bottom: "conv3_2"
bottom: "conv3_3"
bottom: "conv3_4"
bottom: "conv3_5"
top: "conv3"
type: "Concat"
concat_param {
axis: 1
}
}
##########################
layer {
name: "fc4"
type: "InnerProduct"
bottom: "conv3"
top: "fc4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 256
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4"
type: "PReLU"
bottom: "fc4"
top: "fc4"
}
############################
layer {
name: "fc4_1"
type: "InnerProduct"
bottom: "fc4"
top: "fc4_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 64
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4_1"
type: "PReLU"
bottom: "fc4_1"
top: "fc4_1"
}
layer {
name: "fc5_1"
type: "InnerProduct"
bottom: "fc4_1"
top: "fc5_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 2
weight_filler {
type: "xavier"
#type: "constant"
#value: 0
}
bias_filler {
type: "constant"
value: 0
}
}
}
#########################
layer {
name: "fc4_2"
type: "InnerProduct"
bottom: "fc4"
top: "fc4_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 64
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4_2"
type: "PReLU"
bottom: "fc4_2"
top: "fc4_2"
}
layer {
name: "fc5_2"
type: "InnerProduct"
bottom: "fc4_2"
top: "fc5_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 2
weight_filler {
type: "xavier"
#type: "constant"
#value: 0
}
bias_filler {
type: "constant"
value: 0
}
}
}
#########################
layer {
name: "fc4_3"
type: "InnerProduct"
bottom: "fc4"
top: "fc4_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 64
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4_3"
type: "PReLU"
bottom: "fc4_3"
top: "fc4_3"
}
layer {
name: "fc5_3"
type: "InnerProduct"
bottom: "fc4_3"
top: "fc5_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 2
weight_filler {
type: "xavier"
#type: "constant"
#value: 0
}
bias_filler {
type: "constant"
value: 0
}
}
}
#########################
layer {
name: "fc4_4"
type: "InnerProduct"
bottom: "fc4"
top: "fc4_4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 64
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4_4"
type: "PReLU"
bottom: "fc4_4"
top: "fc4_4"
}
layer {
name: "fc5_4"
type: "InnerProduct"
bottom: "fc4_4"
top: "fc5_4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 2
weight_filler {
type: "xavier"
#type: "constant"
#value: 0
}
bias_filler {
type: "constant"
value: 0
}
}
}
#########################
layer {
name: "fc4_5"
type: "InnerProduct"
bottom: "fc4"
top: "fc4_5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 64
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4_5"
type: "PReLU"
bottom: "fc4_5"
top: "fc4_5"
}
layer {
name: "fc5_5"
type: "InnerProduct"
bottom: "fc4_5"
top: "fc5_5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 2
weight_filler {
type: "xavier"
#type: "constant"
#value: 0
}
bias_filler {
type: "constant"
value: 0
}
}
}
#########################

864
deploy/mtcnn_detector.py
View File

@@ -1,864 +0,0 @@
# coding: utf-8
import os
import mxnet as mx
import numpy as np
import math
import cv2
from multiprocessing import Pool
from itertools import repeat
try:
from itertools import izip
except ImportError:
izip = zip
def nms(boxes, overlap_threshold, mode='Union'):
"""
non max suppression
Parameters:
----------
box: numpy array n x 5
input bbox array
overlap_threshold: float number
threshold of overlap
mode: float number
how to compute overlap ratio, 'Union' or 'Min'
Returns:
-------
index array of the selected bbox
"""
# if there are no boxes, return an empty list
if len(boxes) == 0:
return []
# if the bounding boxes integers, convert them to floats
if boxes.dtype.kind == "i":
boxes = boxes.astype("float")
# initialize the list of picked indexes
pick = []
# grab the coordinates of the bounding boxes
x1, y1, x2, y2, score = [boxes[:, i] for i in range(5)]
area = (x2 - x1 + 1) * (y2 - y1 + 1)
idxs = np.argsort(score)
# keep looping while some indexes still remain in the indexes list
while len(idxs) > 0:
# grab the last index in the indexes list and add the index value to the list of picked indexes
last = len(idxs) - 1
i = idxs[last]
pick.append(i)
xx1 = np.maximum(x1[i], x1[idxs[:last]])
yy1 = np.maximum(y1[i], y1[idxs[:last]])
xx2 = np.minimum(x2[i], x2[idxs[:last]])
yy2 = np.minimum(y2[i], y2[idxs[:last]])
# compute the width and height of the bounding box
w = np.maximum(0, xx2 - xx1 + 1)
h = np.maximum(0, yy2 - yy1 + 1)
inter = w * h
if mode == 'Min':
overlap = inter / np.minimum(area[i], area[idxs[:last]])
else:
overlap = inter / (area[i] + area[idxs[:last]] - inter)
# delete all indexes from the index list that have
idxs = np.delete(
idxs,
np.concatenate(([last], np.where(overlap > overlap_threshold)[0])))
return pick
def adjust_input(in_data):
"""
adjust the input from (h, w, c) to ( 1, c, h, w) for network input
Parameters:
----------
in_data: numpy array of shape (h, w, c)
input data
Returns:
-------
out_data: numpy array of shape (1, c, h, w)
reshaped array
"""
if in_data.dtype is not np.dtype('float32'):
out_data = in_data.astype(np.float32)
else:
out_data = in_data
out_data = out_data.transpose((2, 0, 1))
out_data = np.expand_dims(out_data, 0)
out_data = (out_data - 127.5) * 0.0078125
return out_data
def generate_bbox(map, reg, scale, threshold):
"""
generate bbox from feature map
Parameters:
----------
map: numpy array , n x m x 1
detect score for each position
reg: numpy array , n x m x 4
bbox
scale: float number
scale of this detection
threshold: float number
detect threshold
Returns:
-------
bbox array
"""
stride = 2
cellsize = 12
t_index = np.where(map > threshold)
# find nothing
if t_index[0].size == 0:
return np.array([])
dx1, dy1, dx2, dy2 = [reg[0, i, t_index[0], t_index[1]] for i in range(4)]
reg = np.array([dx1, dy1, dx2, dy2])
score = map[t_index[0], t_index[1]]
boundingbox = np.vstack([
np.round((stride * t_index[1] + 1) / scale),
np.round((stride * t_index[0] + 1) / scale),
np.round((stride * t_index[1] + 1 + cellsize) / scale),
np.round((stride * t_index[0] + 1 + cellsize) / scale), score, reg
])
return boundingbox.T
def detect_first_stage(img, net, scale, threshold):
"""
run PNet for first stage
Parameters:
----------
img: numpy array, bgr order
input image
scale: float number
how much should the input image scale
net: PNet
worker
Returns:
-------
total_boxes : bboxes
"""
height, width, _ = img.shape
hs = int(math.ceil(height * scale))
ws = int(math.ceil(width * scale))
im_data = cv2.resize(img, (ws, hs))
# adjust for the network input
input_buf = adjust_input(im_data)
output = net.predict(input_buf)
boxes = generate_bbox(output[1][0, 1, :, :], output[0], scale, threshold)
if boxes.size == 0:
return None
# nms
pick = nms(boxes[:, 0:5], 0.5, mode='Union')
boxes = boxes[pick]
return boxes
def detect_first_stage_warpper(args):
return detect_first_stage(*args)
class MtcnnDetector(object):
"""
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks
see https://github.com/kpzhang93/MTCNN_face_detection_alignment
this is a mxnet version
"""
def __init__(self,
model_folder='.',
minsize=20,
threshold=[0.6, 0.7, 0.8],
factor=0.709,
num_worker=1,
accurate_landmark=False,
ctx=mx.cpu()):
"""
Initialize the detector
Parameters:
----------
model_folder : string
path for the models
minsize : float number
minimal face to detect
threshold : float number
detect threshold for 3 stages
factor: float number
scale factor for image pyramid
num_worker: int number
number of processes we use for first stage
accurate_landmark: bool
use accurate landmark localization or not
"""
self.num_worker = num_worker
self.accurate_landmark = accurate_landmark
# load 4 models from folder
models = ['det1', 'det2', 'det3', 'det4']
models = [os.path.join(model_folder, f) for f in models]
self.PNets = []
for i in range(num_worker):
workner_net = mx.model.FeedForward.load(models[0], 1, ctx=ctx)
self.PNets.append(workner_net)
#self.Pool = Pool(num_worker)
self.RNet = mx.model.FeedForward.load(models[1], 1, ctx=ctx)
self.ONet = mx.model.FeedForward.load(models[2], 1, ctx=ctx)
self.LNet = mx.model.FeedForward.load(models[3], 1, ctx=ctx)
self.minsize = float(minsize)
self.factor = float(factor)
self.threshold = threshold
def convert_to_square(self, bbox):
"""
convert bbox to square
Parameters:
----------
bbox: numpy array , shape n x 5
input bbox
Returns:
-------
square bbox
"""
square_bbox = bbox.copy()
h = bbox[:, 3] - bbox[:, 1] + 1
w = bbox[:, 2] - bbox[:, 0] + 1
max_side = np.maximum(h, w)
square_bbox[:, 0] = bbox[:, 0] + w * 0.5 - max_side * 0.5
square_bbox[:, 1] = bbox[:, 1] + h * 0.5 - max_side * 0.5
square_bbox[:, 2] = square_bbox[:, 0] + max_side - 1
square_bbox[:, 3] = square_bbox[:, 1] + max_side - 1
return square_bbox
def calibrate_box(self, bbox, reg):
"""
calibrate bboxes
Parameters:
----------
bbox: numpy array, shape n x 5
input bboxes
reg: numpy array, shape n x 4
bboxex adjustment
Returns:
-------
bboxes after refinement
"""
w = bbox[:, 2] - bbox[:, 0] + 1
w = np.expand_dims(w, 1)
h = bbox[:, 3] - bbox[:, 1] + 1
h = np.expand_dims(h, 1)
reg_m = np.hstack([w, h, w, h])
aug = reg_m * reg
bbox[:, 0:4] = bbox[:, 0:4] + aug
return bbox
def pad(self, bboxes, w, h):
"""
pad the the bboxes, alse restrict the size of it
Parameters:
----------
bboxes: numpy array, n x 5
input bboxes
w: float number
width of the input image
h: float number
height of the input image
Returns :
------s
dy, dx : numpy array, n x 1
start point of the bbox in target image
edy, edx : numpy array, n x 1
end point of the bbox in target image
y, x : numpy array, n x 1
start point of the bbox in original image
ex, ex : numpy array, n x 1
end point of the bbox in original image
tmph, tmpw: numpy array, n x 1
height and width of the bbox
"""
tmpw, tmph = bboxes[:, 2] - bboxes[:, 0] + 1, bboxes[:,
3] - bboxes[:,
1] + 1
num_box = bboxes.shape[0]
dx, dy = np.zeros((num_box, )), np.zeros((num_box, ))
edx, edy = tmpw.copy() - 1, tmph.copy() - 1
x, y, ex, ey = bboxes[:, 0], bboxes[:, 1], bboxes[:, 2], bboxes[:, 3]
tmp_index = np.where(ex > w - 1)
edx[tmp_index] = tmpw[tmp_index] + w - 2 - ex[tmp_index]
ex[tmp_index] = w - 1
tmp_index = np.where(ey > h - 1)
edy[tmp_index] = tmph[tmp_index] + h - 2 - ey[tmp_index]
ey[tmp_index] = h - 1
tmp_index = np.where(x < 0)
dx[tmp_index] = 0 - x[tmp_index]
x[tmp_index] = 0
tmp_index = np.where(y < 0)
dy[tmp_index] = 0 - y[tmp_index]
y[tmp_index] = 0
return_list = [dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph]
return_list = [item.astype(np.int32) for item in return_list]
return return_list
def slice_index(self, number):
"""
slice the index into (n,n,m), m < n
Parameters:
----------
number: int number
number
"""
def chunks(l, n):
"""Yield successive n-sized chunks from l."""
for i in range(0, len(l), n):
yield l[i:i + n]
num_list = range(number)
return list(chunks(num_list, self.num_worker))
def detect_face_limited(self, img, det_type=2):
height, width, _ = img.shape
if det_type >= 2:
total_boxes = np.array(
[[0.0, 0.0, img.shape[1], img.shape[0], 0.9]],
dtype=np.float32)
num_box = total_boxes.shape[0]
# pad the bbox
[dy, edy, dx, edx, y, ey, x, ex, tmpw,
tmph] = self.pad(total_boxes, width, height)
# (3, 24, 24) is the input shape for RNet
input_buf = np.zeros((num_box, 3, 24, 24), dtype=np.float32)
for i in range(num_box):
tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.uint8)
tmp[dy[i]:edy[i] + 1,
dx[i]:edx[i] + 1, :] = img[y[i]:ey[i] + 1,
x[i]:ex[i] + 1, :]
input_buf[i, :, :, :] = adjust_input(cv2.resize(tmp, (24, 24)))
output = self.RNet.predict(input_buf)
# filter the total_boxes with threshold
passed = np.where(output[1][:, 1] > self.threshold[1])
total_boxes = total_boxes[passed]
if total_boxes.size == 0:
return None
total_boxes[:, 4] = output[1][passed, 1].reshape((-1, ))
reg = output[0][passed]
# nms
pick = nms(total_boxes, 0.7, 'Union')
total_boxes = total_boxes[pick]
total_boxes = self.calibrate_box(total_boxes, reg[pick])
total_boxes = self.convert_to_square(total_boxes)
total_boxes[:, 0:4] = np.round(total_boxes[:, 0:4])
else:
total_boxes = np.array(
[[0.0, 0.0, img.shape[1], img.shape[0], 0.9]],
dtype=np.float32)
num_box = total_boxes.shape[0]
[dy, edy, dx, edx, y, ey, x, ex, tmpw,
tmph] = self.pad(total_boxes, width, height)
# (3, 48, 48) is the input shape for ONet
input_buf = np.zeros((num_box, 3, 48, 48), dtype=np.float32)
for i in range(num_box):
tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.float32)
tmp[dy[i]:edy[i] + 1, dx[i]:edx[i] + 1, :] = img[y[i]:ey[i] + 1,
x[i]:ex[i] + 1, :]
input_buf[i, :, :, :] = adjust_input(cv2.resize(tmp, (48, 48)))
output = self.ONet.predict(input_buf)
#print(output[2])
# filter the total_boxes with threshold
passed = np.where(output[2][:, 1] > self.threshold[2])
total_boxes = total_boxes[passed]
if total_boxes.size == 0:
return None
total_boxes[:, 4] = output[2][passed, 1].reshape((-1, ))
reg = output[1][passed]
points = output[0][passed]
# compute landmark points
bbw = total_boxes[:, 2] - total_boxes[:, 0] + 1
bbh = total_boxes[:, 3] - total_boxes[:, 1] + 1
points[:, 0:5] = np.expand_dims(
total_boxes[:, 0], 1) + np.expand_dims(bbw, 1) * points[:, 0:5]
points[:, 5:10] = np.expand_dims(
total_boxes[:, 1], 1) + np.expand_dims(bbh, 1) * points[:, 5:10]
# nms
total_boxes = self.calibrate_box(total_boxes, reg)
pick = nms(total_boxes, 0.7, 'Min')
total_boxes = total_boxes[pick]
points = points[pick]
if not self.accurate_landmark:
return total_boxes, points
#############################################
# extended stage
#############################################
num_box = total_boxes.shape[0]
patchw = np.maximum(total_boxes[:, 2] - total_boxes[:, 0] + 1,
total_boxes[:, 3] - total_boxes[:, 1] + 1)
patchw = np.round(patchw * 0.25)
# make it even
patchw[np.where(np.mod(patchw, 2) == 1)] += 1
input_buf = np.zeros((num_box, 15, 24, 24), dtype=np.float32)
for i in range(5):
x, y = points[:, i], points[:, i + 5]
x, y = np.round(x - 0.5 * patchw), np.round(y - 0.5 * patchw)
[dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph] = self.pad(
np.vstack([x, y, x + patchw - 1, y + patchw - 1]).T, width,
height)
for j in range(num_box):
tmpim = np.zeros((tmpw[j], tmpw[j], 3), dtype=np.float32)
tmpim[dy[j]:edy[j] + 1,
dx[j]:edx[j] + 1, :] = img[y[j]:ey[j] + 1,
x[j]:ex[j] + 1, :]
input_buf[j, i * 3:i * 3 + 3, :, :] = adjust_input(
cv2.resize(tmpim, (24, 24)))
output = self.LNet.predict(input_buf)
pointx = np.zeros((num_box, 5))
pointy = np.zeros((num_box, 5))
for k in range(5):
# do not make a large movement
tmp_index = np.where(np.abs(output[k] - 0.5) > 0.35)
output[k][tmp_index[0]] = 0.5
pointx[:, k] = np.round(points[:, k] -
0.5 * patchw) + output[k][:, 0] * patchw
pointy[:, k] = np.round(points[:, k + 5] -
0.5 * patchw) + output[k][:, 1] * patchw
points = np.hstack([pointx, pointy])
points = points.astype(np.int32)
return total_boxes, points
def detect_face(self, img, det_type=0):
"""
detect face over img
Parameters:
----------
img: numpy array, bgr order of shape (1, 3, n, m)
input image
Retures:
-------
bboxes: numpy array, n x 5 (x1,y2,x2,y2,score)
bboxes
points: numpy array, n x 10 (x1, x2 ... x5, y1, y2 ..y5)
landmarks
"""
# check input
height, width, _ = img.shape
if det_type == 0:
MIN_DET_SIZE = 12
if img is None:
return None
# only works for color image
if len(img.shape) != 3:
return None
# detected boxes
total_boxes = []
minl = min(height, width)
# get all the valid scales
scales = []
m = MIN_DET_SIZE / self.minsize
minl *= m
factor_count = 0
while minl > MIN_DET_SIZE:
scales.append(m * self.factor**factor_count)
minl *= self.factor
factor_count += 1
#############################################
# first stage
#############################################
#for scale in scales:
# return_boxes = self.detect_first_stage(img, scale, 0)
# if return_boxes is not None:
# total_boxes.append(return_boxes)
sliced_index = self.slice_index(len(scales))
total_boxes = []
for batch in sliced_index:
#local_boxes = self.Pool.map( detect_first_stage_warpper, \
# izip(repeat(img), self.PNets[:len(batch)], [scales[i] for i in batch], repeat(self.threshold[0])) )
local_boxes = map( detect_first_stage_warpper, \
izip(repeat(img), self.PNets[:len(batch)], [scales[i] for i in batch], repeat(self.threshold[0])) )
total_boxes.extend(local_boxes)
# remove the Nones
total_boxes = [i for i in total_boxes if i is not None]
if len(total_boxes) == 0:
return None
total_boxes = np.vstack(total_boxes)
if total_boxes.size == 0:
return None
# merge the detection from first stage
pick = nms(total_boxes[:, 0:5], 0.7, 'Union')
total_boxes = total_boxes[pick]
bbw = total_boxes[:, 2] - total_boxes[:, 0] + 1
bbh = total_boxes[:, 3] - total_boxes[:, 1] + 1
# refine the bboxes
total_boxes = np.vstack([
total_boxes[:, 0] + total_boxes[:, 5] * bbw,
total_boxes[:, 1] + total_boxes[:, 6] * bbh,
total_boxes[:, 2] + total_boxes[:, 7] * bbw,
total_boxes[:, 3] + total_boxes[:, 8] * bbh, total_boxes[:, 4]
])
total_boxes = total_boxes.T
total_boxes = self.convert_to_square(total_boxes)
total_boxes[:, 0:4] = np.round(total_boxes[:, 0:4])
else:
total_boxes = np.array(
[[0.0, 0.0, img.shape[1], img.shape[0], 0.9]],
dtype=np.float32)
#############################################
# second stage
#############################################
num_box = total_boxes.shape[0]
# pad the bbox
[dy, edy, dx, edx, y, ey, x, ex, tmpw,
tmph] = self.pad(total_boxes, width, height)
# (3, 24, 24) is the input shape for RNet
input_buf = np.zeros((num_box, 3, 24, 24), dtype=np.float32)
for i in range(num_box):
tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.uint8)
tmp[dy[i]:edy[i] + 1, dx[i]:edx[i] + 1, :] = img[y[i]:ey[i] + 1,
x[i]:ex[i] + 1, :]
input_buf[i, :, :, :] = adjust_input(cv2.resize(tmp, (24, 24)))
output = self.RNet.predict(input_buf)
# filter the total_boxes with threshold
passed = np.where(output[1][:, 1] > self.threshold[1])
total_boxes = total_boxes[passed]
if total_boxes.size == 0:
return None
total_boxes[:, 4] = output[1][passed, 1].reshape((-1, ))
reg = output[0][passed]
# nms
pick = nms(total_boxes, 0.7, 'Union')
total_boxes = total_boxes[pick]
total_boxes = self.calibrate_box(total_boxes, reg[pick])
total_boxes = self.convert_to_square(total_boxes)
total_boxes[:, 0:4] = np.round(total_boxes[:, 0:4])
#############################################
# third stage
#############################################
num_box = total_boxes.shape[0]
# pad the bbox
[dy, edy, dx, edx, y, ey, x, ex, tmpw,
tmph] = self.pad(total_boxes, width, height)
# (3, 48, 48) is the input shape for ONet
input_buf = np.zeros((num_box, 3, 48, 48), dtype=np.float32)
for i in range(num_box):
tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.float32)
tmp[dy[i]:edy[i] + 1, dx[i]:edx[i] + 1, :] = img[y[i]:ey[i] + 1,
x[i]:ex[i] + 1, :]
input_buf[i, :, :, :] = adjust_input(cv2.resize(tmp, (48, 48)))
output = self.ONet.predict(input_buf)
# filter the total_boxes with threshold
passed = np.where(output[2][:, 1] > self.threshold[2])
total_boxes = total_boxes[passed]
if total_boxes.size == 0:
return None
total_boxes[:, 4] = output[2][passed, 1].reshape((-1, ))
reg = output[1][passed]
points = output[0][passed]
# compute landmark points
bbw = total_boxes[:, 2] - total_boxes[:, 0] + 1
bbh = total_boxes[:, 3] - total_boxes[:, 1] + 1
points[:, 0:5] = np.expand_dims(
total_boxes[:, 0], 1) + np.expand_dims(bbw, 1) * points[:, 0:5]
points[:, 5:10] = np.expand_dims(
total_boxes[:, 1], 1) + np.expand_dims(bbh, 1) * points[:, 5:10]
# nms
total_boxes = self.calibrate_box(total_boxes, reg)
pick = nms(total_boxes, 0.7, 'Min')
total_boxes = total_boxes[pick]
points = points[pick]
if not self.accurate_landmark:
return total_boxes, points
#############################################
# extended stage
#############################################
num_box = total_boxes.shape[0]
patchw = np.maximum(total_boxes[:, 2] - total_boxes[:, 0] + 1,
total_boxes[:, 3] - total_boxes[:, 1] + 1)
patchw = np.round(patchw * 0.25)
# make it even
patchw[np.where(np.mod(patchw, 2) == 1)] += 1
input_buf = np.zeros((num_box, 15, 24, 24), dtype=np.float32)
for i in range(5):
x, y = points[:, i], points[:, i + 5]
x, y = np.round(x - 0.5 * patchw), np.round(y - 0.5 * patchw)
[dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph] = self.pad(
np.vstack([x, y, x + patchw - 1, y + patchw - 1]).T, width,
height)
for j in range(num_box):
tmpim = np.zeros((tmpw[j], tmpw[j], 3), dtype=np.float32)
tmpim[dy[j]:edy[j] + 1,
dx[j]:edx[j] + 1, :] = img[y[j]:ey[j] + 1,
x[j]:ex[j] + 1, :]
input_buf[j, i * 3:i * 3 + 3, :, :] = adjust_input(
cv2.resize(tmpim, (24, 24)))
output = self.LNet.predict(input_buf)
pointx = np.zeros((num_box, 5))
pointy = np.zeros((num_box, 5))
for k in range(5):
# do not make a large movement
tmp_index = np.where(np.abs(output[k] - 0.5) > 0.35)
output[k][tmp_index[0]] = 0.5
pointx[:, k] = np.round(points[:, k] -
0.5 * patchw) + output[k][:, 0] * patchw
pointy[:, k] = np.round(points[:, k + 5] -
0.5 * patchw) + output[k][:, 1] * patchw
points = np.hstack([pointx, pointy])
points = points.astype(np.int32)
return total_boxes, points
def list2colmatrix(self, pts_list):
"""
convert list to column matrix
Parameters:
----------
pts_list:
input list
Retures:
-------
colMat:
"""
assert len(pts_list) > 0
colMat = []
for i in range(len(pts_list)):
colMat.append(pts_list[i][0])
colMat.append(pts_list[i][1])
colMat = np.matrix(colMat).transpose()
return colMat
def find_tfrom_between_shapes(self, from_shape, to_shape):
"""
find transform between shapes
Parameters:
----------
from_shape:
to_shape:
Retures:
-------
tran_m:
tran_b:
"""
assert from_shape.shape[0] == to_shape.shape[
0] and from_shape.shape[0] % 2 == 0
sigma_from = 0.0
sigma_to = 0.0
cov = np.matrix([[0.0, 0.0], [0.0, 0.0]])
# compute the mean and cov
from_shape_points = from_shape.reshape(from_shape.shape[0] / 2, 2)
to_shape_points = to_shape.reshape(to_shape.shape[0] / 2, 2)
mean_from = from_shape_points.mean(axis=0)
mean_to = to_shape_points.mean(axis=0)
for i in range(from_shape_points.shape[0]):
temp_dis = np.linalg.norm(from_shape_points[i] - mean_from)
sigma_from += temp_dis * temp_dis
temp_dis = np.linalg.norm(to_shape_points[i] - mean_to)
sigma_to += temp_dis * temp_dis
cov += (to_shape_points[i].transpose() -
mean_to.transpose()) * (from_shape_points[i] - mean_from)
sigma_from = sigma_from / to_shape_points.shape[0]
sigma_to = sigma_to / to_shape_points.shape[0]
cov = cov / to_shape_points.shape[0]
# compute the affine matrix
s = np.matrix([[1.0, 0.0], [0.0, 1.0]])
u, d, vt = np.linalg.svd(cov)
if np.linalg.det(cov) < 0:
if d[1] < d[0]:
s[1, 1] = -1
else:
s[0, 0] = -1
r = u * s * vt
c = 1.0
if sigma_from != 0:
c = 1.0 / sigma_from * np.trace(np.diag(d) * s)
tran_b = mean_to.transpose() - c * r * mean_from.transpose()
tran_m = c * r
return tran_m, tran_b
def extract_image_chips(self, img, points, desired_size=256, padding=0):
"""
crop and align face
Parameters:
----------
img: numpy array, bgr order of shape (1, 3, n, m)
input image
points: numpy array, n x 10 (x1, x2 ... x5, y1, y2 ..y5)
desired_size: default 256
padding: default 0
Retures:
-------
crop_imgs: list, n
cropped and aligned faces
"""
crop_imgs = []
for p in points:
shape = []
for k in range(len(p) / 2):
shape.append(p[k])
shape.append(p[k + 5])
if padding > 0:
padding = padding
else:
padding = 0
# average positions of face points
mean_face_shape_x = [
0.224152, 0.75610125, 0.490127, 0.254149, 0.726104
]
mean_face_shape_y = [
0.2119465, 0.2119465, 0.628106, 0.780233, 0.780233
]
from_points = []
to_points = []
for i in range(len(shape) / 2):
x = (padding + mean_face_shape_x[i]) / (2 * padding +
1) * desired_size
y = (padding + mean_face_shape_y[i]) / (2 * padding +
1) * desired_size
to_points.append([x, y])
from_points.append([shape[2 * i], shape[2 * i + 1]])
# convert the points to Mat
from_mat = self.list2colmatrix(from_points)
to_mat = self.list2colmatrix(to_points)
# compute the similar transfrom
tran_m, tran_b = self.find_tfrom_between_shapes(from_mat, to_mat)
probe_vec = np.matrix([1.0, 0.0]).transpose()
probe_vec = tran_m * probe_vec
scale = np.linalg.norm(probe_vec)
angle = 180.0 / math.pi * math.atan2(probe_vec[1, 0], probe_vec[0,
0])
from_center = [(shape[0] + shape[2]) / 2.0,
(shape[1] + shape[3]) / 2.0]
to_center = [0, 0]
to_center[1] = desired_size * 0.4
to_center[0] = desired_size * 0.5
ex = to_center[0] - from_center[0]
ey = to_center[1] - from_center[1]
rot_mat = cv2.getRotationMatrix2D((from_center[0], from_center[1]),
-1 * angle, scale)
rot_mat[0][2] += ex
rot_mat[1][2] += ey
chips = cv2.warpAffine(img, rot_mat, (desired_size, desired_size))
crop_imgs.append(chips)
return crop_imgs

