-
Notifications
You must be signed in to change notification settings - Fork 13
/
yolo_openvino_demo.py
446 lines (371 loc) · 21.5 KB
/
yolo_openvino_demo.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
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
#!/usr/bin/env python
"""
Copyright (C) 2018-2019 Intel Corporation
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
"""
from __future__ import print_function, division
import logging
import os
import sys
from argparse import ArgumentParser, SUPPRESS
from math import exp as exp
from time import time
import numpy as np
import ngraph
import cv2
from openvino.inference_engine import IENetwork, IECore
logging.basicConfig(format="[ %(levelname)s ] %(message)s", level=logging.INFO, stream=sys.stdout)
log = logging.getLogger()
def build_argparser():
parser = ArgumentParser(add_help=False)
args = parser.add_argument_group('Options')
args.add_argument('-h', '--help', action='help', default=SUPPRESS, help='Show this help message and exit.')
args.add_argument("-m", "--model", help="Required. Path to an .xml file with a trained model.",
required=True, type=str)
args.add_argument("-at", "--architecture_type", help='Required. Specify model\' architecture type.',
type=str, required=True, choices=('yolov3', 'yolov4', 'yolov5', 'yolov4-p5', 'yolov4-p6', 'yolov4-p7'))
args.add_argument("-i", "--input", help="Required. Path to an image/video file. (Specify 'cam' to work with "
"camera)", required=True, type=str)
args.add_argument("-l", "--cpu_extension",
help="Optional. Required for CPU custom layers. Absolute path to a shared library with "
"the kernels implementations.", type=str, default=None)
args.add_argument("-d", "--device",
help="Optional. Specify the target device to infer on; CPU, GPU, FPGA, HDDL or MYRIAD is"
" acceptable. The sample will look for a suitable plugin for device specified. "
"Default value is CPU", default="CPU", type=str)
args.add_argument("--labels", help="Optional. Labels mapping file", default=None, type=str)
args.add_argument("-t", "--prob_threshold", help="Optional. Probability threshold for detections filtering",
default=0.5, type=float)
args.add_argument("-iout", "--iou_threshold", help="Optional. Intersection over union threshold for overlapping "
"detections filtering", default=0.4, type=float)
args.add_argument("-ni", "--number_iter", help="Optional. Number of inference iterations", default=1, type=int)
args.add_argument("-pc", "--perf_counts", help="Optional. Report performance counters", default=False,
action="store_true")
args.add_argument("-r", "--raw_output_message", help="Optional. Output inference results raw values showing",
default=False, action="store_true")
args.add_argument("--no_show", help="Optional. Don't show output", action='store_true')
return parser
class YoloParams:
# ------------------------------------------- Extracting layer parameters ------------------------------------------
# Magic numbers are copied from yolo samples
def __init__(self, param, side, yolo_type):
self.coords = 4 if 'coords' not in param else int(param['coords'])
self.classes = 80 if 'classes' not in param else int(param['classes'])
self.side = side
if yolo_type == 'yolov4':
self.num = 3
self.anchors = [12.0,16.0, 19.0,36.0, 40.0,28.0, 36.0,75.0, 76.0,55.0, 72.0,146.0, 142.0,110.0, 192.0,243.0,
459.0,401.0]
elif yolo_type == 'yolov4-p5':
self.num = 4
self.anchors = [13.0,17.0, 31.0,25.0, 24.0,51.0, 61.0,45.0, 48.0,102.0, 119.0,96.0, 97.0,189.0, 217.0,184.0,
