-
Notifications
You must be signed in to change notification settings - Fork 0
/
detect_face.py
205 lines (165 loc) · 7.57 KB
/
detect_face.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
# -*- coding: UTF-8 -*-
import argparse
import time
from pathlib import Path
import cv2
import torch
import torch.backends.cudnn as cudnn
from numpy import random
import copy
from models.experimental import attempt_load
from utils.datasets import letterbox
from utils.general import check_img_size, non_max_suppression_face, apply_classifier, scale_coords, xyxy2xywh, \
strip_optimizer, set_logging, increment_path
from utils.plots import plot_one_box
from utils.torch_utils import select_device, load_classifier, time_synchronized
import os
os.environ['CUDA_VISIBLE_DEVICES'] = "2"
def load_model(weights, device):
model = attempt_load(weights, map_location=device) # load FP32 model
return model
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = load_model('./weights/yolov5n-face.pt', device)
video_path = './images/chinese_1.mp4'
def scale_coords_landmarks(img1_shape, coords, img0_shape, ratio_pad=None):
# Rescale coords (xyxy) from img1_shape to img0_shape
if ratio_pad is None: # calculate from img0_shape
gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new
pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding
else:
gain = ratio_pad[0][0]
pad = ratio_pad[1]
coords[:, [0, 2, 4, 6, 8]] -= pad[0] # x padding
coords[:, [1, 3, 5, 7, 9]] -= pad[1] # y padding
coords[:, :10] /= gain
#clip_coords(coords, img0_shape)
coords[:, 0].clamp_(0, img0_shape[1]) # x1
coords[:, 1].clamp_(0, img0_shape[0]) # y1
coords[:, 2].clamp_(0, img0_shape[1]) # x2
coords[:, 3].clamp_(0, img0_shape[0]) # y2
coords[:, 4].clamp_(0, img0_shape[1]) # x3
coords[:, 5].clamp_(0, img0_shape[0]) # y3
coords[:, 6].clamp_(0, img0_shape[1]) # x4
coords[:, 7].clamp_(0, img0_shape[0]) # y4
coords[:, 8].clamp_(0, img0_shape[1]) # x5
coords[:, 9].clamp_(0, img0_shape[0]) # y5
return coords
def show_results(img, xywh, conf, landmarks, class_num):
h,w,c = img.shape
tl = 1 or round(0.002 * (h + w) / 2) + 1 # line/font thickness
x1 = int(xywh[0] * w - 0.5 * xywh[2] * w)
y1 = int(xywh[1] * h - 0.5 * xywh[3] * h)
x2 = int(xywh[0] * w + 0.5 * xywh[2] * w)
y2 = int(xywh[1] * h + 0.5 * xywh[3] * h)
cv2.rectangle(img, (x1,y1), (x2, y2), (0,255,0), thickness=tl, lineType=cv2.LINE_AA)
clors = [(255,0,0),(0,255,0),(0,0,255),(255,255,0),(0,255,255)]
for i in range(5):
point_x = int(landmarks[2 * i] * w)
point_y = int(landmarks[2 * i + 1] * h)
cv2.circle(img, (point_x, point_y), tl+1, clors[i], -1)
tf = max(tl - 1, 1) # font thickness
label = str(conf)[:5]
cv2.putText(img, label, (x1, y1 - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)
return img
def detect_one(model, image_path, device):
# Load model
img_size = 2048
conf_thres = 0.3
iou_thres = 0.5
orgimg = cv2.imread(image_path) # BGR
img0 = copy.deepcopy(orgimg)
assert orgimg is not None, 'Image Not Found ' + image_path
h0, w0 = orgimg.shape[:2] # orig hw
r = img_size / max(h0, w0) # resize image to img_size
if r != 1: # always resize down, only resize up if training with augmentation
interp = cv2.INTER_AREA if r < 1 else cv2.INTER_LINEAR
img0 = cv2.resize(img0, (int(w0 * r), int(h0 * r)), interpolation=interp)
