-
Notifications
You must be signed in to change notification settings - Fork 26
/
tflite_detect.py
212 lines (173 loc) · 8.41 KB
/
tflite_detect.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
205
206
207
208
209
210
211
import argparse
from sys import platform
import sys
from models import * # set ONNX_EXPORT in models.py
from utils.datasets import *
from utils.utils import *
import onnxruntime as rt
import cv2
import time
import numpy as np
import tensorflow as tf
def detect(save_txt=False, save_img=False):
# img_size = (320, 192) if ONNX_EXPORT else opt.img_size # (320, 192) or (416, 256) or (608, 352) for (height, width)
img_size = (416, 416)
out, source, weights, half, view_img = opt.output, opt.source, opt.weights, opt.half, opt.view_img
webcam = source == '0' or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt')
# Initialize
device = torch_utils.select_device(device='cpu' if ONNX_EXPORT else opt.device)
if os.path.exists(out):
shutil.rmtree(out) # delete output folder
os.makedirs(out) # make new output folder
# Initialize model
# model = Darknet(opt.cfg, img_size)
# sess = rt.InferenceSession("weights/export.onnx")
# input_name = sess.get_inputs()[0].name
# Load TFLite model and allocate tensors.
interpreter = tf.lite.Interpreter(model_path=opt.weights)
interpreter.allocate_tensors()
# Get input and output tensors.
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
# Load weights
# attempt_download(weights)
# if weights.endswith('.pt'): # pytorch format
# model.load_state_dict(torch.load(weights, map_location=device)['model'])
# else: # darknet format
# _ = load_darknet_weights(model, weights)
# Second-stage classifier
classify = False
if classify:
modelc = torch_utils.load_classifier(name='resnet101', n=2) # initialize
modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']) # load weights
modelc.to(device).eval()
# Fuse Conv2d + BatchNorm2d layers
# model.fuse()
# Eval mode
# model.to(device).eval()
# Export mode
# if ONNX_EXPORT:
# img = torch.zeros((1, 3) + img_size) # (1, 3, 320, 192)
# torch.onnx.export(model, img, 'weights/export.onnx', verbose=False, opset_version=10)
# # torch.onnx.export(model, img, 'weights/export.onnx', verbose=False, opset_version=11)
# # Validate exported model
# import onnx
# model = onnx.load('weights/export.onnx') # Load the ONNX model
# onnx.checker.check_model(model) # Check that the IR is well formed
# print(onnx.helper.printable_graph(model.graph)) # Print a human readable representation of the graph
# return
# Half precision
half = half and device.type != 'cpu' # half precision only supported on CUDA
if half:
model.half()
# Set Dataloader
vid_path, vid_writer = None, None
if webcam:
view_img = True
torch.backends.cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=img_size, half=half)
else:
save_img = True
dataset = LoadImages(source, img_size=img_size, half=half)
# Get classes and colors
classes = load_classes(parse_data_cfg(opt.data)['names'])
colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(classes))]
# Run inference
t0 = time.time()
for path, img, im0s, vid_cap in dataset:
t = time.time()
img0 = img
start = time.time()
for i in range(10):
# Get detections
# img = torch.from_numpy(img).to(device)
# if img.ndimension() == 3:
# img = img.unsqueeze(0)
# pred = model(img)[0]
input_shape = input_details[0]['shape']
print("input_shape", input_shape)
img = img0
img = img[None, :, :, :]
input_data = img.astype(np.float32)
interpreter.set_tensor(input_details[0]['index'], input_data)
interpreter.invoke()
output_data = interpreter.get_tensor(output_details[0]['index'])
print("output_data.shape", output_data.shape)
pred = torch.Tensor(output_data)
# pred = torch.Tensor(pred)
if opt.half:
pred = pred.float()
# Apply NMS
pred = non_max_suppression(pred, opt.conf_thres, opt.nms_thres)
# Apply
if classify:
pred = apply_classifier(pred, modelc, img, im0s)
end = time.time()
print("avg time:", (end - start) / 10)
# Process detections
for i, det in enumerate(pred): # detections per image
if webcam: # batch_size >= 1
p, s, im0 = path[i], '%g: ' % i, im0s[i]
else:
p, s, im0 = path, '', im0s
save_path = str(Path(out) / Path(p).name)
s += '%gx%g ' % img.shape[2:] # print string
# print("len(det)", len(det))
if det is not None and len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
s += '%g %ss, ' % (n, classes[int(c)]) # add to string
# Write results
for *xyxy, conf, _, cls in det:
if save_txt: # Write to file
with open(save_path + '.txt', 'a') as file:
file.write(('%g ' * 6 + '\n') % (*xyxy, cls, conf))
if save_img or view_img: # Add bbox to image
label = '%s %.2f' % (classes[int(cls)], conf)
plot_one_box(xyxy, im0, label=label, color=colors[int(cls)])
print('%sDone. (%.3fs)' % (s, time.time() - t))
# Stream results
if view_img:
cv2.imshow(p, im0)
if cv2.waitKey(1) == ord('q'): # q to quit
raise StopIteration
# Save results (image with detections)
if save_img:
if dataset.mode == 'images':
cv2.imwrite(save_path, im0)
else:
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.release() # release previous video writer
fps = vid_cap.get(cv2.CAP_PROP_FPS)
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*opt.fourcc), fps, (w, h))
vid_writer.write(im0)
if save_txt or save_img:
print('Results saved to %s' % os.getcwd() + os.sep + out)
if platform == 'darwin': # MacOS
os.system('open ' + out + ' ' + save_path)
print('Done. (%.3fs)' % (time.time() - t0))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path')
parser.add_argument('--data', type=str, default='data/coco.data', help='coco.data file path')
parser.add_argument('--weights', type=str, default='weights/yolov3_quant.tflite', help='path to weights file')
parser.add_argument('--source', type=str, default='data/samples', help='source') # input file/folder, 0 for webcam
parser.add_argument('--output', type=str, default='output', help='output folder') # output folder
parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)')
parser.add_argument('--conf-thres', type=float, default=0.3, help='object confidence threshold')
parser.add_argument('--nms-thres', type=float, default=0.5, help='iou threshold for non-maximum suppression')
parser.add_argument('--fourcc', type=str, default='mp4v', help='output video codec (verify ffmpeg support)')
parser.add_argument('--half', action='store_true', help='half precision FP16 inference')
parser.add_argument('--device', default='', help='device id (i.e. 0 or 0,1) or cpu')
parser.add_argument('--view-img', action='store_true', help='display results')
opt = parser.parse_args()
print(opt)
with torch.no_grad():
detect()