171.0,384.0, 324.0,451.0, 616.0,618.0, 800.0,800.0]
elif yolo_type == 'yolov4-p6':
self.num = 4
self.anchors = [13.0,17.0, 31.0,25.0, 24.0,51.0, 61.0,45.0, 61.0,45.0, 48.0,102.0, 119.0,96.0, 97.0,189.0,
97.0,189.0, 217.0,184.0, 171.0,384.0, 324.0,451.0, 324.0,451.0, 545.0,357.0, 616.0,618.0, 1024.0,1024.0]
elif yolo_type == 'yolov4-p7':
self.num = 5
self.anchors = [13.0,17.0, 22.0,25.0, 27.0,66.0, 55.0,41.0, 57.0,88.0, 112.0,69.0, 69.0,177.0, 136.0,138.0,
136.0,138.0, 287.0,114.0, 134.0,275.0, 268.0,248.0, 268.0,248.0, 232.0,504.0, 445.0,416.0, 640.0,640.0,
812.0,393.0, 477.0,808.0, 1070.0,908.0, 1408.0,1408.0]
else:
self.num = 3
self.anchors = [10.0, 13.0, 16.0, 30.0, 33.0, 23.0, 30.0, 61.0, 62.0, 45.0, 59.0, 119.0, 116.0, 90.0, 156.0,
198.0, 373.0, 326.0]
def log_params(self):
params_to_print = {'classes': self.classes, 'num': self.num, 'coords': self.coords, 'anchors': self.anchors}
[log.info(" {:8}: {}".format(param_name, param)) for param_name, param in params_to_print.items()]
def letterbox(img, size=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True):
# Resize image to a 32-pixel-multiple rectangle https://github.com/ultralytics/yolov3/issues/232
shape = img.shape[:2] # current shape [height, width]
w, h = size
# Scale ratio (new / old)
r = min(h / shape[0], w / shape[1])
if not scaleup: # only scale down, do not scale up (for better test mAP)
r = min(r, 1.0)
# Compute padding
ratio = r, r # width, height ratios
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
dw, dh = w - new_unpad[0], h - new_unpad[1] # wh padding
if auto: # minimum rectangle
dw, dh = np.mod(dw, 64), np.mod(dh, 64) # wh padding
elif scaleFill: # stretch
dw, dh = 0.0, 0.0
new_unpad = (w, h)
ratio = w / shape[1], h / shape[0] # width, height ratios
dw /= 2 # divide padding into 2 sides
dh /= 2
if shape[::-1] != new_unpad: # resize
img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
top2, bottom2, left2, right2 = 0, 0, 0, 0
if img.shape[0] != h:
top2 = (h - img.shape[0])//2
bottom2 = top2
img = cv2.copyMakeBorder(img, top2, bottom2, left2, right2, cv2.BORDER_CONSTANT, value=color) # add border
elif img.shape[1] != w:
left2 = (w - img.shape[1])//2
right2 = left2
img = cv2.copyMakeBorder(img, top2, bottom2, left2, right2, cv2.BORDER_CONSTANT, value=color) # add border
return img
def scale_bbox(x, y, height, width, class_id, confidence, im_h, im_w, resized_im_h=640, resized_im_w=640):
gain = min(resized_im_w / im_w, resized_im_h / im_h) # gain = old / new
pad = (resized_im_w - im_w * gain) / 2, (resized_im_h - im_h * gain) / 2 # wh padding
x = int((x - pad[0])/gain)
y = int((y - pad[1])/gain)
w = int(width/gain)
h = int(height/gain)
xmin = max(0, int(x - w / 2))
ymin = max(0, int(y - h / 2))
xmax = min(im_w, int(xmin + w))
ymax = min(im_h, int(ymin + h))
# Method item() used here to convert NumPy types to native types for compatibility with functions, which don't
# support Numpy types (e.g., cv2.rectangle doesn't support int64 in color parameter)
return dict(xmin=xmin, xmax=xmax, ymin=ymin, ymax=ymax, class_id=class_id.item(), confidence=confidence.item())
def entry_index(side, coord, classes, location, entry):
side_power_2 = side ** 2
n = location // side_power_2
loc = location % side_power_2
return int(side_power_2 * (n * (coord + classes + 1) + entry) + loc)
def parse_yolo_region(blob, resized_image_shape, original_im_shape, params, threshold, yolo_type):