42
detection/README.md Normal file
View File

@@ -0,0 +1,42 @@
## Face Detection
<div align="left">
<img src="https://insightface.ai/assets/img/custom/logo3.jpg" width="240"/>
</div>
## Introduction
These are the face detection methods of [InsightFace](https://insightface.ai)
<div align="left">
<img src="https://insightface.ai/assets/img/github/11513D05.jpg" width="800"/>
</div>
### Datasets
Please refer to [datasets](_datasets_) page for the details of face detection datasets used for training and evaluation.
### Evaluation
Please refer to [evaluation](_evaluation_) page for the details of face recognition evaluation.
## Methods
Supported methods:
- [x] [RetinaFace (CVPR'2020)](retinaface)
- [x] [SCRFD (Arxiv'2021)](scrfd)
## Contributing
We appreciate all contributions to improve the face detection model zoo of InsightFace.

4
detection/RetinaFace/README.md
View File

@@ -4,9 +4,9 @@
RetinaFace is a practical single-stage [SOTA](http://shuoyang1213.me/WIDERFACE/WiderFace_Results.html) face detector which is initially introduced in [arXiv technical report](https://arxiv.org/abs/1905.00641) and then accepted by [CVPR 2020](https://openaccess.thecvf.com/content_CVPR_2020/html/Deng_RetinaFace_Single-Shot_Multi-Level_Face_Localisation_in_the_Wild_CVPR_2020_paper.html).
![demoimg1](https://github.com/deepinsight/insightface/blob/master/resources/11513D05.jpg)
![demoimg1](https://insightface.ai/assets/img/github/11513D05.jpg)
![demoimg2](https://github.com/deepinsight/insightface/blob/master/resources/widerfacevaltest.png)
![demoimg2](https://insightface.ai/assets/img/github/widerfacevaltest.png)
## Data

2
detection/RetinaFaceAntiCov/README.md → detection/retinaface_anticov/README.md
View File

@@ -4,7 +4,7 @@
RetinaFace-Anti-Cov is a customized one stage face detector to help people protect themselves from CovID-19.
![demoimg1](https://github.com/deepinsight/insightface/blob/master/resources/cov_test.jpg)
![demoimg1](https://insightface.ai/assets/img/github/cov_test.jpg)
## Testing

0
detection/RetinaFaceAntiCov/rcnn/processing/__init__.py → detection/retinaface_anticov/rcnn/processing/__init__.py
View File

0
detection/RetinaFaceAntiCov/rcnn/processing/assign_levels.py → detection/retinaface_anticov/rcnn/processing/assign_levels.py
View File

0
detection/RetinaFaceAntiCov/rcnn/processing/bbox_regression.py → detection/retinaface_anticov/rcnn/processing/bbox_regression.py
View File

0
detection/RetinaFaceAntiCov/rcnn/processing/bbox_transform.py → detection/retinaface_anticov/rcnn/processing/bbox_transform.py
View File

0
detection/RetinaFaceAntiCov/rcnn/processing/bbox_transform.py.orig → detection/retinaface_anticov/rcnn/processing/bbox_transform.py.orig
View File

0
detection/RetinaFaceAntiCov/rcnn/processing/generate_anchor.py → detection/retinaface_anticov/rcnn/processing/generate_anchor.py
View File

0
detection/RetinaFaceAntiCov/rcnn/processing/nms.py → detection/retinaface_anticov/rcnn/processing/nms.py
View File

0
detection/RetinaFaceAntiCov/retinaface_cov.py → detection/retinaface_anticov/retinaface_cov.py
View File

0
detection/RetinaFaceAntiCov/test.py → detection/retinaface_anticov/test.py
View File

520
evaluation/IJB/IJBB_Evaluation_MS1MV2.ipynb
View File

File diff suppressed because one or more lines are too long

535
evaluation/IJB/IJBB_Evaluation_VGG2.ipynb
View File

File diff suppressed because one or more lines are too long

532
evaluation/IJB/IJBC_Evaluation_MS1MV2.ipynb
View File

File diff suppressed because one or more lines are too long

532
evaluation/IJB/IJBC_Evaluation_VGG2.ipynb
View File

File diff suppressed because one or more lines are too long

19
evaluation/IJB/readme.txt
View File

@@ -1,19 +0,0 @@
To reproduce the figures and tables in the notebook, please download everything (model, code, data and meta info) from here:
[Dropbox] https://www.dropbox.com/s/33a6haw7v79e5qe/IJB_release.tar?dl=0
or
[Baidu Cloud] https://pan.baidu.com/s/1oer0p4_mcOrs4cfdeWfbFg
Please apply for the IJB-B and IJB-C by yourself and strictly follow their distribution licenses.
Aknowledgement
Great thanks for Weidi Xie's instruction [2,3,4,5] to evaluate ArcFace [1] on IJB-B[6] and IJB-C[7].
[1] Jiankang Deng, Jia Guo, Niannan Xue, Stefanos Zafeiriou. Arcface: Additive angular margin loss for deep face recognition[J]. arXiv:1801.07698, 2018.
[2] https://github.com/ox-vgg/vgg_face2.
[3] Qiong Cao, Li Shen, Weidi Xie, Omkar M Parkhi, Andrew Zisserman. VGGFace2: A dataset for recognising faces across pose and age. FG, 2018.
[4] Weidi Xie, Andrew Zisserman. Multicolumn Networks for Face Recognition. BMVC 2018.
[5] Weidi Xie, Li Shen, Andrew Zisserman. Comparator Networks. ECCV, 2018.
[6] Whitelam, Cameron, Emma Taborsky, Austin Blanton, Brianna Maze, Jocelyn C. Adams, Tim Miller, Nathan D. Kalka et al. IARPA Janus Benchmark-B Face Dataset. CVPR Workshops, 2017.
[7] Maze, Brianna, Jocelyn Adams, James A. Duncan, Nathan Kalka, Tim Miller, Charles Otto, Anil K. Jain et al. IARPA Janus Benchmark–C: Face Dataset and Protocol. ICB, 2018.

4
examples/README.md Normal file
View File

@@ -0,0 +1,4 @@
InsightFace Example
---
Before running the examples, please install insightface package via `pip install -U insightface`

34
examples/demo_analysis.py Normal file
View File

@@ -0,0 +1,34 @@
import argparse
import cv2
import sys
import numpy as np
import insightface
from insightface.app import FaceAnalysis
from insightface.data import get_image as ins_get_image
assert insightface.__version__>='0.3'
parser = argparse.ArgumentParser(description='insightface app test')
# general
parser.add_argument('--ctx', default=0, type=int, help='ctx id, <0 means using cpu')
parser.add_argument('--det-size', default=640, type=int, help='detection size')
args = parser.parse_args()
app = FaceAnalysis()
app.prepare(ctx_id=args.ctx, det_size=(args.det_size,args.det_size))
img = ins_get_image('t1')
faces = app.get(img)
assert len(faces)==6
rimg = app.draw_on(img, faces)
cv2.imwrite("./t1_output.jpg", rimg)
# then print all-to-all face similarity
feats = []
for face in faces:
feats.append(face.normed_embedding)
feats = np.array(feats, dtype=np.float32)
sims = np.dot(feats, feats.T)
print(sims)

22
examples/mask_renderer.py Normal file
View File

@@ -0,0 +1,22 @@
import os, sys, datetime
import numpy as np
import os.path as osp
import cv2
import insightface
from insightface.app import MaskRenderer
from insightface.data import get_image as ins_get_image
if __name__ == "__main__":
#make sure that you have download correct insightface model pack.
#make sure that BFM.mat and BFM_UV.mat have been generated
tool = MaskRenderer()
tool.prepare(ctx_id=0, det_size=(128,128))
image = ins_get_image('Tom_Hanks_54745')
mask_image = "mask_blue"
params = tool.build_params(image)
mask_out = tool.render_mask(image, mask_image, params)
cv2.imwrite('output_mask.jpg', mask_out)

73
deploy/mxnet_to_ort.py → examples/mxnet_to_onnx.py
View File

@@ -2,10 +2,13 @@ import sys
import os
import argparse
import onnx
import json
import mxnet as mx
from onnx import helper
from onnx import TensorProto
from onnx import numpy_helper
import onnxruntime
import cv2
print('mxnet version:', mx.__version__)
print('onnx version:', onnx.__version__)
@@ -23,12 +26,15 @@ def create_map(graph_member_list):
return member_map
parser = argparse.ArgumentParser(description='convert arcface models to onnx')
parser = argparse.ArgumentParser(description='convert mxnet model to onnx')
# general
parser.add_argument('params', default='./r100a/model-0000.params', help='mxnet params to load.')
parser.add_argument('output', default='./r100a.onnx', help='path to write onnx model.')
parser.add_argument('--eps', default=1.0e-8, type=float, help='eps for weights.')
parser.add_argument('--input-shape', default='3,112,112', help='input shape.')
parser.add_argument('--check', action='store_true')
parser.add_argument('--input-mean', default=0.0, type=float, help='input mean for checking.')
parser.add_argument('--input-std', default=1.0, type=float, help='input std for checking.')
args = parser.parse_args()
input_shape = (1,) + tuple( [int(x) for x in args.input_shape.split(',')] )
@@ -41,6 +47,29 @@ assert os.path.exists(sym_file)
assert os.path.exists(params_file)
sym, arg_params, aux_params = mx.model.load_checkpoint(prefix, epoch)
nodes = json.loads(sym.tojson())['nodes']
bn_fixgamma_list = []
for nodeid, node in enumerate(nodes):
if node['op'] == 'BatchNorm':
attr = node['attrs']
fix_gamma = False
if attr is not None and 'fix_gamma' in attr:
if str(attr['fix_gamma']).lower()=='true':
fix_gamma = True
if fix_gamma:
bn_fixgamma_list.append(node['name'])
#print(node, fix_gamma)
print('fixgamma list:', bn_fixgamma_list)
layer = None
#layer = 'conv_2_dw_relu' #for debug
if layer is not None:
all_layers = sym.get_internals()
sym = all_layers[layer + '_output']
eps = args.eps
arg = {}
@@ -50,24 +79,27 @@ ac = 0
for k in arg_params:
v = arg_params[k]
nv = v.asnumpy()
#print(k, nv.dtype)
nv = nv.astype(np.float32)
#print(k, nv.shape)
if k.endswith('_gamma'):
bnname = k[:-6]
if bnname in bn_fixgamma_list:
nv[:] = 1.0
ac += nv.size
invalid += np.count_nonzero(np.abs(nv)<eps)
nv[np.abs(nv) < eps] = 0.0
arg[k] = mx.nd.array(nv, dtype='float32')
print(invalid, ac)
arg_params = arg
invalid = 0
ac = 0
for k in aux_params:
v = aux_params[k]
nv = v.asnumpy().astype(np.float32)
ac += nv.size
invalid += np.count_nonzero(np.abs(nv)<eps)
nv[np.abs(nv) < eps] = 0.0
aux[k] = mx.nd.array(nv, dtype='float32')
print(invalid, ac)
aux_params = aux
all_args = {}
@@ -75,6 +107,7 @@ all_args.update(arg_params)
all_args.update(aux_params)
converted_model_path = onnx_mxnet.export_model(sym, all_args, [input_shape], np.float32, args.output, opset_version=11)
model = onnx.load(args.output)
graph = model.graph
input_map = create_map(graph.input)
@@ -90,8 +123,8 @@ for input_name in input_map.keys():
node = node_map[node_name]
if node.op_type!='PRelu':
continue
input_shape = input_map[input_name].type.tensor_type.shape.dim
input_dim_val=input_shape[0].dim_value
_input_shape = input_map[input_name].type.tensor_type.shape.dim
input_dim_val=_input_shape[0].dim_value
graph.initializer.remove(init_map[input_name])
weight_array = numpy_helper.to_array(init_map[input_name])
@@ -113,3 +146,31 @@ graph.input[0].type.tensor_type.shape.dim[0].dim_param = 'None'
onnx.save(model, args.output)
#start to check correctness
if args.check:
im_size = tuple(input_shape[2:])+(3,)
img = np.random.randint(0, 256, size=im_size, dtype=np.uint8)
input_size = tuple(input_shape[2:4][::-1])
input_std = args.input_std
input_mean = args.input_mean
#print(img.shape, input_size)
img = cv2.dnn.blobFromImage(img, 1.0/input_std, input_size, (input_mean, input_mean, input_mean), swapRB=True)
ctx = mx.cpu()
model = mx.mod.Module(symbol=sym, context=ctx, label_names = None)
model.bind(for_training=False, data_shapes=[('data', input_shape)])
_, arg_params, aux_params = mx.model.load_checkpoint(prefix, epoch) #reload original params
model.set_params(arg_params, aux_params)
data = mx.nd.array(img)
db = mx.io.DataBatch(data=(data,))
model.forward(db, is_train=False)
x1 = model.get_outputs()[-1].asnumpy()
session = onnxruntime.InferenceSession(args.output, None)
input_name = session.get_inputs()[0].name
output_name = session.get_outputs()[0].name
x2 = session.run([output_name], {input_name : img})[0]
print(x1.shape, x2.shape)
print(x1.flatten()[:20])
print(x2.flatten()[:20])

BIN
gender-age/Tom_Hanks_54745.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 12 KiB

281
gender-age/data.py
View File

@@ -1,281 +0,0 @@
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import random
import logging
import sys
import numbers
import math
import sklearn
import datetime
import numpy as np
import cv2
from PIL import Image
from io import BytesIO
import mxnet as mx
from mxnet import ndarray as nd
from mxnet import io
from mxnet import recordio
logger = logging.getLogger()
class FaceImageIter(io.DataIter):
def __init__(self,
batch_size,
data_shape,
path_imgrec=None,
shuffle=False,
aug_list=None,
mean=None,
rand_mirror=False,
cutoff=0,
color_jittering=0,
data_name='data',
label_name='softmax_label',
**kwargs):
super(FaceImageIter, self).__init__()
assert path_imgrec
logging.info('loading recordio %s...', path_imgrec)
path_imgidx = path_imgrec[0:-4] + ".idx"
self.imgrec = recordio.MXIndexedRecordIO(path_imgidx, path_imgrec, 'r') # pylint: disable=redefined-variable-type
s = self.imgrec.read_idx(0)
header, _ = recordio.unpack(s)
self.imgidx = list(self.imgrec.keys)
self.seq = self.imgidx
self.mean = mean
self.nd_mean = None
if self.mean:
self.mean = np.array(self.mean, dtype=np.float32).reshape(1, 1, 3)
self.nd_mean = mx.nd.array(self.mean).reshape((1, 1, 3))
self.check_data_shape(data_shape)
self.provide_data = [(data_name, (batch_size, ) + data_shape)]
self.batch_size = batch_size
self.data_shape = data_shape
self.shuffle = shuffle
self.image_size = '%d,%d' % (data_shape[1], data_shape[2])
self.rand_mirror = rand_mirror
print('rand_mirror', rand_mirror)
self.cutoff = cutoff
self.color_jittering = color_jittering
self.CJA = mx.image.ColorJitterAug(0.125, 0.125, 0.125)
self.provide_label = [(label_name, (batch_size, 101))]
#print(self.provide_label[0][1])
self.cur = 0
self.nbatch = 0
self.is_init = False
def reset(self):
"""Resets the iterator to the beginning of the data."""
print('call reset()')
self.cur = 0
if self.shuffle:
random.shuffle(self.seq)
if self.seq is None and self.imgrec is not None:
self.imgrec.reset()
def num_samples(self):
return len(self.seq)
def next_sample(self):
if self.cur >= len(self.seq):
raise StopIteration
idx = self.seq[self.cur]
self.cur += 1
s = self.imgrec.read_idx(idx)
header, img = recordio.unpack(s)
label = header.label
return label, img, None, None
def brightness_aug(self, src, x):
alpha = 1.0 + random.uniform(-x, x)
src *= alpha
return src
def contrast_aug(self, src, x):
alpha = 1.0 + random.uniform(-x, x)
coef = nd.array([[[0.299, 0.587, 0.114]]])
gray = src * coef
gray = (3.0 * (1.0 - alpha) / gray.size) * nd.sum(gray)
src *= alpha
src += gray
return src
def saturation_aug(self, src, x):
alpha = 1.0 + random.uniform(-x, x)
coef = nd.array([[[0.299, 0.587, 0.114]]])
gray = src * coef
gray = nd.sum(gray, axis=2, keepdims=True)
gray *= (1.0 - alpha)
src *= alpha
src += gray
return src
def color_aug(self, img, x):
#augs = [self.brightness_aug, self.contrast_aug, self.saturation_aug]
#random.shuffle(augs)
#for aug in augs:
# #print(img.shape)
# img = aug(img, x)
# #print(img.shape)
#return img
return self.CJA(img)
def mirror_aug(self, img):
_rd = random.randint(0, 1)
if _rd == 1:
for c in range(img.shape[2]):
img[:, :, c] = np.fliplr(img[:, :, c])
return img
def compress_aug(self, img):
buf = BytesIO()
img = Image.fromarray(img.asnumpy(), 'RGB')
q = random.randint(2, 20)
img.save(buf, format='JPEG', quality=q)
buf = buf.getvalue()
img = Image.open(BytesIO(buf))
return nd.array(np.asarray(img, 'float32'))
def next(self):
if not self.is_init:
self.reset()
self.is_init = True
"""Returns the next batch of data."""
#print('in next', self.cur, self.labelcur)
self.nbatch += 1
batch_size = self.batch_size
c, h, w = self.data_shape
batch_data = nd.empty((batch_size, c, h, w))
if self.provide_label is not None:
batch_label = nd.empty(self.provide_label[0][1])
i = 0
try:
while i < batch_size:
#print('XXXX', i)
label, s, bbox, landmark = self.next_sample()
gender = int(label[0])
age = int(label[1])
assert age >= 0
#assert gender==0 or gender==1
plabel = np.zeros(shape=(101, ), dtype=np.float32)
plabel[0] = gender
if age == 0:
age = 1
if age > 100:
age = 100
plabel[1:age + 1] = 1
label = plabel
_data = self.imdecode(s)
if _data.shape[0] != self.data_shape[1]:
_data = mx.image.resize_short(_data, self.data_shape[1])
if self.rand_mirror:
_rd = random.randint(0, 1)
if _rd == 1:
_data = mx.ndarray.flip(data=_data, axis=1)
if self.color_jittering > 0:
if self.color_jittering > 1:
_rd = random.randint(0, 1)
if _rd == 1:
_data = self.compress_aug(_data)
#print('do color aug')
_data = _data.astype('float32', copy=False)
#print(_data.__class__)
_data = self.color_aug(_data, 0.125)
if self.nd_mean is not None:
_data = _data.astype('float32', copy=False)
_data -= self.nd_mean
_data *= 0.0078125
if self.cutoff > 0:
_rd = random.randint(0, 1)
if _rd == 1:
#print('do cutoff aug', self.cutoff)
centerh = random.randint(0, _data.shape[0] - 1)
centerw = random.randint(0, _data.shape[1] - 1)
half = self.cutoff // 2
starth = max(0, centerh - half)
endh = min(_data.shape[0], centerh + half)
startw = max(0, centerw - half)
endw = min(_data.shape[1], centerw + half)
#print(starth, endh, startw, endw, _data.shape)
_data[starth:endh, startw:endw, :] = 128
data = [_data]
for datum in data:
assert i < batch_size, 'Batch size must be multiples of augmenter output length'
#print(datum.shape)
batch_data[i][:] = self.postprocess_data(datum)
batch_label[i][:] = label
i += 1
except StopIteration:
if i < batch_size:
raise StopIteration
return io.DataBatch([batch_data], [batch_label], batch_size - i)
def check_data_shape(self, data_shape):
"""Checks if the input data shape is valid"""
if not len(data_shape) == 3:
raise ValueError(
'data_shape should have length 3, with dimensions CxHxW')
if not data_shape[0] == 3:
raise ValueError(
'This iterator expects inputs to have 3 channels.')
def check_valid_image(self, data):
"""Checks if the input data is valid"""
if len(data[0].shape) == 0:
raise RuntimeError('Data shape is wrong')
def imdecode(self, s):
"""Decodes a string or byte string to an NDArray.
See mx.img.imdecode for more details."""
img = mx.image.imdecode(s) #mx.ndarray
return img
def read_image(self, fname):
"""Reads an input image `fname` and returns the decoded raw bytes.
Example usage:
----------
>>> dataIter.read_image('Face.jpg') # returns decoded raw bytes.
"""
with open(os.path.join(self.path_root, fname), 'rb') as fin:
img = fin.read()
return img
def augmentation_transform(self, data):
"""Transforms input data with specified augmentation."""
for aug in self.auglist:
data = [ret for src in data for ret in aug(src)]
return data
def postprocess_data(self, datum):
"""Final postprocessing step before image is loaded into the batch."""
return nd.transpose(datum, axes=(2, 0, 1))
class FaceImageIterList(io.DataIter):
def __init__(self, iter_list):
assert len(iter_list) > 0
self.provide_data = iter_list[0].provide_data
self.provide_label = iter_list[0].provide_label
self.iter_list = iter_list
self.cur_iter = None
def reset(self):
self.cur_iter.reset()
def next(self):
self.cur_iter = random.choice(self.iter_list)
while True:
try:
ret = self.cur_iter.next()
except StopIteration:
self.cur_iter.reset()
continue
return ret

