add some tests

Add MobileViT

.github/workflows/python-test.yml

@@ -0,0 +1,33 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Test
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.7, 3.8, 3.9]
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install pytest
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+    - name: Test with pytest
+      run: |
+        python setup.py test

README.md

@@ -19,9 +19,11 @@
 - [CrossFormer](#crossformer)
 - [RegionViT](#regionvit)
 - [NesT](#nest)
+- [MobileViT](#mobilevit)
 - [Masked Autoencoder](#masked-autoencoder)
 - [Simple Masked Image Modeling](#simple-masked-image-modeling)
 - [Masked Patch Prediction](#masked-patch-prediction)
+- [Adaptive Token Sampling](#adaptive-token-sampling)
 - [Dino](#dino)
 - [Accessing Attention](#accessing-attention)
 - [Research Ideas](#research-ideas)
@@ -548,6 +550,31 @@ img = torch.randn(1, 3, 224, 224)
 pred = nest(img) # (1, 1000)
 ```
 
+## MobileViT
+
+<img src="./images/mbvit.png" width="400px"></img>
+
+This <a href="https://arxiv.org/abs/2110.02178">paper</a> introduce MobileViT, a light-weight and general purpose vision transformer for mobile devices. MobileViT presents a different
+perspective for the global processing of information with transformers.
+
+You can use it with the following code (ex. mobilevit_xs)
+
+```python
+import torch
+from vit_pytorch.mobile_vit import MobileViT
+
+mbvit_xs = MobileViT(
+    image_size = (256, 256),
+    dims = [96, 120, 144],
+    channels = [16, 32, 48, 48, 64, 64, 80, 80, 96, 96, 384],
+    num_classes = 1000
+)
+
+img = torch.randn(1, 3, 256, 256)
+
+pred = mbvit_xs(img) # (1, 1000)
+```
+
 ## Simple Masked Image Modeling
 
 <img src="./images/simmim.png" width="400px"/>
@@ -807,6 +834,41 @@ to cleanup the class and the hooks once you have collected enough data
 v = v.eject()  # wrapper is discarded and original ViT instance is returned
 ```
 
+## Accessing Embeddings
+
+You can similarly access the embeddings with the `Extractor` wrapper
+
+```python
+import torch
+from vit_pytorch.vit import ViT
+
+v = ViT(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+# import Recorder and wrap the ViT
+
+from vit_pytorch.extractor import Extractor
+v = Extractor(v)
+
+# forward pass now returns predictions and the attention maps
+
+img = torch.randn(1, 3, 256, 256)
+logits, embeddings = v(img)
+
+# there is one extra token due to the CLS token
+
+embeddings # (1, 65, 1024) - (batch x patches x model dim)
+```
+
 ## Research Ideas
 