# ------------------------------------------ Validating output parameters ------------------------------------------
out_blob_n, out_blob_c, out_blob_h, out_blob_w = blob.shape
predictions = 1.0/(1.0+np.exp(-blob))
assert out_blob_w == out_blob_h, "Invalid size of output blob. It sould be in NCHW layout and height should " \
"be equal to width. Current height = {}, current width = {}" \
"".format(out_blob_h, out_blob_w)
# ------------------------------------------ Extracting layer parameters -------------------------------------------
orig_im_h, orig_im_w = original_im_shape
resized_image_h, resized_image_w = resized_image_shape
objects = list()
side_square = params.side[1] * params.side[0]
# ------------------------------------------- Parsing YOLO Region output -------------------------------------------
bbox_size = int(out_blob_c/params.num) #4+1+num_classes
#print('bbox_size = ' + str(bbox_size))
#print('bbox_size = ' + str(bbox_size))
for row, col, n in np.ndindex(params.side[0], params.side[1], params.num):
bbox = predictions[0, n*bbox_size:(n+1)*bbox_size, row, col]
x, y, width, height, object_probability = bbox[:5]
class_probabilities = bbox[5:]
if object_probability < threshold:
continue
#print('resized_image_w = ' + str(resized_image_w))
#print('out_blob_w = ' + str(out_blob_w))
x = (2*x - 0.5 + col)*(resized_image_w/out_blob_w)
y = (2*y - 0.5 + row)*(resized_image_h/out_blob_h)
if int(resized_image_w/out_blob_w) == 8 & int(resized_image_h/out_blob_h) == 8: #80x80,
idx = 0
elif int(resized_image_w/out_blob_w) == 16 & int(resized_image_h/out_blob_h) == 16: #40x40
idx = 1
elif int(resized_image_w/out_blob_w) == 32 & int(resized_image_h/out_blob_h) == 32: # 20x20
idx = 2
elif int(resized_image_w/out_blob_w) == 64 & int(resized_image_h/out_blob_h) == 64: # 20x20
idx = 3
elif int(resized_image_w/out_blob_w) == 128 & int(resized_image_h/out_blob_h) == 128: # 20x20
idx = 4
if yolo_type == 'yolov4-p5' or yolo_type == 'yolov4-p6' or yolo_type == 'yolov4-p7':
width = (2*width)**2* params.anchors[idx * 8 + 2 * n]
height = (2*height)**2 * params.anchors[idx * 8 + 2 * n + 1]
else:
width = (2*width)**2* params.anchors[idx * 6 + 2 * n]
height = (2*height)**2 * params.anchors[idx * 6 + 2 * n + 1]
class_id = np.argmax(class_probabilities * object_probability)
confidence = class_probabilities[class_id] * object_probability
objects.append(scale_bbox(x=x, y=y, height=height, width=width, class_id=class_id, confidence=confidence,
im_h=orig_im_h, im_w=orig_im_w, resized_im_h=resized_image_h, resized_im_w=resized_image_w))
return objects
def intersection_over_union(box_1, box_2):
width_of_overlap_area = min(box_1['xmax'], box_2['xmax']) - max(box_1['xmin'], box_2['xmin'])
height_of_overlap_area = min(box_1['ymax'], box_2['ymax']) - max(box_1['ymin'], box_2['ymin'])
if width_of_overlap_area < 0 or height_of_overlap_area < 0:
area_of_overlap = 0
else:
area_of_overlap = width_of_overlap_area * height_of_overlap_area
box_1_area = (box_1['ymax'] - box_1['ymin']) * (box_1['xmax'] - box_1['xmin'])
box_2_area = (box_2['ymax'] - box_2['ymin']) * (box_2['xmax'] - box_2['xmin'])
area_of_union = box_1_area + box_2_area - area_of_overlap
if area_of_union == 0:
return 0
return area_of_overlap / area_of_union
def main():
args = build_argparser().parse_args()
model_xml = args.model
model_bin = os.path.splitext(model_xml)[0] + ".bin"
# ------------- 1. Plugin initialization for specified device and load extensions library if specified -------------
log.info("Creating Inference Engine...")
