mirror of
https://github.com/deepinsight/insightface.git
synced 2026-05-19 15:41:33 +00:00
82 lines
2.6 KiB
Python
82 lines
2.6 KiB
Python
# -*- coding: utf-8 -*-
|
|
# @Organization : insightface.ai
|
|
# @Author : Jia Guo
|
|
# @Time : 2021-05-04
|
|
# @Function :
|
|
|
|
from __future__ import division
|
|
import numpy as np
|
|
import cv2
|
|
import onnx
|
|
import onnxruntime
|
|
from ..utils import face_align
|
|
|
|
__all__ = [
|
|
'ArcFaceONNX',
|
|
]
|
|
|
|
|
|
class ArcFaceONNX:
|
|
def __init__(self, model_file=None, session=None):
|
|
import onnxruntime
|
|
assert model_file is not None
|
|
self.model_file = model_file
|
|
self.session = session
|
|
self.taskname = 'recognition'
|
|
find_sub = False
|
|
find_mul = False
|
|
model = onnx.load(self.model_file)
|
|
graph = model.graph
|
|
for nid, node in enumerate(graph.node[:8]):
|
|
#print(nid, node.name)
|
|
if node.name.startswith('Sub') or node.name.startswith('_minus'):
|
|
find_sub = True
|
|
if node.name.startswith('Mul') or node.name.startswith('_mul'):
|
|
find_mul = True
|
|
if find_sub and find_mul:
|
|
#mxnet arcface model
|
|
input_mean = 0.0
|
|
input_std = 1.0
|
|
else:
|
|
input_mean = 127.5
|
|
input_std = 127.5
|
|
self.input_mean = input_mean
|
|
self.input_std = input_std
|
|
print('input mean and std:', self.input_mean, self.input_std)
|
|
if self.session is None:
|
|
self.session = onnxruntime.InferenceSession(self.model_file, None)
|
|
input_cfg = self.session.get_inputs()[0]
|
|
input_shape = input_cfg.shape
|
|
input_name = input_cfg.name
|
|
self.input_size = tuple(input_shape[2:4][::-1])
|
|
outputs = self.session.get_outputs()
|
|
output_names = []
|
|
for out in outputs:
|
|
output_names.append(out.name)
|
|
self.input_name = input_name
|
|
self.output_names = output_names
|
|
assert len(self.output_names)==1
|
|
|
|
def prepare(self, ctx_id, **kwargs):
|
|
if ctx_id<0:
|
|
self.session.set_providers(['CPUExecutionProvider'])
|
|
|
|
def get_feat(self, img):
|
|
assert img.shape[2] == 3
|
|
input_size = tuple(img.shape[0:2][::-1])
|
|
assert input_size==self.input_size
|
|
blob = cv2.dnn.blobFromImage(img, 1.0/self.input_std, input_size, (self.input_mean, self.input_mean, self.input_mean), swapRB=True)
|
|
net_outs = self.session.run(self.output_names, {self.input_name : blob})
|
|
feat = net_outs[0]
|
|
return feat
|
|
|
|
|
|
def compute_sim(self, feat1, feat2):
|
|
from np.linalg import norm
|
|
feat1 = feat1.ravel()
|
|
feat2 = feat2.ravel()
|
|
sim = np.dot(feat1, feat2) / (norm(feat1) * norm(feat2))
|
|
return sim
|
|
|
|
|