109
gender-age/face_model.py
View File

@@ -1,109 +0,0 @@
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from scipy import misc
import sys
import os
import argparse
#import tensorflow as tf
import numpy as np
import mxnet as mx
import random
import cv2
import sklearn
from sklearn.decomposition import PCA
from time import sleep
from easydict import EasyDict as edict
from mtcnn_detector import MtcnnDetector
sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'src', 'common'))
import face_image
import face_preprocess
def do_flip(data):
for idx in range(data.shape[0]):
data[idx, :, :] = np.fliplr(data[idx, :, :])
def get_model(ctx, image_size, model_str, layer):
_vec = model_str.split(',')
assert len(_vec) == 2
prefix = _vec[0]
epoch = int(_vec[1])
print('loading', prefix, epoch)
sym, arg_params, aux_params = mx.model.load_checkpoint(prefix, epoch)
all_layers = sym.get_internals()
sym = all_layers[layer + '_output']
model = mx.mod.Module(symbol=sym, context=ctx, label_names=None)
#model.bind(data_shapes=[('data', (args.batch_size, 3, image_size[0], image_size[1]))], label_shapes=[('softmax_label', (args.batch_size,))])
model.bind(data_shapes=[('data', (1, 3, image_size[0], image_size[1]))])
model.set_params(arg_params, aux_params)
return model
class FaceModel:
def __init__(self, args):
self.args = args
if args.gpu >= 0:
ctx = mx.gpu(args.gpu)
else:
ctx = mx.cpu()
_vec = args.image_size.split(',')
assert len(_vec) == 2
image_size = (int(_vec[0]), int(_vec[1]))
self.model = None
if len(args.model) > 0:
self.model = get_model(ctx, image_size, args.model, 'fc1')
self.det_minsize = 50
self.det_threshold = [0.6, 0.7, 0.8]
#self.det_factor = 0.9
self.image_size = image_size
mtcnn_path = os.path.join(os.path.dirname(__file__), 'mtcnn-model')
if args.det == 0:
detector = MtcnnDetector(model_folder=mtcnn_path,
ctx=ctx,
num_worker=1,
accurate_landmark=True,
threshold=self.det_threshold)
else:
detector = MtcnnDetector(model_folder=mtcnn_path,
ctx=ctx,
num_worker=1,
accurate_landmark=True,
threshold=[0.0, 0.0, 0.2])
self.detector = detector
def get_input(self, face_img):
ret = self.detector.detect_face(face_img, det_type=self.args.det)
if ret is None:
return None
bbox, points = ret
if bbox.shape[0] == 0:
return None
bbox = bbox[0, 0:4]
points = points[0, :].reshape((2, 5)).T
#print(bbox)
#print(points)
nimg = face_preprocess.preprocess(face_img,
bbox,
points,
image_size='112,112')
nimg = cv2.cvtColor(nimg, cv2.COLOR_BGR2RGB)
aligned = np.transpose(nimg, (2, 0, 1))
input_blob = np.expand_dims(aligned, axis=0)
data = mx.nd.array(input_blob)
db = mx.io.DataBatch(data=(data, ))
return db
def get_ga(self, data):
self.model.forward(data, is_train=False)
ret = self.model.get_outputs()[0].asnumpy()
g = ret[:, 0:2].flatten()
gender = np.argmax(g)
a = ret[:, 2:202].reshape((100, 2))
a = np.argmax(a, axis=1)
age = int(sum(a))
return gender, age

172
gender-age/helper.py
View File

@@ -1,172 +0,0 @@
# coding: utf-8
# YuanYang
import math
import cv2
import numpy as np
def nms(boxes, overlap_threshold, mode='Union'):
"""
non max suppression
Parameters:
----------
box: numpy array n x 5
input bbox array
overlap_threshold: float number
threshold of overlap
mode: float number
how to compute overlap ratio, 'Union' or 'Min'
Returns:
-------
index array of the selected bbox
"""
# if there are no boxes, return an empty list
if len(boxes) == 0:
return []
# if the bounding boxes integers, convert them to floats
if boxes.dtype.kind == "i":
boxes = boxes.astype("float")
# initialize the list of picked indexes
pick = []
# grab the coordinates of the bounding boxes
x1, y1, x2, y2, score = [boxes[:, i] for i in range(5)]
area = (x2 - x1 + 1) * (y2 - y1 + 1)
idxs = np.argsort(score)
# keep looping while some indexes still remain in the indexes list
while len(idxs) > 0:
# grab the last index in the indexes list and add the index value to the list of picked indexes
last = len(idxs) - 1
i = idxs[last]
pick.append(i)
xx1 = np.maximum(x1[i], x1[idxs[:last]])
yy1 = np.maximum(y1[i], y1[idxs[:last]])
xx2 = np.minimum(x2[i], x2[idxs[:last]])
yy2 = np.minimum(y2[i], y2[idxs[:last]])
# compute the width and height of the bounding box
w = np.maximum(0, xx2 - xx1 + 1)
h = np.maximum(0, yy2 - yy1 + 1)
inter = w * h
if mode == 'Min':
overlap = inter / np.minimum(area[i], area[idxs[:last]])
else:
overlap = inter / (area[i] + area[idxs[:last]] - inter)
# delete all indexes from the index list that have
idxs = np.delete(
idxs,
np.concatenate(([last], np.where(overlap > overlap_threshold)[0])))
return pick
def adjust_input(in_data):
"""
adjust the input from (h, w, c) to ( 1, c, h, w) for network input
Parameters:
----------
in_data: numpy array of shape (h, w, c)
input data
Returns:
-------
out_data: numpy array of shape (1, c, h, w)
reshaped array
"""
if in_data.dtype is not np.dtype('float32'):
out_data = in_data.astype(np.float32)
else:
out_data = in_data
out_data = out_data.transpose((2, 0, 1))
out_data = np.expand_dims(out_data, 0)
out_data = (out_data - 127.5) * 0.0078125
return out_data
def generate_bbox(map, reg, scale, threshold):
"""
generate bbox from feature map
Parameters:
----------
map: numpy array , n x m x 1
detect score for each position
reg: numpy array , n x m x 4
bbox
scale: float number
scale of this detection
threshold: float number
detect threshold
Returns:
-------
bbox array
"""
stride = 2
cellsize = 12
t_index = np.where(map > threshold)
# find nothing
if t_index[0].size == 0:
return np.array([])
dx1, dy1, dx2, dy2 = [reg[0, i, t_index[0], t_index[1]] for i in range(4)]
reg = np.array([dx1, dy1, dx2, dy2])
score = map[t_index[0], t_index[1]]
boundingbox = np.vstack([
np.round((stride * t_index[1] + 1) / scale),
np.round((stride * t_index[0] + 1) / scale),
np.round((stride * t_index[1] + 1 + cellsize) / scale),
np.round((stride * t_index[0] + 1 + cellsize) / scale), score, reg
])
return boundingbox.T
def detect_first_stage(img, net, scale, threshold):
"""
run PNet for first stage
Parameters:
----------
img: numpy array, bgr order
input image
scale: float number
how much should the input image scale
net: PNet
worker
Returns:
-------
total_boxes : bboxes
"""
height, width, _ = img.shape
hs = int(math.ceil(height * scale))
ws = int(math.ceil(width * scale))
im_data = cv2.resize(img, (ws, hs))
# adjust for the network input
input_buf = adjust_input(im_data)
output = net.predict(input_buf)
boxes = generate_bbox(output[1][0, 1, :, :], output[0], scale, threshold)
if boxes.size == 0:
return None
# nms
pick = nms(boxes[:, 0:5], 0.5, mode='Union')
boxes = boxes[pick]
return boxes
def detect_first_stage_warpper(args):
return detect_first_stage(*args)

BIN
gender-age/model/model-0000.params
View File

Binary file not shown.

2399
gender-age/model/model-symbol.json
View File

File diff suppressed because it is too large Load Diff

BIN
gender-age/mtcnn-model/det1-0001.params
View File

Binary file not shown.

266
gender-age/mtcnn-model/det1-symbol.json
View File

@@ -1,266 +0,0 @@
{
"nodes": [
{
"op": "null",
"param": {},
"name": "data",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv1_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv1_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "10",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv1",
"inputs": [[0, 0], [1, 0], [2, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu1_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu1",
"inputs": [[3, 0], [4, 0]],
"backward_source_id": -1
},
{
"op": "Pooling",
"param": {
"global_pool": "False",
"kernel": "(2,2)",
"pad": "(0,0)",
"pool_type": "max",
"pooling_convention": "full",
"stride": "(2,2)"
},
"name": "pool1",
"inputs": [[5, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv2_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv2_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "16",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv2",
"inputs": [[6, 0], [7, 0], [8, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu2_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu2",
"inputs": [[9, 0], [10, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv3_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv3_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "32",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv3",
"inputs": [[11, 0], [12, 0], [13, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu3_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu3",
"inputs": [[14, 0], [15, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_2_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_2_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(1,1)",
"no_bias": "False",
"num_filter": "4",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv4_2",
"inputs": [[16, 0], [17, 0], [18, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_1_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_1_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(1,1)",
"no_bias": "False",
"num_filter": "2",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv4_1",
"inputs": [[16, 0], [20, 0], [21, 0]],
"backward_source_id": -1
},
{
"op": "SoftmaxActivation",
"param": {"mode": "channel"},
"name": "prob1",
"inputs": [[22, 0]],
"backward_source_id": -1
}
],
"arg_nodes": [
0,
1,
2,
4,
7,
8,
10,
12,
13,
15,
17,
18,
20,
21
],
"heads": [[19, 0], [23, 0]]
}

BIN
gender-age/mtcnn-model/det1.caffemodel
View File

Binary file not shown.

177
gender-age/mtcnn-model/det1.prototxt
View File

@@ -1,177 +0,0 @@
name: "PNet"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 12
input_dim: 12
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 10
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "PReLU1"
type: "PReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 16
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "PReLU2"
type: "PReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "conv3"
type: "Convolution"
bottom: "conv2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 32
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "PReLU3"
type: "PReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4-1"
type: "Convolution"
bottom: "conv3"
top: "conv4-1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 2
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv4-2"
type: "Convolution"
bottom: "conv3"
top: "conv4-2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 4
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prob1"
type: "Softmax"
bottom: "conv4-1"
top: "prob1"
}

BIN
gender-age/mtcnn-model/det2-0001.params
View File

Binary file not shown.

324
gender-age/mtcnn-model/det2-symbol.json
View File

@@ -1,324 +0,0 @@
{
"nodes": [
{
"op": "null",
"param": {},
"name": "data",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv1_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv1_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "28",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv1",
"inputs": [[0, 0], [1, 0], [2, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu1_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu1",
"inputs": [[3, 0], [4, 0]],
"backward_source_id": -1
},
{
"op": "Pooling",
"param": {
"global_pool": "False",
"kernel": "(3,3)",
"pad": "(0,0)",
"pool_type": "max",
"pooling_convention": "full",
"stride": "(2,2)"
},
"name": "pool1",
"inputs": [[5, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv2_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv2_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "48",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv2",
"inputs": [[6, 0], [7, 0], [8, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu2_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu2",
"inputs": [[9, 0], [10, 0]],
"backward_source_id": -1
},
{
"op": "Pooling",
"param": {
"global_pool": "False",
"kernel": "(3,3)",
"pad": "(0,0)",
"pool_type": "max",
"pooling_convention": "full",
"stride": "(2,2)"
},
"name": "pool2",
"inputs": [[11, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv3_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv3_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(2,2)",
"no_bias": "False",
"num_filter": "64",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv3",
"inputs": [[12, 0], [13, 0], [14, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu3_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu3",
"inputs": [[15, 0], [16, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "128"
},
"name": "conv4",
"inputs": [[17, 0], [18, 0], [19, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu4_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu4",
"inputs": [[20, 0], [21, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv5_2_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv5_2_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "4"
},
"name": "conv5_2",
"inputs": [[22, 0], [23, 0], [24, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv5_1_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv5_1_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "2"
},
"name": "conv5_1",
"inputs": [[22, 0], [26, 0], [27, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prob1_label",
"inputs": [],
"backward_source_id": -1
},
{
"op": "SoftmaxOutput",
"param": {
"grad_scale": "1",
"ignore_label": "-1",
"multi_output": "False",
"normalization": "null",
"use_ignore": "False"
},
"name": "prob1",
"inputs": [[28, 0], [29, 0]],
"backward_source_id": -1
}
],
"arg_nodes": [
0,
1,
2,
4,
7,
8,
10,
13,
14,
16,
18,
19,
21,
23,
24,
26,
27,
29
],
"heads": [[25, 0], [30, 0]]
}

BIN
gender-age/mtcnn-model/det2.caffemodel
View File

Binary file not shown.

228
gender-age/mtcnn-model/det2.prototxt
View File

@@ -1,228 +0,0 @@
name: "RNet"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 24
input_dim: 24
##########################
######################
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
convolution_param {
num_output: 28
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1"
type: "PReLU"
bottom: "conv1"
top: "conv1"
propagate_down: true
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
convolution_param {
num_output: 48
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2"
type: "PReLU"
bottom: "conv2"
top: "conv2"
propagate_down: true
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
####################################
##################################
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
convolution_param {
num_output: 64
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3"
type: "PReLU"
bottom: "conv3"
top: "conv3"
propagate_down: true
}
###############################
###############################
layer {
name: "conv4"
type: "InnerProduct"
bottom: "conv3"
top: "conv4"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
inner_product_param {
num_output: 128
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4"
type: "PReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5-1"
type: "InnerProduct"
bottom: "conv4"
top: "conv5-1"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
inner_product_param {
num_output: 2
#kernel_size: 1
#stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv5-2"
type: "InnerProduct"
bottom: "conv4"
top: "conv5-2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 4
#kernel_size: 1
#stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prob1"
type: "Softmax"
bottom: "conv5-1"
top: "prob1"
}

BIN
gender-age/mtcnn-model/det3-0001.params
View File

Binary file not shown.