ie = IECore()
if args.cpu_extension and 'CPU' in args.device:
ie.add_extension(args.cpu_extension, "CPU")
# -------------------- 2. Reading the IR generated by the Model Optimizer (.xml and .bin files) --------------------
log.info("Loading network files:\n\t{}\n\t{}".format(model_xml, model_bin))
net = IENetwork(model=model_xml, weights=model_bin)
# ---------------------------------- 3. Load CPU extension for support specific layer ------------------------------
#if "CPU" in args.device:
# supported_layers = ie.query_network(net, "CPU")
# not_supported_layers = [l for l in net.layers.keys() if l not in supported_layers]
# if len(not_supported_layers) != 0:
# log.error("Following layers are not supported by the plugin for specified device {}:\n {}".
# format(args.device, ', '.join(not_supported_layers)))
# log.error("Please try to specify cpu extensions library path in sample's command line parameters using -l "
# "or --cpu_extension command line argument")
# sys.exit(1)
#
#assert len(net.inputs.keys()) == 1, "Sample supports only YOLO V3 based single input topologies"
# ---------------------------------------------- 4. Preparing inputs -----------------------------------------------
log.info("Preparing inputs")
input_blob = next(iter(net.inputs))
# Defaulf batch_size is 1
net.batch_size = 1
# Read and pre-process input images
n, c, h, w = net.inputs[input_blob].shape
ng_func = ngraph.function_from_cnn(net)
yolo_layer_params = {}
for node in ng_func.get_ordered_ops():
layer_name = node.get_friendly_name()
if layer_name not in net.outputs:
continue
shape = list(node.inputs()[0].get_source_output().get_node().shape)
yolo_params = YoloParams(node._get_attributes(), shape[2:4], args.architecture_type)
yolo_layer_params[layer_name] = (shape, yolo_params)
if args.labels:
with open(args.labels, 'r') as f:
labels_map = [x.strip() for x in f]
else:
labels_map = None
input_stream = 0 if args.input == "cam" else args.input
is_async_mode = True
cap = cv2.VideoCapture(input_stream)
number_input_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
number_input_frames = 1 if number_input_frames != -1 and number_input_frames < 0 else number_input_frames
wait_key_code = 1
# Number of frames in picture is 1 and this will be read in cycle. Sync mode is default value for this case
if number_input_frames != 1:
ret, frame = cap.read()
else:
is_async_mode = False
wait_key_code = 0
# ----------------------------------------- 5. Loading model to the plugin -----------------------------------------
log.info("Loading model to the plugin")
exec_net = ie.load_network(network=net, num_requests=2, device_name=args.device)
cur_request_id = 0
next_request_id = 1
render_time = 0
parsing_time = 0
# ----------------------------------------------- 6. Doing inference -----------------------------------------------
log.info("Starting inference...")
print("To close the application, press 'CTRL+C' here or switch to the output window and press ESC key")
print("To switch between sync/async modes, press TAB key in the output window")
while cap.isOpened():
# Here is the first asynchronous point: in the Async mode, we capture frame to populate the NEXT infer request
# in the regular mode, we capture frame to the CURRENT infer request
if is_async_mode:
ret, next_frame = cap.read()
else:
ret, frame = cap.read()
if not ret:
break
if is_async_mode:
request_id = next_request_id
in_frame = letterbox(frame, (w, h))
else:
request_id = cur_request_id
in_frame = letterbox(frame, (w, h))
# resize input_frame to network size
in_frame = in_frame.transpose((2, 0, 1)) # Change data layout from HWC to CHW
in_frame = in_frame.reshape((n, c, h, w))
# Start inference
start_time = time()
exec_net.start_async(request_id=request_id, inputs={input_blob: in_frame})
# Collecting object detection results
objects = list()