 ### Efficient Attention
@@ -1163,6 +1225,17 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@misc{mehta2021mobilevit,
+    title   = {MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer},
+    author  = {Sachin Mehta and Mohammad Rastegari},
+    year    = {2021},
+    eprint  = {2110.02178},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
 ```bibtex
 @misc{vaswani2017attention,
     title   = {Attention Is All You Need},

setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'vit-pytorch',
   packages = find_packages(exclude=['examples']),
-  version = '0.24.3',
+  version = '0.25.3',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
   author = 'Phil Wang',
@@ -19,6 +19,12 @@ setup(
     'torch>=1.6',
     'torchvision'
   ],
+  setup_requires=[
+    'pytest-runner',
+  ],
+  tests_require=[
+    'pytest'
+  ],
   classifiers=[
     'Development Status :: 4 - Beta',
     'Intended Audience :: Developers',

tests/test.py

@@ -0,0 +1,20 @@
+import torch
+from vit_pytorch import ViT
+
+def test():
+    v = ViT(
+        image_size = 256,
+        patch_size = 32,
+        num_classes = 1000,
+        dim = 1024,
+        depth = 6,
+        heads = 16,
+        mlp_dim = 2048,
+        dropout = 0.1,
+        emb_dropout = 0.1
+    )
+
+    img = torch.randn(1, 3, 256, 256)
+
+    preds = v(img)
+    assert preds.shape == (1, 1000), 'correct logits outputted'

vit_pytorch/extractor.py

@@ -0,0 +1,48 @@
+import torch
+from torch import nn
+
+def exists(val):
+    return val is not None
+
+class Extractor(nn.Module):
+    def __init__(self, vit, device = None):
+        super().__init__()
+        self.vit = vit
+
+        self.data = None
+        self.latents = None
+        self.hooks = []
+        self.hook_registered = False
+        self.ejected = False
+        self.device = device
+
+    def _hook(self, _, input, output):
+        self.latents = output.clone().detach()
+
+    def _register_hook(self):
+        handle = self.vit.transformer.register_forward_hook(self._hook)
+        self.hooks.append(handle)
+        self.hook_registered = True
+
+    def eject(self):
+        self.ejected = True
+        for hook in self.hooks:
+            hook.remove()
+        self.hooks.clear()
+        return self.vit
+
+    def clear(self):
+        del self.latents
+        self.latents = None
+
+    def forward(self, img):
+        assert not self.ejected, 'extractor has been ejected, cannot be used anymore'
+        self.clear()
+        if not self.hook_registered:
+            self._register_hook()
+
+        pred = self.vit(img)
+
+        target_device = self.device if exists(self.device) else img.device
+        latents = self.latents.to(target_device)
+        return pred, latents

vit_pytorch/mobile_vit.py

@@ -0,0 +1,239 @@
+"""
+An implementation of MobileViT Model as defined in:
+MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
+Arxiv: https://arxiv.org/abs/2110.02178
+Origin Code: https://github.com/murufeng/awesome_lightweight_networks
+"""
+
+import torch
+import torch.nn as nn
+
+from einops import rearrange
+from einops.layers.torch import Reduce
+
+def _make_divisible(v, divisor, min_value=None):
+    if min_value is None:
+        min_value = divisor
+    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
+    if new_v < 0.9 * v:
+        new_v += divisor
+    return new_v
+
+
+def conv_bn_relu(inp, oup, kernel, stride=1):
+    return nn.Sequential(
+        nn.Conv2d(inp, oup, kernel_size=kernel, stride=stride, padding=1, bias=False),
+        nn.BatchNorm2d(oup),
+        nn.ReLU6(inplace=True)
+    )
+
+
+def conv_1x1_bn(inp, oup):
+    return nn.Sequential(
+        nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
+        nn.BatchNorm2d(oup),
+        nn.ReLU6(inplace=True)
+    )
+
+class PreNorm(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.fn = fn
+
+    def forward(self, x, **kwargs):
+        return self.fn(self.norm(x), **kwargs)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout=0.):
+        super().__init__()
+        self.ffn = nn.Sequential(
+            nn.Linear(dim, hidden_dim),
+            nn.SiLU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        return self.ffn(x)
+
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads=8, dim_head=64, dropout=0.):
+        super().__init__()
+        inner_dim = dim_head * heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim=-1)
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias=False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        qkv = self.to_qkv(x).chunk(3, dim=-1)
+        q, k, v = map(lambda t: rearrange(t, 'b p n (h d) -> b p h n d', h=self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+        attn = self.attend(dots)