418
gender-age/mtcnn-model/det3-symbol.json
View File

@@ -1,418 +0,0 @@
{
"nodes": [
{
"op": "null",
"param": {},
"name": "data",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv1_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv1_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "32",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv1",
"inputs": [[0, 0], [1, 0], [2, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu1_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu1",
"inputs": [[3, 0], [4, 0]],
"backward_source_id": -1
},
{
"op": "Pooling",
"param": {
"global_pool": "False",
"kernel": "(3,3)",
"pad": "(0,0)",
"pool_type": "max",
"pooling_convention": "full",
"stride": "(2,2)"
},
"name": "pool1",
"inputs": [[5, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv2_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv2_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "64",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv2",
"inputs": [[6, 0], [7, 0], [8, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu2_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu2",
"inputs": [[9, 0], [10, 0]],
"backward_source_id": -1
},
{
"op": "Pooling",
"param": {
"global_pool": "False",
"kernel": "(3,3)",
"pad": "(0,0)",
"pool_type": "max",
"pooling_convention": "full",
"stride": "(2,2)"
},
"name": "pool2",
"inputs": [[11, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv3_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv3_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(3,3)",
"no_bias": "False",
"num_filter": "64",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv3",
"inputs": [[12, 0], [13, 0], [14, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu3_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu3",
"inputs": [[15, 0], [16, 0]],
"backward_source_id": -1
},
{
"op": "Pooling",
"param": {
"global_pool": "False",
"kernel": "(2,2)",
"pad": "(0,0)",
"pool_type": "max",
"pooling_convention": "full",
"stride": "(2,2)"
},
"name": "pool3",
"inputs": [[17, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv4_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "Convolution",
"param": {
"cudnn_off": "False",
"cudnn_tune": "off",
"dilate": "(1,1)",
"kernel": "(2,2)",
"no_bias": "False",
"num_filter": "128",
"num_group": "1",
"pad": "(0,0)",
"stride": "(1,1)",
"workspace": "1024"
},
"name": "conv4",
"inputs": [[18, 0], [19, 0], [20, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu4_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu4",
"inputs": [[21, 0], [22, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv5_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv5_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "256"
},
"name": "conv5",
"inputs": [[23, 0], [24, 0], [25, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prelu5_gamma",
"inputs": [],
"backward_source_id": -1
},
{
"op": "LeakyReLU",
"param": {
"act_type": "prelu",
"lower_bound": "0.125",
"slope": "0.25",
"upper_bound": "0.334"
},
"name": "prelu5",
"inputs": [[26, 0], [27, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv6_3_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv6_3_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "10"
},
"name": "conv6_3",
"inputs": [[28, 0], [29, 0], [30, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv6_2_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv6_2_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "4"
},
"name": "conv6_2",
"inputs": [[28, 0], [32, 0], [33, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv6_1_weight",
"inputs": [],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "conv6_1_bias",
"inputs": [],
"backward_source_id": -1
},
{
"op": "FullyConnected",
"param": {
"no_bias": "False",
"num_hidden": "2"
},
"name": "conv6_1",
"inputs": [[28, 0], [35, 0], [36, 0]],
"backward_source_id": -1
},
{
"op": "null",
"param": {},
"name": "prob1_label",
"inputs": [],
"backward_source_id": -1
},
{
"op": "SoftmaxOutput",
"param": {
"grad_scale": "1",
"ignore_label": "-1",
"multi_output": "False",
"normalization": "null",
"use_ignore": "False"
},
"name": "prob1",
"inputs": [[37, 0], [38, 0]],
"backward_source_id": -1
}
],
"arg_nodes": [
0,
1,
2,
4,
7,
8,
10,
13,
14,
16,
19,
20,
22,
24,
25,
27,
29,
30,
32,
33,
35,
36,
38
],
"heads": [[31, 0], [34, 0], [39, 0]]
}

BIN
gender-age/mtcnn-model/det3.caffemodel
View File

Binary file not shown.

294
gender-age/mtcnn-model/det3.prototxt
View File

@@ -1,294 +0,0 @@
name: "ONet"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 48
input_dim: 48
##################################
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 32
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1"
type: "PReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2"
type: "PReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 3
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3"
type: "PReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "pool3"
type: "Pooling"
bottom: "conv3"
top: "pool3"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv4"
type: "Convolution"
bottom: "pool3"
top: "conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 128
kernel_size: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4"
type: "PReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "InnerProduct"
bottom: "conv4"
top: "conv5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
#kernel_size: 3
num_output: 256
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "drop5"
type: "Dropout"
bottom: "conv5"
top: "conv5"
dropout_param {
dropout_ratio: 0.25
}
}
layer {
name: "prelu5"
type: "PReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "conv6-1"
type: "InnerProduct"
bottom: "conv5"
top: "conv6-1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
#kernel_size: 1
num_output: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv6-2"
type: "InnerProduct"
bottom: "conv5"
top: "conv6-2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
#kernel_size: 1
num_output: 4
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv6-3"
type: "InnerProduct"
bottom: "conv5"
top: "conv6-3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
#kernel_size: 1
num_output: 10
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prob1"
type: "Softmax"
bottom: "conv6-1"
top: "prob1"
}

BIN
gender-age/mtcnn-model/det4-0001.params
View File

Binary file not shown.

1392
gender-age/mtcnn-model/det4-symbol.json
View File

File diff suppressed because it is too large Load Diff

BIN
gender-age/mtcnn-model/det4.caffemodel
View File

Binary file not shown.

995
gender-age/mtcnn-model/det4.prototxt
View File

@@ -1,995 +0,0 @@
name: "LNet"
input: "data"
input_dim: 1
input_dim: 15
input_dim: 24
input_dim: 24
layer {
name: "slicer_data"
type: "Slice"
bottom: "data"
top: "data241"
top: "data242"
top: "data243"
top: "data244"
top: "data245"
slice_param {
axis: 1
slice_point: 3
slice_point: 6
slice_point: 9
slice_point: 12
}
}
layer {
name: "conv1_1"
type: "Convolution"
bottom: "data241"
top: "conv1_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 28
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1_1"
type: "PReLU"
bottom: "conv1_1"
top: "conv1_1"
}
layer {
name: "pool1_1"
type: "Pooling"
bottom: "conv1_1"
top: "pool1_1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2_1"
type: "Convolution"
bottom: "pool1_1"
top: "conv2_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 48
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2_1"
type: "PReLU"
bottom: "conv2_1"
top: "conv2_1"
}
layer {
name: "pool2_1"
type: "Pooling"
bottom: "conv2_1"
top: "pool2_1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3_1"
type: "Convolution"
bottom: "pool2_1"
top: "conv3_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3_1"
type: "PReLU"
bottom: "conv3_1"
top: "conv3_1"
}
##########################
layer {
name: "conv1_2"
type: "Convolution"
bottom: "data242"
top: "conv1_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 28
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1_2"
type: "PReLU"
bottom: "conv1_2"
top: "conv1_2"
}
layer {
name: "pool1_2"
type: "Pooling"
bottom: "conv1_2"
top: "pool1_2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2_2"
type: "Convolution"
bottom: "pool1_2"
top: "conv2_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 48
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2_2"
type: "PReLU"
bottom: "conv2_2"
top: "conv2_2"
}
layer {
name: "pool2_2"
type: "Pooling"
bottom: "conv2_2"
top: "pool2_2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3_2"
type: "Convolution"
bottom: "pool2_2"
top: "conv3_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3_2"
type: "PReLU"
bottom: "conv3_2"
top: "conv3_2"
}
##########################
##########################
layer {
name: "conv1_3"
type: "Convolution"
bottom: "data243"
top: "conv1_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 28
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1_3"
type: "PReLU"
bottom: "conv1_3"
top: "conv1_3"
}
layer {
name: "pool1_3"
type: "Pooling"
bottom: "conv1_3"
top: "pool1_3"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2_3"
type: "Convolution"
bottom: "pool1_3"
top: "conv2_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 48
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2_3"
type: "PReLU"
bottom: "conv2_3"
top: "conv2_3"
}
layer {
name: "pool2_3"
type: "Pooling"
bottom: "conv2_3"
top: "pool2_3"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3_3"
type: "Convolution"
bottom: "pool2_3"
top: "conv3_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3_3"
type: "PReLU"
bottom: "conv3_3"
top: "conv3_3"
}
##########################
##########################
layer {
name: "conv1_4"
type: "Convolution"
bottom: "data244"
top: "conv1_4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 28
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1_4"
type: "PReLU"
bottom: "conv1_4"
top: "conv1_4"
}
layer {
name: "pool1_4"
type: "Pooling"
bottom: "conv1_4"
top: "pool1_4"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2_4"
type: "Convolution"
bottom: "pool1_4"
top: "conv2_4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 48
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2_4"
type: "PReLU"
bottom: "conv2_4"
top: "conv2_4"
}
layer {
name: "pool2_4"
type: "Pooling"
bottom: "conv2_4"
top: "pool2_4"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3_4"
type: "Convolution"
bottom: "pool2_4"
top: "conv3_4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3_4"
type: "PReLU"
bottom: "conv3_4"
top: "conv3_4"
}
##########################
##########################
layer {
name: "conv1_5"
type: "Convolution"
bottom: "data245"
top: "conv1_5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 28
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu1_5"
type: "PReLU"
bottom: "conv1_5"
top: "conv1_5"
}
layer {
name: "pool1_5"
type: "Pooling"
bottom: "conv1_5"
top: "pool1_5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2_5"
type: "Convolution"
bottom: "pool1_5"
top: "conv2_5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 48
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu2_5"
type: "PReLU"
bottom: "conv2_5"
top: "conv2_5"
}
layer {
name: "pool2_5"
type: "Pooling"
bottom: "conv2_5"
top: "pool2_5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3_5"
type: "Convolution"
bottom: "pool2_5"
top: "conv3_5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
convolution_param {
num_output: 64
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu3_5"
type: "PReLU"
bottom: "conv3_5"
top: "conv3_5"
}
##########################
layer {
name: "concat"
bottom: "conv3_1"
bottom: "conv3_2"
bottom: "conv3_3"
bottom: "conv3_4"
bottom: "conv3_5"
top: "conv3"
type: "Concat"
concat_param {
axis: 1
}
}
##########################
layer {
name: "fc4"
type: "InnerProduct"
bottom: "conv3"
top: "fc4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 256
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4"
type: "PReLU"
bottom: "fc4"
top: "fc4"
}
############################
layer {
name: "fc4_1"
type: "InnerProduct"
bottom: "fc4"
top: "fc4_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 64
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4_1"
type: "PReLU"
bottom: "fc4_1"
top: "fc4_1"
}
layer {
name: "fc5_1"
type: "InnerProduct"
bottom: "fc4_1"
top: "fc5_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 2
weight_filler {
type: "xavier"
#type: "constant"
#value: 0
}
bias_filler {
type: "constant"
value: 0
}
}
}
#########################
layer {
name: "fc4_2"
type: "InnerProduct"
bottom: "fc4"
top: "fc4_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 64
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4_2"
type: "PReLU"
bottom: "fc4_2"
top: "fc4_2"
}
layer {
name: "fc5_2"
type: "InnerProduct"
bottom: "fc4_2"
top: "fc5_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 2
weight_filler {
type: "xavier"
#type: "constant"
#value: 0
}
bias_filler {
type: "constant"
value: 0
}
}
}
#########################
layer {
name: "fc4_3"
type: "InnerProduct"
bottom: "fc4"
top: "fc4_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 64
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4_3"
type: "PReLU"
bottom: "fc4_3"
top: "fc4_3"
}
layer {
name: "fc5_3"
type: "InnerProduct"
bottom: "fc4_3"
top: "fc5_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 2
weight_filler {
type: "xavier"
#type: "constant"
#value: 0
}
bias_filler {
type: "constant"
value: 0
}
}
}
#########################
layer {
name: "fc4_4"
type: "InnerProduct"
bottom: "fc4"
top: "fc4_4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 64
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4_4"
type: "PReLU"
bottom: "fc4_4"
top: "fc4_4"
}
layer {
name: "fc5_4"
type: "InnerProduct"
bottom: "fc4_4"
top: "fc5_4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 2
weight_filler {
type: "xavier"
#type: "constant"
#value: 0
}
bias_filler {
type: "constant"
value: 0
}
}
}
#########################
layer {
name: "fc4_5"
type: "InnerProduct"
bottom: "fc4"
top: "fc4_5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 64
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "prelu4_5"
type: "PReLU"
bottom: "fc4_5"
top: "fc4_5"
}
layer {
name: "fc5_5"
type: "InnerProduct"
bottom: "fc4_5"
top: "fc5_5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 1
}
inner_product_param {
num_output: 2
weight_filler {
type: "xavier"
#type: "constant"
#value: 0
}
bias_filler {
type: "constant"
value: 0
}
}
}
#########################