if exec_net.requests[cur_request_id].wait(-1) == 0:
det_time = time() - start_time
output = exec_net.requests[cur_request_id].outputs
start_time = time()
for layer_name, out_blob in output.items():
#out_blob = out_blob.reshape(net.layers[layer_name].out_data[0].shape)
layer_params = yolo_layer_params[layer_name]#YoloParams(net.layers[layer_name].params, out_blob.shape[2])
out_blob.shape = layer_params[0]
#log.info("Layer {} parameters: ".format(layer_name))
#layer_params.log_params()
objects += parse_yolo_region(out_blob, in_frame.shape[2:],
#in_frame.shape[2:], layer_params,
frame.shape[:-1], layer_params[1],
args.prob_threshold, args.architecture_type)
parsing_time = time() - start_time
# Filtering overlapping boxes with respect to the --iou_threshold CLI parameter
objects = sorted(objects, key=lambda obj : obj['confidence'], reverse=True)
for i in range(len(objects)):
if objects[i]['confidence'] == 0:
continue
for j in range(i + 1, len(objects)):
if objects[i]['class_id'] != objects[j]['class_id']: # Only compare bounding box with same class id
continue
if intersection_over_union(objects[i], objects[j]) > args.iou_threshold:
objects[j]['confidence'] = 0
# Drawing objects with respect to the --prob_threshold CLI parameter
objects = [obj for obj in objects if obj['confidence'] >= args.prob_threshold]
if len(objects) and args.raw_output_message:
log.info("\nDetected boxes for batch {}:".format(1))
log.info(" Class ID | Confidence | XMIN | YMIN | XMAX | YMAX | COLOR ")
origin_im_size = frame.shape[:-1]
for obj in objects:
# Validation bbox of detected object
if obj['xmax'] > origin_im_size[1] or obj['ymax'] > origin_im_size[0] or obj['xmin'] < 0 or obj['ymin'] < 0:
continue
color = (int(min(obj['class_id'] * 12.5, 255)),
min(obj['class_id'] * 7, 255), min(obj['class_id'] * 5, 255))
det_label = labels_map[obj['class_id']] if labels_map and len(labels_map) >= obj['class_id'] else \
str(obj['class_id'])
if args.raw_output_message:
log.info(
"{:^9} | {:10f} | {:4} | {:4} | {:4} | {:4} | {} ".format(det_label, obj['confidence'], obj['xmin'],
obj['ymin'], obj['xmax'], obj['ymax'],
color))
cv2.rectangle(frame, (obj['xmin'], obj['ymin']), (obj['xmax'], obj['ymax']), color, 2)
cv2.putText(frame,
"#" + det_label + ' ' + str(round(obj['confidence'] * 100, 1)) + ' %',
(obj['xmin'], obj['ymin'] - 7), cv2.FONT_HERSHEY_COMPLEX, 0.6, color, 1)
# Draw performance stats over frame
inf_time_message = "Inference time: N\A for async mode" if is_async_mode else \
"Inference time: {:.3f} ms".format(det_time * 1e3)
render_time_message = "OpenCV rendering time: {:.3f} ms".format(render_time * 1e3)
async_mode_message = "Async mode is on. Processing request {}".format(cur_request_id) if is_async_mode else \
"Async mode is off. Processing request {}".format(cur_request_id)
parsing_message = "YOLO parsing time is {:.3f} ms".format(parsing_time * 1e3)
cv2.putText(frame, inf_time_message, (15, 15), cv2.FONT_HERSHEY_COMPLEX, 0.5, (200, 10, 10), 1)
cv2.putText(frame, render_time_message, (15, 45), cv2.FONT_HERSHEY_COMPLEX, 0.5, (10, 10, 200), 1)
cv2.putText(frame, async_mode_message, (10, int(origin_im_size[0] - 20)), cv2.FONT_HERSHEY_COMPLEX, 0.5,
(10, 10, 200), 1)
cv2.putText(frame, parsing_message, (15, 30), cv2.FONT_HERSHEY_COMPLEX, 0.5, (10, 10, 200), 1)
start_time = time()
if not args.no_show:
cv2.imshow("DetectionResults", frame)
render_time = time() - start_time
if is_async_mode:
cur_request_id, next_request_id = next_request_id, cur_request_id
frame = next_frame
if not args.no_show:
key = cv2.waitKey(wait_key_code)
# ESC key
if key == 27:
break
# Tab key
if key == 9:
exec_net.requests[cur_request_id].wait()
is_async_mode = not is_async_mode
log.info("Switched to {} mode".format("async" if is_async_mode else "sync"))
cv2.destroyAllWindows()
if __name__ == '__main__':
sys.exit(main() or 0)