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b p h n d -> b p n (h d)')
+        return self.to_out(out)
+
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+            ]))
+
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class MV2Block(nn.Module):
+    def __init__(self, inp, oup, stride=1, expand_ratio=4):
+        super(MV2Block, self).__init__()
+        assert stride in [1, 2]
+
+        hidden_dim = round(inp * expand_ratio)
+        self.identity = stride == 1 and inp == oup
+
+        if expand_ratio == 1:
+            self.conv = nn.Sequential(
+                # dw
+                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
+                nn.BatchNorm2d(hidden_dim),
+                nn.SiLU(),
+                # pw-linear
+                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
+                nn.BatchNorm2d(oup),
+            )
+        else:
+            self.conv = nn.Sequential(
+                # pw
+                nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False),
+                nn.BatchNorm2d(hidden_dim),
+                nn.SiLU(),
+                # dw
+                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
+                nn.BatchNorm2d(hidden_dim),
+                nn.SiLU(),
+                # pw-linear
+                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
+                nn.BatchNorm2d(oup),
+            )
+
+    def forward(self, x):
+        out = self.conv(x)
+
+        if self.identity:
+            out = out + x
+        return out
+
+class MobileViTBlock(nn.Module):
+    def __init__(self, dim, depth, channel, kernel_size, patch_size, mlp_dim, dropout=0.):
+        super().__init__()
+        self.ph, self.pw = patch_size
+
+        self.conv1 = conv_bn_relu(channel, channel, kernel_size)
+        self.conv2 = conv_1x1_bn(channel, dim)
+
+        self.transformer = Transformer(dim, depth, 1, 32, mlp_dim, dropout)
+
+        self.conv3 = conv_1x1_bn(dim, channel)
+        self.conv4 = conv_bn_relu(2 * channel, channel, kernel_size)
+
+    def forward(self, x):
+        y = x.clone()
+
+        # Local representations
+        x = self.conv1(x)
+        x = self.conv2(x)
+
+        # Global representations
+        _, _, h, w = x.shape
+        x = rearrange(x, 'b d (h ph) (w pw) -> b (ph pw) (h w) d', ph=self.ph, pw=self.pw)
+        x = self.transformer(x)
+        x = rearrange(x, 'b (ph pw) (h w) d -> b d (h ph) (w pw)', h=h // self.ph, w=w // self.pw, ph=self.ph, pw=self.pw)
+
+        # Fusion
+        x = self.conv3(x)
+        x = torch.cat((x, y), 1)
+        x = self.conv4(x)
+        return x
+
+
+class MobileViT(nn.Module):
+    def __init__(
+        self,
+        image_size,
+        dims,
+        channels,
+        num_classes,
+        expansion = 4,
+        kernel_size = 3,
+        patch_size = (2, 2),
+        depths = (2, 4, 3)
+    ):
+        super().__init__()
+        assert len(dims) == 3, 'dims must be a tuple of 3'
+        assert len(depths) == 3, 'depths must be a tuple of 3'
+
+        ih, iw = image_size
+        ph, pw = patch_size
+        assert ih % ph == 0 and iw % pw == 0
+
+        init_dim, *_, last_dim = channels
+
+        self.conv1 = conv_bn_relu(3, init_dim, kernel=3, stride=2)
+
+        self.stem = nn.ModuleList([])
+        self.stem.append(MV2Block(channels[0], channels[1], 1, expansion))
+        self.stem.append(MV2Block(channels[1], channels[2], 2, expansion))
+        self.stem.append(MV2Block(channels[2], channels[3], 1, expansion))
+        self.stem.append(MV2Block(channels[2], channels[3], 1, expansion))
+    
+        self.trunk = nn.ModuleList([])
+        self.trunk.append(nn.ModuleList([
+            MV2Block(channels[3], channels[4], 2, expansion),
+            MobileViTBlock(dims[0], depths[0], channels[5], kernel_size, patch_size, int(dims[0] * 2))
+        ]))
+
+        self.trunk.append(nn.ModuleList([
+            MV2Block(channels[5], channels[6], 2, expansion),
+            MobileViTBlock(dims[1], depths[1], channels[7], kernel_size, patch_size, int(dims[1] * 4))
+        ]))
+
+        self.trunk.append(nn.ModuleList([
+            MV2Block(channels[7], channels[8], 2, expansion),
+            MobileViTBlock(dims[2], depths[2], channels[9], kernel_size, patch_size, int(dims[2] * 4))
+        ]))
+
+        self.to_logits = nn.Sequential(
+            conv_1x1_bn(channels[-2], last_dim),
+            Reduce('b c h w -> b c', 'mean'),
+            nn.Linear(channels[-1], num_classes, bias=False)
+        )
+
+    def forward(self, x):
+        x = self.conv1(x)
+
+        for conv in self.stem:
+            x = conv(x)
+
+        for conv, attn in self.trunk:
+            x = conv(x)
+            x = attn(x)
+
+        return self.to_logits(x)