696
gender-age/mtcnn_detector.py
View File

@@ -1,696 +0,0 @@
# coding: utf-8
import os
import mxnet as mx
import numpy as np
import math
import cv2
from multiprocessing import Pool
from itertools import repeat
from itertools import izip
from helper import nms, adjust_input, generate_bbox, detect_first_stage_warpper
class MtcnnDetector(object):
"""
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks
see https://github.com/kpzhang93/MTCNN_face_detection_alignment
this is a mxnet version
"""
def __init__(self,
model_folder='.',
minsize=20,
threshold=[0.6, 0.7, 0.8],
factor=0.709,
num_worker=1,
accurate_landmark=False,
ctx=mx.cpu()):
"""
Initialize the detector
Parameters:
----------
model_folder : string
path for the models
minsize : float number
minimal face to detect
threshold : float number
detect threshold for 3 stages
factor: float number
scale factor for image pyramid
num_worker: int number
number of processes we use for first stage
accurate_landmark: bool
use accurate landmark localization or not
"""
self.num_worker = num_worker
self.accurate_landmark = accurate_landmark
# load 4 models from folder
models = ['det1', 'det2', 'det3', 'det4']
models = [os.path.join(model_folder, f) for f in models]
self.PNets = []
for i in range(num_worker):
workner_net = mx.model.FeedForward.load(models[0], 1, ctx=ctx)
self.PNets.append(workner_net)
#self.Pool = Pool(num_worker)
self.RNet = mx.model.FeedForward.load(models[1], 1, ctx=ctx)
self.ONet = mx.model.FeedForward.load(models[2], 1, ctx=ctx)
self.LNet = mx.model.FeedForward.load(models[3], 1, ctx=ctx)
self.minsize = float(minsize)
self.factor = float(factor)
self.threshold = threshold
def convert_to_square(self, bbox):
"""
convert bbox to square
Parameters:
----------
bbox: numpy array , shape n x 5
input bbox
Returns:
-------
square bbox
"""
square_bbox = bbox.copy()
h = bbox[:, 3] - bbox[:, 1] + 1
w = bbox[:, 2] - bbox[:, 0] + 1
max_side = np.maximum(h, w)
square_bbox[:, 0] = bbox[:, 0] + w * 0.5 - max_side * 0.5
square_bbox[:, 1] = bbox[:, 1] + h * 0.5 - max_side * 0.5
square_bbox[:, 2] = square_bbox[:, 0] + max_side - 1
square_bbox[:, 3] = square_bbox[:, 1] + max_side - 1
return square_bbox
def calibrate_box(self, bbox, reg):
"""
calibrate bboxes
Parameters:
----------
bbox: numpy array, shape n x 5
input bboxes
reg: numpy array, shape n x 4
bboxex adjustment
Returns:
-------
bboxes after refinement
"""
w = bbox[:, 2] - bbox[:, 0] + 1
w = np.expand_dims(w, 1)
h = bbox[:, 3] - bbox[:, 1] + 1
h = np.expand_dims(h, 1)
reg_m = np.hstack([w, h, w, h])
aug = reg_m * reg
bbox[:, 0:4] = bbox[:, 0:4] + aug
return bbox
def pad(self, bboxes, w, h):
"""
pad the the bboxes, alse restrict the size of it
Parameters:
----------
bboxes: numpy array, n x 5
input bboxes
w: float number
width of the input image
h: float number
height of the input image
Returns :
------s
dy, dx : numpy array, n x 1
start point of the bbox in target image
edy, edx : numpy array, n x 1
end point of the bbox in target image
y, x : numpy array, n x 1
start point of the bbox in original image
ex, ex : numpy array, n x 1
end point of the bbox in original image
tmph, tmpw: numpy array, n x 1
height and width of the bbox
"""
tmpw, tmph = bboxes[:, 2] - bboxes[:, 0] + 1, bboxes[:,
3] - bboxes[:,
1] + 1
num_box = bboxes.shape[0]
dx, dy = np.zeros((num_box, )), np.zeros((num_box, ))
edx, edy = tmpw.copy() - 1, tmph.copy() - 1
x, y, ex, ey = bboxes[:, 0], bboxes[:, 1], bboxes[:, 2], bboxes[:, 3]
tmp_index = np.where(ex > w - 1)
edx[tmp_index] = tmpw[tmp_index] + w - 2 - ex[tmp_index]
ex[tmp_index] = w - 1
tmp_index = np.where(ey > h - 1)
edy[tmp_index] = tmph[tmp_index] + h - 2 - ey[tmp_index]
ey[tmp_index] = h - 1
tmp_index = np.where(x < 0)
dx[tmp_index] = 0 - x[tmp_index]
x[tmp_index] = 0
tmp_index = np.where(y < 0)
dy[tmp_index] = 0 - y[tmp_index]
y[tmp_index] = 0
return_list = [dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph]
return_list = [item.astype(np.int32) for item in return_list]
return return_list
def slice_index(self, number):
"""
slice the index into (n,n,m), m < n
Parameters:
----------
number: int number
number
"""
def chunks(l, n):
"""Yield successive n-sized chunks from l."""
for i in range(0, len(l), n):
yield l[i:i + n]
num_list = range(number)
return list(chunks(num_list, self.num_worker))
def detect_face_limited(self, img, det_type=2):
height, width, _ = img.shape
if det_type >= 2:
total_boxes = np.array(
[[0.0, 0.0, img.shape[1], img.shape[0], 0.9]],
dtype=np.float32)
num_box = total_boxes.shape[0]
# pad the bbox
[dy, edy, dx, edx, y, ey, x, ex, tmpw,
tmph] = self.pad(total_boxes, width, height)
# (3, 24, 24) is the input shape for RNet
input_buf = np.zeros((num_box, 3, 24, 24), dtype=np.float32)
for i in range(num_box):
tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.uint8)
tmp[dy[i]:edy[i] + 1,
dx[i]:edx[i] + 1, :] = img[y[i]:ey[i] + 1,
x[i]:ex[i] + 1, :]
input_buf[i, :, :, :] = adjust_input(cv2.resize(tmp, (24, 24)))
output = self.RNet.predict(input_buf)
# filter the total_boxes with threshold
passed = np.where(output[1][:, 1] > self.threshold[1])
total_boxes = total_boxes[passed]
if total_boxes.size == 0:
return None
total_boxes[:, 4] = output[1][passed, 1].reshape((-1, ))
reg = output[0][passed]
# nms
pick = nms(total_boxes, 0.7, 'Union')
total_boxes = total_boxes[pick]
total_boxes = self.calibrate_box(total_boxes, reg[pick])
total_boxes = self.convert_to_square(total_boxes)
total_boxes[:, 0:4] = np.round(total_boxes[:, 0:4])
else:
total_boxes = np.array(
[[0.0, 0.0, img.shape[1], img.shape[0], 0.9]],
dtype=np.float32)
num_box = total_boxes.shape[0]
[dy, edy, dx, edx, y, ey, x, ex, tmpw,
tmph] = self.pad(total_boxes, width, height)
# (3, 48, 48) is the input shape for ONet
input_buf = np.zeros((num_box, 3, 48, 48), dtype=np.float32)
for i in range(num_box):
tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.float32)
tmp[dy[i]:edy[i] + 1, dx[i]:edx[i] + 1, :] = img[y[i]:ey[i] + 1,
x[i]:ex[i] + 1, :]
input_buf[i, :, :, :] = adjust_input(cv2.resize(tmp, (48, 48)))
output = self.ONet.predict(input_buf)
#print(output[2])
# filter the total_boxes with threshold
passed = np.where(output[2][:, 1] > self.threshold[2])
total_boxes = total_boxes[passed]
if total_boxes.size == 0:
return None
total_boxes[:, 4] = output[2][passed, 1].reshape((-1, ))
reg = output[1][passed]
points = output[0][passed]
# compute landmark points
bbw = total_boxes[:, 2] - total_boxes[:, 0] + 1
bbh = total_boxes[:, 3] - total_boxes[:, 1] + 1
points[:, 0:5] = np.expand_dims(
total_boxes[:, 0], 1) + np.expand_dims(bbw, 1) * points[:, 0:5]
points[:, 5:10] = np.expand_dims(
total_boxes[:, 1], 1) + np.expand_dims(bbh, 1) * points[:, 5:10]
# nms
total_boxes = self.calibrate_box(total_boxes, reg)
pick = nms(total_boxes, 0.7, 'Min')
total_boxes = total_boxes[pick]
points = points[pick]
if not self.accurate_landmark:
return total_boxes, points
#############################################
# extended stage
#############################################
num_box = total_boxes.shape[0]
patchw = np.maximum(total_boxes[:, 2] - total_boxes[:, 0] + 1,
total_boxes[:, 3] - total_boxes[:, 1] + 1)
patchw = np.round(patchw * 0.25)
# make it even
patchw[np.where(np.mod(patchw, 2) == 1)] += 1
input_buf = np.zeros((num_box, 15, 24, 24), dtype=np.float32)
for i in range(5):
x, y = points[:, i], points[:, i + 5]
x, y = np.round(x - 0.5 * patchw), np.round(y - 0.5 * patchw)
[dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph] = self.pad(
np.vstack([x, y, x + patchw - 1, y + patchw - 1]).T, width,
height)
for j in range(num_box):
tmpim = np.zeros((tmpw[j], tmpw[j], 3), dtype=np.float32)
tmpim[dy[j]:edy[j] + 1,
dx[j]:edx[j] + 1, :] = img[y[j]:ey[j] + 1,
x[j]:ex[j] + 1, :]
input_buf[j, i * 3:i * 3 + 3, :, :] = adjust_input(
cv2.resize(tmpim, (24, 24)))
output = self.LNet.predict(input_buf)
pointx = np.zeros((num_box, 5))
pointy = np.zeros((num_box, 5))
for k in range(5):
# do not make a large movement
tmp_index = np.where(np.abs(output[k] - 0.5) > 0.35)
output[k][tmp_index[0]] = 0.5
pointx[:, k] = np.round(points[:, k] -
0.5 * patchw) + output[k][:, 0] * patchw
pointy[:, k] = np.round(points[:, k + 5] -
0.5 * patchw) + output[k][:, 1] * patchw
points = np.hstack([pointx, pointy])
points = points.astype(np.int32)
return total_boxes, points
def detect_face(self, img, det_type=0):
"""
detect face over img
Parameters:
----------
img: numpy array, bgr order of shape (1, 3, n, m)
input image
Retures:
-------
bboxes: numpy array, n x 5 (x1,y2,x2,y2,score)
bboxes
points: numpy array, n x 10 (x1, x2 ... x5, y1, y2 ..y5)
landmarks
"""
# check input
height, width, _ = img.shape
if det_type == 0:
MIN_DET_SIZE = 12
if img is None:
return None
# only works for color image
if len(img.shape) != 3:
return None
# detected boxes
total_boxes = []
minl = min(height, width)
# get all the valid scales
scales = []
m = MIN_DET_SIZE / self.minsize
minl *= m
factor_count = 0
while minl > MIN_DET_SIZE:
scales.append(m * self.factor**factor_count)
minl *= self.factor
factor_count += 1
#############################################
# first stage
#############################################
#for scale in scales:
# return_boxes = self.detect_first_stage(img, scale, 0)
# if return_boxes is not None:
# total_boxes.append(return_boxes)
sliced_index = self.slice_index(len(scales))
total_boxes = []
for batch in sliced_index:
#local_boxes = self.Pool.map( detect_first_stage_warpper, \
# izip(repeat(img), self.PNets[:len(batch)], [scales[i] for i in batch], repeat(self.threshold[0])) )
local_boxes = map( detect_first_stage_warpper, \
izip(repeat(img), self.PNets[:len(batch)], [scales[i] for i in batch], repeat(self.threshold[0])) )
total_boxes.extend(local_boxes)
# remove the Nones
total_boxes = [i for i in total_boxes if i is not None]
if len(total_boxes) == 0:
return None
total_boxes = np.vstack(total_boxes)
if total_boxes.size == 0:
return None
# merge the detection from first stage
pick = nms(total_boxes[:, 0:5], 0.7, 'Union')
total_boxes = total_boxes[pick]
bbw = total_boxes[:, 2] - total_boxes[:, 0] + 1
bbh = total_boxes[:, 3] - total_boxes[:, 1] + 1
# refine the bboxes
total_boxes = np.vstack([
total_boxes[:, 0] + total_boxes[:, 5] * bbw,
total_boxes[:, 1] + total_boxes[:, 6] * bbh,
total_boxes[:, 2] + total_boxes[:, 7] * bbw,
total_boxes[:, 3] + total_boxes[:, 8] * bbh, total_boxes[:, 4]
])
total_boxes = total_boxes.T
total_boxes = self.convert_to_square(total_boxes)
total_boxes[:, 0:4] = np.round(total_boxes[:, 0:4])
else:
total_boxes = np.array(
[[0.0, 0.0, img.shape[1], img.shape[0], 0.9]],
dtype=np.float32)
#############################################
# second stage
#############################################
num_box = total_boxes.shape[0]
# pad the bbox
[dy, edy, dx, edx, y, ey, x, ex, tmpw,
tmph] = self.pad(total_boxes, width, height)
# (3, 24, 24) is the input shape for RNet
input_buf = np.zeros((num_box, 3, 24, 24), dtype=np.float32)
for i in range(num_box):
tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.uint8)
tmp[dy[i]:edy[i] + 1, dx[i]:edx[i] + 1, :] = img[y[i]:ey[i] + 1,
x[i]:ex[i] + 1, :]
input_buf[i, :, :, :] = adjust_input(cv2.resize(tmp, (24, 24)))
output = self.RNet.predict(input_buf)
# filter the total_boxes with threshold
passed = np.where(output[1][:, 1] > self.threshold[1])
total_boxes = total_boxes[passed]
if total_boxes.size == 0:
return None
total_boxes[:, 4] = output[1][passed, 1].reshape((-1, ))
reg = output[0][passed]
# nms
pick = nms(total_boxes, 0.7, 'Union')
total_boxes = total_boxes[pick]
total_boxes = self.calibrate_box(total_boxes, reg[pick])
total_boxes = self.convert_to_square(total_boxes)
total_boxes[:, 0:4] = np.round(total_boxes[:, 0:4])
#############################################
# third stage
#############################################
num_box = total_boxes.shape[0]
# pad the bbox
[dy, edy, dx, edx, y, ey, x, ex, tmpw,
tmph] = self.pad(total_boxes, width, height)
# (3, 48, 48) is the input shape for ONet
input_buf = np.zeros((num_box, 3, 48, 48), dtype=np.float32)
for i in range(num_box):
tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.float32)
tmp[dy[i]:edy[i] + 1, dx[i]:edx[i] + 1, :] = img[y[i]:ey[i] + 1,
x[i]:ex[i] + 1, :]
input_buf[i, :, :, :] = adjust_input(cv2.resize(tmp, (48, 48)))
output = self.ONet.predict(input_buf)
# filter the total_boxes with threshold
passed = np.where(output[2][:, 1] > self.threshold[2])
total_boxes = total_boxes[passed]
if total_boxes.size == 0:
return None
total_boxes[:, 4] = output[2][passed, 1].reshape((-1, ))
reg = output[1][passed]
points = output[0][passed]
# compute landmark points
bbw = total_boxes[:, 2] - total_boxes[:, 0] + 1
bbh = total_boxes[:, 3] - total_boxes[:, 1] + 1
points[:, 0:5] = np.expand_dims(
total_boxes[:, 0], 1) + np.expand_dims(bbw, 1) * points[:, 0:5]
points[:, 5:10] = np.expand_dims(
total_boxes[:, 1], 1) + np.expand_dims(bbh, 1) * points[:, 5:10]
# nms
total_boxes = self.calibrate_box(total_boxes, reg)
pick = nms(total_boxes, 0.7, 'Min')
total_boxes = total_boxes[pick]
points = points[pick]
if not self.accurate_landmark:
return total_boxes, points
#############################################
# extended stage
#############################################
num_box = total_boxes.shape[0]
patchw = np.maximum(total_boxes[:, 2] - total_boxes[:, 0] + 1,
total_boxes[:, 3] - total_boxes[:, 1] + 1)
patchw = np.round(patchw * 0.25)
# make it even
patchw[np.where(np.mod(patchw, 2) == 1)] += 1
input_buf = np.zeros((num_box, 15, 24, 24), dtype=np.float32)
for i in range(5):
x, y = points[:, i], points[:, i + 5]
x, y = np.round(x - 0.5 * patchw), np.round(y - 0.5 * patchw)
[dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph] = self.pad(
np.vstack([x, y, x + patchw - 1, y + patchw - 1]).T, width,
height)
for j in range(num_box):
tmpim = np.zeros((tmpw[j], tmpw[j], 3), dtype=np.float32)
tmpim[dy[j]:edy[j] + 1,
dx[j]:edx[j] + 1, :] = img[y[j]:ey[j] + 1,
x[j]:ex[j] + 1, :]
input_buf[j, i * 3:i * 3 + 3, :, :] = adjust_input(
cv2.resize(tmpim, (24, 24)))
output = self.LNet.predict(input_buf)
pointx = np.zeros((num_box, 5))
pointy = np.zeros((num_box, 5))
for k in range(5):
# do not make a large movement
tmp_index = np.where(np.abs(output[k] - 0.5) > 0.35)
output[k][tmp_index[0]] = 0.5
pointx[:, k] = np.round(points[:, k] -
0.5 * patchw) + output[k][:, 0] * patchw
pointy[:, k] = np.round(points[:, k + 5] -
0.5 * patchw) + output[k][:, 1] * patchw
points = np.hstack([pointx, pointy])
points = points.astype(np.int32)
return total_boxes, points
def list2colmatrix(self, pts_list):
"""
convert list to column matrix
Parameters:
----------
pts_list:
input list
Retures:
-------
colMat:
"""
assert len(pts_list) > 0
colMat = []
for i in range(len(pts_list)):
colMat.append(pts_list[i][0])
colMat.append(pts_list[i][1])
colMat = np.matrix(colMat).transpose()
return colMat
def find_tfrom_between_shapes(self, from_shape, to_shape):
"""
find transform between shapes
Parameters:
----------
from_shape:
to_shape:
Retures:
-------
tran_m:
tran_b:
"""
assert from_shape.shape[0] == to_shape.shape[
0] and from_shape.shape[0] % 2 == 0
sigma_from = 0.0
sigma_to = 0.0
cov = np.matrix([[0.0, 0.0], [0.0, 0.0]])
# compute the mean and cov
from_shape_points = from_shape.reshape(from_shape.shape[0] / 2, 2)
to_shape_points = to_shape.reshape(to_shape.shape[0] / 2, 2)
mean_from = from_shape_points.mean(axis=0)
mean_to = to_shape_points.mean(axis=0)
for i in range(from_shape_points.shape[0]):
temp_dis = np.linalg.norm(from_shape_points[i] - mean_from)
sigma_from += temp_dis * temp_dis
temp_dis = np.linalg.norm(to_shape_points[i] - mean_to)
sigma_to += temp_dis * temp_dis
cov += (to_shape_points[i].transpose() -
mean_to.transpose()) * (from_shape_points[i] - mean_from)
sigma_from = sigma_from / to_shape_points.shape[0]
sigma_to = sigma_to / to_shape_points.shape[0]
cov = cov / to_shape_points.shape[0]
# compute the affine matrix
s = np.matrix([[1.0, 0.0], [0.0, 1.0]])
u, d, vt = np.linalg.svd(cov)
if np.linalg.det(cov) < 0:
if d[1] < d[0]:
s[1, 1] = -1
else:
s[0, 0] = -1
r = u * s * vt
c = 1.0
if sigma_from != 0:
c = 1.0 / sigma_from * np.trace(np.diag(d) * s)
tran_b = mean_to.transpose() - c * r * mean_from.transpose()
tran_m = c * r
return tran_m, tran_b
def extract_image_chips(self, img, points, desired_size=256, padding=0):
"""
crop and align face
Parameters:
----------
img: numpy array, bgr order of shape (1, 3, n, m)
input image
points: numpy array, n x 10 (x1, x2 ... x5, y1, y2 ..y5)
desired_size: default 256
padding: default 0
Retures:
-------
crop_imgs: list, n
cropped and aligned faces
"""
crop_imgs = []
for p in points:
shape = []
for k in range(len(p) / 2):
shape.append(p[k])
shape.append(p[k + 5])
if padding > 0:
padding = padding
else:
padding = 0
# average positions of face points
mean_face_shape_x = [
0.224152, 0.75610125, 0.490127, 0.254149, 0.726104
]
mean_face_shape_y = [
0.2119465, 0.2119465, 0.628106, 0.780233, 0.780233
]
from_points = []
to_points = []
for i in range(len(shape) / 2):
x = (padding + mean_face_shape_x[i]) / (2 * padding +
1) * desired_size
y = (padding + mean_face_shape_y[i]) / (2 * padding +
1) * desired_size
to_points.append([x, y])
from_points.append([shape[2 * i], shape[2 * i + 1]])
# convert the points to Mat
from_mat = self.list2colmatrix(from_points)
to_mat = self.list2colmatrix(to_points)
# compute the similar transfrom
tran_m, tran_b = self.find_tfrom_between_shapes(from_mat, to_mat)
probe_vec = np.matrix([1.0, 0.0]).transpose()
probe_vec = tran_m * probe_vec
scale = np.linalg.norm(probe_vec)
angle = 180.0 / math.pi * math.atan2(probe_vec[1, 0], probe_vec[0,
0])
from_center = [(shape[0] + shape[2]) / 2.0,
(shape[1] + shape[3]) / 2.0]
to_center = [0, 0]
to_center[1] = desired_size * 0.4
to_center[0] = desired_size * 0.5
ex = to_center[0] - from_center[0]
ey = to_center[1] - from_center[1]
rot_mat = cv2.getRotationMatrix2D((from_center[0], from_center[1]),
-1 * angle, scale)
rot_mat[0][2] += ex
rot_mat[1][2] += ey
chips = cv2.warpAffine(img, rot_mat, (desired_size, desired_size))
crop_imgs.append(chips)
return crop_imgs