imgsz = check_img_size(img_size, s=model.stride.max()) # check img_size
img = letterbox(img0, new_shape=imgsz)[0]
# Convert
img = img[:, :, ::-1].transpose(2, 0, 1).copy() # BGR to RGB, to 3x416x416
# Run inference
t0 = time.time()
img = torch.from_numpy(img).to(device)
img = img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
# Inference
t1 = time_synchronized()
pred = model(img)[0]
# Apply NMS
pred = non_max_suppression_face(pred, conf_thres, iou_thres)
print('img.shape: ', img.shape)
print('orgimg.shape: ', orgimg.shape)
# Process detections
for i, det in enumerate(pred): # detections per image
gn = torch.tensor(orgimg.shape)[[1, 0, 1, 0]].to(device) # normalization gain whwh
gn_lks = torch.tensor(orgimg.shape)[[1, 0, 1, 0, 1, 0, 1, 0, 1, 0]].to(device) # normalization gain landmarks
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], orgimg.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
det[:, 5:15] = scale_coords_landmarks(img.shape[2:], det[:, 5:15], orgimg.shape).round()
for j in range(det.size()[0]):
xywh = (xyxy2xywh(det[j, :4].view(1, 4)) / gn).view(-1).tolist()
conf = det[j, 4].cpu().numpy()
landmarks = (det[j, 5:15].view(1, 10) / gn_lks).view(-1).tolist()
class_num = det[j, 15].cpu().numpy()
orgimg = show_results(orgimg, xywh, conf, landmarks, class_num)
cv2.imwrite('result.jpg', orgimg)
def detect_frame(orgimg):
# Load model
img_size = 2048
conf_thres = 0.3
iou_thres = 0.5
# orgimg = cv2.imread(image_path) # BGR
img0 = copy.deepcopy(orgimg)
assert orgimg is not None, 'Image Not Found ' + image_path
h0, w0 = orgimg.shape[:2] # orig hw
# print(h0,w0)
r = img_size / max(h0, w0) # resize image to img_size
if r != 1: # always resize down, only resize up if training with augmentation
interp = cv2.INTER_AREA if r < 1 else cv2.INTER_LINEAR
img0 = cv2.resize(img0, (int(w0 * r), int(h0 * r)), interpolation=interp)
imgsz = check_img_size(img_size, s=model.stride.max()) # check img_size
print(f"imgsz :{imgsz}")
img = letterbox(img0, new_shape=imgsz)[0]
# Convert
img = img[:, :, ::-1].transpose(2, 0, 1).copy() # BGR to RGB, to 3x416x416
# Run inference
t0 = time.time()
img = torch.from_numpy(img).to(device)
img = img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
# Inference
t1 = time_synchronized()
pred = model(img)[0]
# Apply NMS
pred = non_max_suppression_face(pred, conf_thres, iou_thres)
# print('img.shape: ', img.shape)
# print('orgimg.shape: ', orgimg.shape)
# Process detections
for i, det in enumerate(pred): # detections per image
gn = torch.tensor(orgimg.shape)[[1, 0, 1, 0]].to(device) # normalization gain whwh
gn_lks = torch.tensor(orgimg.shape)[[1, 0, 1, 0, 1, 0, 1, 0, 1, 0]].to(device) # normalization gain landmarks
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], orgimg.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
det[:, 5:15] = scale_coords_landmarks(img.shape[2:], det[:, 5:15], orgimg.shape).round()
for j in range(det.size()[0]):
xywh = (xyxy2xywh(det[j, :4].view(1, 4)) / gn).view(-1).tolist()
conf = det[j, 4].cpu().numpy()
landmarks = (det[j, 5:15].view(1, 10) / gn_lks).view(-1).tolist()
class_num = det[j, 15].cpu().numpy()
orgimg = show_results(orgimg, xywh, conf, landmarks, class_num)
# cv2.imwrite('result.jpg', orgimg)
return orgimg
def FrameToNum():