39
gender-age/test.py
View File

@@ -1,39 +0,0 @@
import face_model
import argparse
import cv2
import sys
import numpy as np
import datetime
parser = argparse.ArgumentParser(description='face model test')
# general
parser.add_argument('--image-size', default='112,112', help='')
parser.add_argument('--image', default='Tom_Hanks_54745.png', help='')
parser.add_argument('--model',
default='model/model,0',
help='path to load model.')
parser.add_argument('--gpu', default=0, type=int, help='gpu id')
parser.add_argument(
'--det',
default=0,
type=int,
help='mtcnn option, 1 means using R+O, 0 means detect from begining')
args = parser.parse_args()
model = face_model.FaceModel(args)
#img = cv2.imread('Tom_Hanks_54745.png')
img = cv2.imread(args.image)
img = model.get_input(img)
#f1 = model.get_feature(img)
#print(f1[0:10])
for _ in range(5):
gender, age = model.get_ga(img)
time_now = datetime.datetime.now()
count = 200
for _ in range(count):
gender, age = model.get_ga(img)
time_now2 = datetime.datetime.now()
diff = time_now2 - time_now
print('time cost', diff.total_seconds() / count)
print('gender is', gender)
print('age is', age)

420
gender-age/train.py
View File

@@ -1,420 +0,0 @@
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import sys
import math
import random
import logging
import pickle
import numpy as np
import sklearn
from data import FaceImageIter
import mxnet as mx
from mxnet import ndarray as nd
import argparse
import mxnet.optimizer as optimizer
sys.path.append(os.path.join(os.path.dirname(__file__), 'common'))
#import face_image
import fresnet
import fmobilenet
logger = logging.getLogger()
logger.setLevel(logging.INFO)
AGE = 100
args = None
class AccMetric(mx.metric.EvalMetric):
def __init__(self):
self.axis = 1
super(AccMetric, self).__init__('acc',
axis=self.axis,
output_names=None,
label_names=None)
self.losses = []
self.count = 0
def update(self, labels, preds):
self.count += 1
label = labels[0].asnumpy()[:, 0:1]
pred_label = preds[-1].asnumpy()[:, 0:2]
pred_label = np.argmax(pred_label, axis=self.axis)
pred_label = pred_label.astype('int32').flatten()
label = label.astype('int32').flatten()
assert label.shape == pred_label.shape
self.sum_metric += (pred_label.flat == label.flat).sum()
self.num_inst += len(pred_label.flat)
class LossValueMetric(mx.metric.EvalMetric):
def __init__(self):
self.axis = 1
super(LossValueMetric, self).__init__('lossvalue',
axis=self.axis,
output_names=None,
label_names=None)
self.losses = []
def update(self, labels, preds):
loss = preds[-1].asnumpy()[0]
self.sum_metric += loss
self.num_inst += 1.0
gt_label = preds[-2].asnumpy()
#print(gt_label)
class MAEMetric(mx.metric.EvalMetric):
def __init__(self):
self.axis = 1
super(MAEMetric, self).__init__('MAE',
axis=self.axis,
output_names=None,
label_names=None)
self.losses = []
self.count = 0
def update(self, labels, preds):
self.count += 1
label = labels[0].asnumpy()
label_age = np.count_nonzero(label[:, 1:], axis=1)
pred_age = np.zeros(label_age.shape, dtype=np.int)
#pred_age = np.zeros( label_age.shape, dtype=np.float32)
pred = preds[-1].asnumpy()
for i in range(AGE):
_pred = pred[:, 2 + i * 2:4 + i * 2]
_pred = np.argmax(_pred, axis=1)
#pred = pred[:,1]
pred_age += _pred
#pred_age = pred_age.astype(np.int)
mae = np.mean(np.abs(label_age - pred_age))
self.sum_metric += mae
self.num_inst += 1.0
class CUMMetric(mx.metric.EvalMetric):
def __init__(self, n=5):
self.axis = 1
self.n = n
super(CUMMetric, self).__init__('CUM_%d' % n,
axis=self.axis,
output_names=None,
label_names=None)
self.losses = []
self.count = 0
def update(self, labels, preds):
self.count += 1
label = labels[0].asnumpy()
label_age = np.count_nonzero(label[:, 1:], axis=1)
pred_age = np.zeros(label_age.shape, dtype=np.int)
pred = preds[-1].asnumpy()
for i in range(AGE):
_pred = pred[:, 2 + i * 2:4 + i * 2]
_pred = np.argmax(_pred, axis=1)
#pred = pred[:,1]
pred_age += _pred
diff = np.abs(label_age - pred_age)
cum = np.sum((diff < self.n))
self.sum_metric += cum
self.num_inst += len(label_age)
def parse_args():
parser = argparse.ArgumentParser(description='Train face network')
# general
parser.add_argument('--data-dir',
default='',
help='training set directory')
parser.add_argument('--prefix',
default='../model/model',
help='directory to save model.')
parser.add_argument('--pretrained',
default='',
help='pretrained model to load')
parser.add_argument(
'--ckpt',
type=int,
default=1,
help=
'checkpoint saving option. 0: discard saving. 1: save when necessary. 2: always save'
)
parser.add_argument('--loss-type', type=int, default=4, help='loss type')
parser.add_argument(
'--verbose',
type=int,
default=2000,
help='do verification testing and model saving every verbose batches')
parser.add_argument('--max-steps',
type=int,
default=0,
help='max training batches')
parser.add_argument('--end-epoch',
type=int,
default=100000,
help='training epoch size.')
parser.add_argument('--network', default='r50', help='specify network')
parser.add_argument('--image-size',
default='112,112',
help='specify input image height and width')
parser.add_argument('--version-input',
type=int,
default=1,
help='network input config')
parser.add_argument('--version-output',
type=str,
default='GAP',
help='network embedding output config')
parser.add_argument('--version-act',
type=str,
default='prelu',
help='network activation config')
parser.add_argument('--multiplier', type=float, default=1.0, help='')
parser.add_argument('--lr',
type=float,
default=0.1,
help='start learning rate')
parser.add_argument('--lr-steps',
type=str,
default='',
help='steps of lr changing')
parser.add_argument('--wd',
type=float,
default=0.0005,
help='weight decay')
parser.add_argument('--bn-mom', type=float, default=0.9, help='bn mom')
parser.add_argument('--mom', type=float, default=0.9, help='momentum')
parser.add_argument('--per-batch-size',
type=int,
default=128,
help='batch size in each context')
parser.add_argument('--rand-mirror',
type=int,
default=1,
help='if do random mirror in training')
parser.add_argument('--cutoff', type=int, default=0, help='cut off aug')
parser.add_argument('--color',
type=int,
default=0,
help='color jittering aug')
parser.add_argument('--ce-loss',
default=False,
action='store_true',
help='if output ce loss')
args = parser.parse_args()
return args
def get_symbol(args, arg_params, aux_params):
data_shape = (args.image_channel, args.image_h, args.image_w)
image_shape = ",".join([str(x) for x in data_shape])
margin_symbols = []
if args.network[0] == 'm':
fc1 = fmobilenet.get_symbol(AGE * 2 + 2,
multiplier=args.multiplier,
version_input=args.version_input,
version_output=args.version_output)
else:
fc1 = fresnet.get_symbol(AGE * 2 + 2,
args.num_layers,
version_input=args.version_input,
version_output=args.version_output)
label = mx.symbol.Variable('softmax_label')
gender_label = mx.symbol.slice_axis(data=label, axis=1, begin=0, end=1)
gender_label = mx.symbol.reshape(gender_label,
shape=(args.per_batch_size, ))
gender_fc1 = mx.symbol.slice_axis(data=fc1, axis=1, begin=0, end=2)
#gender_fc7 = mx.sym.FullyConnected(data=gender_fc1, num_hidden=2, name='gender_fc7')
gender_softmax = mx.symbol.SoftmaxOutput(data=gender_fc1,
label=gender_label,
name='gender_softmax',
normalization='valid',
use_ignore=True,
ignore_label=9999)
outs = [gender_softmax]
for i in range(AGE):
age_label = mx.symbol.slice_axis(data=label,
axis=1,
begin=i + 1,
end=i + 2)
age_label = mx.symbol.reshape(age_label, shape=(args.per_batch_size, ))
age_fc1 = mx.symbol.slice_axis(data=fc1,
axis=1,
begin=2 + i * 2,
end=4 + i * 2)
#age_fc7 = mx.sym.FullyConnected(data=age_fc1, num_hidden=2, name='age_fc7_%i'%i)
age_softmax = mx.symbol.SoftmaxOutput(data=age_fc1,
label=age_label,
name='age_softmax_%d' % i,
normalization='valid',
grad_scale=1)
outs.append(age_softmax)
outs.append(mx.sym.BlockGrad(fc1))
out = mx.symbol.Group(outs)
return (out, arg_params, aux_params)
def train_net(args):
ctx = []
cvd = os.environ['CUDA_VISIBLE_DEVICES'].strip()
if len(cvd) > 0:
for i in range(len(cvd.split(','))):
ctx.append(mx.gpu(i))
if len(ctx) == 0:
ctx = [mx.cpu()]
print('use cpu')
else:
print('gpu num:', len(ctx))
prefix = args.prefix
prefix_dir = os.path.dirname(prefix)
if not os.path.exists(prefix_dir):
os.makedirs(prefix_dir)
end_epoch = args.end_epoch
args.ctx_num = len(ctx)
args.num_layers = int(args.network[1:])
print('num_layers', args.num_layers)
if args.per_batch_size == 0:
args.per_batch_size = 128
args.batch_size = args.per_batch_size * args.ctx_num
args.rescale_threshold = 0
args.image_channel = 3
data_dir_list = args.data_dir.split(',')
assert len(data_dir_list) == 1
data_dir = data_dir_list[0]
path_imgrec = None
path_imglist = None
image_size = [int(x) for x in args.image_size.split(',')]
assert len(image_size) == 2
assert image_size[0] == image_size[1]
args.image_h = image_size[0]
args.image_w = image_size[1]
print('image_size', image_size)
path_imgrec = os.path.join(data_dir, "train.rec")
path_imgrec_val = os.path.join(data_dir, "val.rec")
print('Called with argument:', args)
data_shape = (args.image_channel, image_size[0], image_size[1])
mean = None
begin_epoch = 0
base_lr = args.lr
base_wd = args.wd
base_mom = args.mom
if len(args.pretrained) == 0:
arg_params = None
aux_params = None
sym, arg_params, aux_params = get_symbol(args, arg_params, aux_params)
else:
vec = args.pretrained.split(',')
print('loading', vec)
_, arg_params, aux_params = mx.model.load_checkpoint(
vec[0], int(vec[1]))
sym, arg_params, aux_params = get_symbol(args, arg_params, aux_params)
#label_name = 'softmax_label'
#label_shape = (args.batch_size,)
model = mx.mod.Module(
context=ctx,
symbol=sym,
)
val_dataiter = None
train_dataiter = FaceImageIter(
batch_size=args.batch_size,
data_shape=data_shape,
path_imgrec=path_imgrec,
shuffle=True,
rand_mirror=args.rand_mirror,
mean=mean,
cutoff=args.cutoff,
color_jittering=args.color,
)
val_dataiter = FaceImageIter(
batch_size=args.batch_size,
data_shape=data_shape,
path_imgrec=path_imgrec_val,
shuffle=False,
rand_mirror=False,
mean=mean,
)
metric = mx.metric.CompositeEvalMetric(
[AccMetric(), MAEMetric(), CUMMetric()])
if args.network[0] == 'r' or args.network[0] == 'y':
initializer = mx.init.Xavier(rnd_type='gaussian',
factor_type="out",
magnitude=2) #resnet style
elif args.network[0] == 'i' or args.network[0] == 'x':
initializer = mx.init.Xavier(rnd_type='gaussian',
factor_type="in",
magnitude=2) #inception
else:
initializer = mx.init.Xavier(rnd_type='uniform',
factor_type="in",
magnitude=2)
_rescale = 1.0 / args.ctx_num
opt = optimizer.SGD(learning_rate=base_lr,
momentum=base_mom,
wd=base_wd,
rescale_grad=_rescale)
#opt = optimizer.Nadam(learning_rate=base_lr, wd=base_wd, rescale_grad=_rescale)
som = 20
_cb = mx.callback.Speedometer(args.batch_size, som)
lr_steps = [int(x) for x in args.lr_steps.split(',')]
global_step = [0]
def _batch_callback(param):
_cb(param)
global_step[0] += 1
mbatch = global_step[0]
for _lr in lr_steps:
if mbatch == _lr:
opt.lr *= 0.1
print('lr change to', opt.lr)
break
if mbatch % 1000 == 0:
print('lr-batch-epoch:', opt.lr, param.nbatch, param.epoch)
if mbatch == lr_steps[-1]:
arg, aux = model.get_params()
all_layers = model.symbol.get_internals()
_sym = all_layers['fc1_output']
mx.model.save_checkpoint(args.prefix, 0, _sym, arg, aux)
sys.exit(0)
epoch_cb = None
train_dataiter = mx.io.PrefetchingIter(train_dataiter)
print('start fitting')
model.fit(
train_dataiter,
begin_epoch=begin_epoch,
num_epoch=end_epoch,
eval_data=val_dataiter,
eval_metric=metric,
kvstore='device',
optimizer=opt,
#optimizer_params = optimizer_params,
initializer=initializer,
arg_params=arg_params,
aux_params=aux_params,
allow_missing=True,
batch_end_callback=_batch_callback,
epoch_end_callback=epoch_cb)
def main():
#time.sleep(3600*6.5)
global args
args = parse_args()
train_net(args)
if __name__ == '__main__':
main()

2
python-package/README.md
View File

@@ -1,4 +1,4 @@
## Python package of insightface README
## Python package
For insightface pip-package <= 0.1.5, we use MXNet as inference backend, please download all models from [onedrive](https://1drv.ms/u/s!AswpsDO2toNKrUy0VktHTWgIQ0bn?e=UEF7C4), and put them all under `~/.insightface/models/` directory.

0
deploy/Tom_Hanks_54745.png → python-package/insightface/data/images/Tom_Hanks_54745.png
View File

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 12 KiB

After

Width:  |  Height:  |  Size: 12 KiB

0
sample-images/t1.jpg → python-package/insightface/data/images/t1.jpg
View File

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 126 KiB

After

Width:  |  Height:  |  Size: 126 KiB

10
python-package/insightface/model_zoo/arcface_onnx.py
View File

@@ -82,4 +82,14 @@ class ArcFaceONNX:
sim = np.dot(feat1, feat2) / (norm(feat1) * norm(feat2))
return sim
def forward(self, imgs):
if not isinstance(imgs, list):
imgs = [imgs]
input_size = self.input_size
blob = cv2.dnn.blobFromImages(imgs, 1.0 / self.input_std, input_size,
(self.input_mean, self.input_mean, self.input_mean), swapRB=True)
net_out = self.session.run(self.output_names, {self.input_name: blob})[0]
return net_out

58
recognition/README.md
View File

@@ -1,24 +1,46 @@
## Angular Margin Loss for Deep Face Recognition
## Face Recognition
### Citation
If you find this project useful in your research, please consider to cite the following related papers:
<div align="left">
<img src="https://insightface.ai/assets/img/custom/logo3.jpg" width="240"/>
</div>
```
@inproceedings{deng2019arcface,
title={Arcface: Additive angular margin loss for deep face recognition},
author={Deng, Jiankang and Guo, Jia and Xue, Niannan and Zafeiriou, Stefanos},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={4690--4699},
year={2019}
}
## Introduction
These are the face recognition methods of [InsightFace](https://insightface.ai)
<div align="left">
<img src="https://insightface.ai/assets/img/github/facerecognitionfromvideo.PNG" width="600"/>
</div>
### Datasets
Please refer to [datasets](_datasets_) page for the details of face recognition datasets used for training and evaluation.
### Evaluation
Please refer to [evaluation](_evaluation_) page for the details of face recognition evaluation.
## Methods
Supported methods:
- [x] [ArcFace_mxnet (CVPR'2019)](arcface_mxnet)
- [x] [ArcFace_torch (CVPR'2019)](arcface_torch)
- [x] [SubCenter ArcFace (ECCV'2020)](subcenter_arcface)
- [x] [PartialFC_mxnet (Arxiv'2020)](partial_fc)
- [x] [PartialFC_torch (Arxiv'2020)](arcface_torch)
- [x] [VPL (CVPR'2021)](vpl)
- [x] [OneFlow_face](oneflow_face)
## Contributing
We appreciate all contributions to improve the face recognition model zoo of InsightFace.
@inproceedings{deng2020subcenter,
title={Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces},
author={Deng, Jiankang and Guo, Jia and Liu, Tongliang and Gong, Mingming and Zafeiriou, Stefanos},
booktitle={Proceedings of the IEEE Conference on European Conference on Computer Vision},
year={2020}
}
```

24
recognition/_datasets_/README.md Normal file
View File

@@ -0,0 +1,24 @@
## Angular Margin Loss for Deep Face Recognition
### Citation
If you find this project useful in your research, please consider to cite the following related papers:
```
@inproceedings{deng2019arcface,
title={Arcface: Additive angular margin loss for deep face recognition},
author={Deng, Jiankang and Guo, Jia and Xue, Niannan and Zafeiriou, Stefanos},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={4690--4699},
year={2019}
}
@inproceedings{deng2020subcenter,
title={Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces},
author={Deng, Jiankang and Guo, Jia and Liu, Tongliang and Gong, Mingming and Zafeiriou, Stefanos},
booktitle={Proceedings of the IEEE Conference on European Conference on Computer Vision},
year={2020}
}
```

0
evaluation/IJB/README.md → recognition/_evaluation_/ijb/README.md
View File

4
evaluation/IJB/example.sh → recognition/_evaluation_/ijb/example.sh
View File

@@ -1,6 +1,6 @@
#!/usr/bin/env bash
python -u IJB_11.py --model-prefix ./pretrained_models/r100-arcface/model --model-epoch 1 --gpu 0 --target IJBC --job arcface > ijbc_11.log 2>&1 &
python -u ijb_11.py --model-prefix ./pretrained_models/r100-arcface/model --model-epoch 1 --gpu 0 --target IJBC --job arcface > ijbc_11.log 2>&1 &
python -u IJB_1N.py --model-prefix ./pretrained_models/r100-arcface/model --model-epoch 1 --gpu 0 --target IJBB --job arcface > ijbb_1n.log 2>&1 &
python -u ijb_1n.py --model-prefix ./pretrained_models/r100-arcface/model --model-epoch 1 --gpu 0 --target IJBB --job arcface > ijbb_1n.log 2>&1 &

0
evaluation/IJB/IJB_11.py → recognition/_evaluation_/ijb/ijb_11.py
View File

0
evaluation/IJB/IJB_1N.py → recognition/_evaluation_/ijb/ijb_1n.py
View File

0
evaluation/IJB/IJB_evals.py → recognition/_evaluation_/ijb/ijb_evals.py
View File

267
recognition/_evaluation_/ijb/ijb_onnx.py Normal file
View File

@@ -0,0 +1,267 @@
import argparse
import os
import pickle
import timeit
import cv2
import mxnet as mx
import numpy as np
import pandas as pd
import prettytable
import skimage.transform
from sklearn.metrics import roc_curve
from sklearn.preprocessing import normalize
import insightface
from insightface.model_zoo import ArcFaceONNX
SRC = np.array(
[
[30.2946, 51.6963],
[65.5318, 51.5014],
[48.0252, 71.7366],
[33.5493, 92.3655],
[62.7299, 92.2041]]
, dtype=np.float32)
SRC[:, 0] += 8.0
class AlignedDataSet(mx.gluon.data.Dataset):
def __init__(self, root, lines, align=True):
self.lines = lines
self.root = root
self.align = align
def __len__(self):
return len(self.lines)
def __getitem__(self, idx):
each_line = self.lines[idx]
name_lmk_score = each_line.strip().split(' ')
name = os.path.join(self.root, name_lmk_score[0])
img = cv2.cvtColor(cv2.imread(name), cv2.COLOR_BGR2RGB)
landmark5 = np.array([float(x) for x in name_lmk_score[1:-1]], dtype=np.float32).reshape((5, 2))
st = skimage.transform.SimilarityTransform()
st.estimate(landmark5, SRC)
img = cv2.warpAffine(img, st.params[0:2, :], (112, 112), borderValue=0.0)
img_1 = np.expand_dims(img, 0)
img_2 = np.expand_dims(np.fliplr(img), 0)
output = np.concatenate((img_1, img_2), axis=0).astype(np.float32)
output = np.transpose(output, (0, 3, 1, 2))
output = mx.nd.array(output)
return output
def extract(model_file, dataset):
model = ArcFaceONNX(model_file=model_file)
model.check()
feat_mat = np.zeros(shape=(len(dataset), 2 * model.feat_dim))
def batchify_fn(data):
return mx.nd.concat(*data, dim=0)
data_loader = mx.gluon.data.DataLoader(
dataset, 128, last_batch='keep', num_workers=4,
thread_pool=True, prefetch=16, batchify_fn=batchify_fn)
num_iter = 0
for batch in data_loader:
batch = batch.asnumpy()
feat = model.forward(batch)
feat = np.reshape(feat, (-1, model.feat_dim * 2))
feat_mat[128 * num_iter: 128 * num_iter + feat.shape[0], :] = feat
num_iter += 1
if num_iter % 50 == 0:
print(num_iter)
return feat_mat
def read_template_media_list(path):
ijb_meta = pd.read_csv(path, sep=' ', header=None).values
templates = ijb_meta[:, 1].astype(np.int)
medias = ijb_meta[:, 2].astype(np.int)
return templates, medias
def read_template_pair_list(path):
pairs = pd.read_csv(path, sep=' ', header=None).values
t1 = pairs[:, 0].astype(np.int)
t2 = pairs[:, 1].astype(np.int)
label = pairs[:, 2].astype(np.int)
return t1, t2, label
def read_image_feature(path):
with open(path, 'rb') as fid:
img_feats = pickle.load(fid)
return img_feats
def image2template_feature(img_feats=None,
templates=None,
medias=None):
unique_templates = np.unique(templates)
template_feats = np.zeros((len(unique_templates), img_feats.shape[1]))
for count_template, uqt in enumerate(unique_templates):
(ind_t,) = np.where(templates == uqt)
face_norm_feats = img_feats[ind_t]
face_medias = medias[ind_t]
unique_medias, unique_media_counts = np.unique(face_medias, return_counts=True)
media_norm_feats = []
for u, ct in zip(unique_medias, unique_media_counts):
(ind_m,) = np.where(face_medias == u)
if ct == 1:
media_norm_feats += [face_norm_feats[ind_m]]
else: # image features from the same video will be aggregated into one feature
media_norm_feats += [np.mean(face_norm_feats[ind_m], axis=0, keepdims=True), ]
media_norm_feats = np.array(media_norm_feats)
template_feats[count_template] = np.sum(media_norm_feats, axis=0)
if count_template % 2000 == 0:
print('Finish Calculating {} template features.'.format(
count_template))
template_norm_feats = normalize(template_feats)
return template_norm_feats, unique_templates
def verification(template_norm_feats=None,
unique_templates=None,
p1=None,
p2=None):
template2id = np.zeros((max(unique_templates) + 1, 1), dtype=int)
for count_template, uqt in enumerate(unique_templates):
template2id[uqt] = count_template
score = np.zeros((len(p1),))
total_pairs = np.array(range(len(p1)))
batchsize = 100000
sublists = [total_pairs[i: i + batchsize] for i in range(0, len(p1), batchsize)]
total_sublists = len(sublists)
for c, s in enumerate(sublists):
feat1 = template_norm_feats[template2id[p1[s]]]
feat2 = template_norm_feats[template2id[p2[s]]]
similarity_score = np.sum(feat1 * feat2, -1)
score[s] = similarity_score.flatten()
if c % 10 == 0:
print('Finish {}/{} pairs.'.format(c, total_sublists))
return score
def verification2(template_norm_feats=None,
unique_templates=None,
p1=None,
p2=None):
template2id = np.zeros((max(unique_templates) + 1, 1), dtype=int)
for count_template, uqt in enumerate(unique_templates):
template2id[uqt] = count_template
score = np.zeros((len(p1),)) # save cosine distance between pairs
total_pairs = np.array(range(len(p1)))
batchsize = 100000 # small batchsize instead of all pairs in one batch due to the memory limiation
sublists = [total_pairs[i:i + batchsize] for i in range(0, len(p1), batchsize)]
total_sublists = len(sublists)
for c, s in enumerate(sublists):
feat1 = template_norm_feats[template2id[p1[s]]]
feat2 = template_norm_feats[template2id[p2[s]]]
similarity_score = np.sum(feat1 * feat2, -1)
score[s] = similarity_score.flatten()
if c % 10 == 0:
print('Finish {}/{} pairs.'.format(c, total_sublists))
return score
def main(args):
use_norm_score = True # if Ture, TestMode(N1)
use_detector_score = True # if Ture, TestMode(D1)
use_flip_test = True # if Ture, TestMode(F1)
assert args.target == 'IJBC' or args.target == 'IJBB'
start = timeit.default_timer()
templates, medias = read_template_media_list(
os.path.join('%s/meta' % args.image_path, '%s_face_tid_mid.txt' % args.target.lower()))
stop = timeit.default_timer()
print('Time: %.2f s. ' % (stop - start))
start = timeit.default_timer()
p1, p2, label = read_template_pair_list(
os.path.join('%s/meta' % args.image_path,
'%s_template_pair_label.txt' % args.target.lower()))
stop = timeit.default_timer()
print('Time: %.2f s. ' % (stop - start))
start = timeit.default_timer()
img_path = '%s/loose_crop' % args.image_path
img_list_path = '%s/meta/%s_name_5pts_score.txt' % (args.image_path, args.target.lower())
img_list = open(img_list_path)
files = img_list.readlines()
dataset = AlignedDataSet(root=img_path, lines=files, align=True)
img_feats = extract(args.model_file, dataset)
faceness_scores = []
for each_line in files:
name_lmk_score = each_line.split()
faceness_scores.append(name_lmk_score[-1])
faceness_scores = np.array(faceness_scores).astype(np.float32)
stop = timeit.default_timer()
print('Time: %.2f s. ' % (stop - start))
print('Feature Shape: ({} , {}) .'.format(img_feats.shape[0], img_feats.shape[1]))
start = timeit.default_timer()
if use_flip_test:
img_input_feats = img_feats[:, 0:img_feats.shape[1] // 2] + img_feats[:, img_feats.shape[1] // 2:]
else:
img_input_feats = img_feats[:, 0:img_feats.shape[1] // 2]
if use_norm_score:
img_input_feats = img_input_feats
else:
img_input_feats = img_input_feats / np.sqrt(np.sum(img_input_feats ** 2, -1, keepdims=True))
if use_detector_score:
print(img_input_feats.shape, faceness_scores.shape)
img_input_feats = img_input_feats * faceness_scores[:, np.newaxis]
else:
img_input_feats = img_input_feats
template_norm_feats, unique_templates = image2template_feature(
img_input_feats, templates, medias)
stop = timeit.default_timer()
print('Time: %.2f s. ' % (stop - start))
start = timeit.default_timer()
score = verification(template_norm_feats, unique_templates, p1, p2)
stop = timeit.default_timer()
print('Time: %.2f s. ' % (stop - start))
save_path = os.path.join(args.result_dir, "{}_result".format(args.target))
if not os.path.exists(save_path):
os.makedirs(save_path)
score_save_file = os.path.join(save_path, "{}.npy".format(args.model_file.split('/')[-1]))
np.save(score_save_file, score)
files = [score_save_file]
methods = []
scores = []
for file in files:
methods.append(os.path.basename(file))
scores.append(np.load(file))
methods = np.array(methods)
scores = dict(zip(methods, scores))
x_labels = [10 ** -6, 10 ** -5, 10 ** -4, 10 ** -3, 10 ** -2, 10 ** -1]
tpr_fpr_table = prettytable.PrettyTable(['Methods'] + [str(x) for x in x_labels])
for method in methods:
fpr, tpr, _ = roc_curve(label, scores[method])
fpr = np.flipud(fpr)
tpr = np.flipud(tpr)
tpr_fpr_row = []
tpr_fpr_row.append("%s-%s" % (method, args.target))
for fpr_iter in np.arange(len(x_labels)):
_, min_index = min(
list(zip(abs(fpr - x_labels[fpr_iter]), range(len(fpr)))))
tpr_fpr_row.append('%.2f' % (tpr[min_index] * 100))
tpr_fpr_table.add_row(tpr_fpr_row)
print(tpr_fpr_table)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='do onnx ijb test')
# general
parser.add_argument('--model-file', default='', help='path to onnx model.')
parser.add_argument('--image-path', default='', type=str, help='')
parser.add_argument('--result-dir', default='.', type=str, help='')
parser.add_argument('--target', default='IJBC', type=str, help='target, set to IJBC or IJBB')
main(parser.parse_args())

0
evaluation/Megaface/README.md → recognition/_evaluation_/megaface/README.md
View File

0
evaluation/Megaface/gen_megaface.py → recognition/_evaluation_/megaface/gen_megaface.py
View File

Some files were not shown because too many files have changed in this diff Show More