forked from tatz1101/Edge-AI-Platform-Tutorials
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathyolo_convert.py.relative
610 lines (574 loc) · 23.2 KB
/
yolo_convert.py.relative
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
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
import sys
sys.path.append('PATH_TO/caffe-master/python')
import caffe
import numpy as np
from collections import OrderedDict
DEBUG = True
def parse_cfg(cfgfile):
def erase_comment(line):
line = line.split('#')[0]
return line
blocks = []
fp = open(cfgfile, 'r')
block = None
line = fp.readline()
while line != '':
line = line.rstrip()
if line == '' or line[0] == '#':
line = fp.readline()
continue
elif line[0] == '[':
if block:
blocks.append(block)
block = OrderedDict()
block['type'] = line.lstrip('[').rstrip(']')
if block['type'] == 'convolutional':
block['batch_normalize'] = 0
else:
line = erase_comment(line)
key,value = line.split('=')
key = key.strip()
if key == 'type':
key = '_type'
value = value.strip()
block[key] = value
line = fp.readline()
if block:
blocks.append(block)
fp.close()
return blocks
try:
import caffe.proto.caffe_pb2 as caffe_pb2
except:
try:
import caffe_pb2
except:
print 'caffe_pb2.py not found. Try:'
print ' protoc caffe.proto --python_out=.'
exit()
def parse_caffemodel(caffemodel):
model = caffe_pb2.NetParameter()
print 'Loading caffemodel: ', caffemodel
with open(caffemodel, 'rb') as fp:
model.ParseFromString(fp.read())
return model
def parse_prototxt(protofile):
def line_type(line):
if line.find(':') >= 0:
return 0
elif line.find('{') >= 0:
return 1
return -1
def parse_block(fp):
block = OrderedDict()
line = fp.readline().strip()
while line != '}':
ltype = line_type(line)
if ltype == 0: # key: value
line = line.split('#')[0]
key, value = line.split(':')
key = key.strip()
value = value.strip().strip('"')
if block.has_key(key):
if type(block[key]) == list:
block[key].append(value)
else:
block[key] = [block[key], value]
else:
block[key] = value
elif ltype == 1: # blockname {
key = line.split('{')[0].strip()
sub_block = parse_block(fp)
block[key] = sub_block
line = fp.readline().strip()
line = line.split('#')[0]
return block
fp = open(protofile, 'r')
props = OrderedDict()
layers = []
line = fp.readline()
while line != '':
line = line.strip().split('#')[0]
if line == '':
line = fp.readline()
continue
ltype = line_type(line)
if ltype == 0: # key: value
key, value = line.split(':')
key = key.strip()
value = value.strip().strip('"')
if props.has_key(key):
if type(props[key]) == list:
props[key].append(value)
else:
props[key] = [props[key], value]
else:
props[key] = value
elif ltype == 1: # blockname {
key = line.split('{')[0].strip()
if key == 'layer':
layer = parse_block(fp)
layers.append(layer)
else:
props[key] = parse_block(fp)
line = fp.readline()
if len(layers) > 0:
net_info = OrderedDict()
net_info['props'] = props
net_info['layers'] = layers
return net_info
else:
return props
def is_number(s):
try:
float(s)
return True
except ValueError:
return False
def print_prototxt(net_info):
# whether add double quote
def format_value(value):
if is_number(value):
return value
elif value == 'true' or value == 'false' or value == 'MAX' or value == 'SUM' or value == 'AVE':
return value
else:
return '\"%s\"' % value
def print_block(block_info, prefix, indent):
blanks = ''.join([' ']*indent)
print('%s%s {' % (blanks, prefix))
for key,value in block_info.items():
if type(value) == OrderedDict:
print_block(value, key, indent+4)
elif type(value) == list:
for v in value:
print('%s %s: %s' % (blanks, key, format_value(v)))
else:
print('%s %s: %s' % (blanks, key, format_value(value)))
print('%s}' % blanks)
props = net_info['props']
layers = net_info['layers']
print('name: \"%s\"' % props['name'])
print('input: \"%s\"' % props['input'])
print('input_dim: %s' % props['input_dim'][0])
print('input_dim: %s' % props['input_dim'][1])
print('input_dim: %s' % props['input_dim'][2])
print('input_dim: %s' % props['input_dim'][3])
print('')
for layer in layers:
print_block(layer, 'layer', 0)
def save_prototxt(net_info, protofile, region=True):
fp = open(protofile, 'w')
def format_value(value):
if is_number(value):
return value
elif value == 'true' or value == 'false' or value == 'MAX' or value == 'SUM' or value == 'AVE':
return value
else:
return '\"%s\"' % value
def print_block(block_info, prefix, indent):
blanks = ''.join([' ']*indent)
print >>fp, '%s%s {' % (blanks, prefix)
for key,value in block_info.items():
if type(value) == OrderedDict:
print_block(value, key, indent+4)
elif type(value) == list:
for v in value:
print >> fp, '%s %s: %s' % (blanks, key, format_value(v))
else:
print >> fp, '%s %s: %s' % (blanks, key, format_value(value))
print >> fp, '%s}' % blanks
props = net_info['props']
layers = net_info['layers']
print >> fp, 'name: \"%s\"' % props['name']
print >> fp, 'input: \"%s\"' % props['input']
print >> fp, 'input_dim: %s' % props['input_dim'][0]
print >> fp, 'input_dim: %s' % props['input_dim'][1]
print >> fp, 'input_dim: %s' % props['input_dim'][2]
print >> fp, 'input_dim: %s' % props['input_dim'][3]
print >> fp, ''
for layer in layers:
if layer['type'] != 'Region' or region == True:
print_block(layer, 'layer', 0)
fp.close()
def darknet2caffe(cfgfile, weightfile, protofile, caffemodel):
net_info = cfg2prototxt(cfgfile)
save_prototxt(net_info , protofile, region=False)
net = caffe.Net(protofile, caffe.TEST)
params = net.params
blocks = parse_cfg(cfgfile)
fp = open(weightfile, 'rb')
header = np.fromfile(fp, count=5, dtype=np.int32)
buf = np.fromfile(fp, dtype = np.float32)
print (buf[:5])
fp.close()
layers = []
layer_id =0
start = 0
for block in blocks:
if start >= buf.size:
break
if block['type'] == 'net':
continue
elif block['type'] == 'convolutional':
batch_normalize = int(block['batch_normalize'])
if block.has_key('name'):
conv_layer_name = block['name']
bn_layer_name = '%s-bn' % block['name']
scale_layer_name = '%s-scale' % block['name']
else:
conv_layer_name = 'layer%d-conv' % layer_id
bn_layer_name = 'layer%d-bn' % layer_id
scale_layer_name = 'layer%d-scale' % layer_id
if batch_normalize:
start = load_conv_bn2caffe(buf, start, params[conv_layer_name], params[bn_layer_name], params[scale_layer_name])
else:
start = load_conv2caffe(buf,start, params[conv_layer_name])
layer_id = layer_id+1
elif block['type'] == 'connected':
if block.has_key('name'):
fc_layer_name = block['name']
else:
fc_layer_name = 'layer%d-fc' % layer_id
start = load_fc2caffe(buf, start, params[fc_layer_name])
layer_id = layer_id+1
elif block['type'] == 'maxpool':
layer_id = layer_id+1
elif block['type'] == 'avgpool':
layer_id = layer_id+1
elif block['type'] == 'region':
layer_id = layer_id + 1
elif block['type'] == 'reorg':
layer_id = layer_id + 1
elif block['type'] == 'route':
layer_id = layer_id + 1
elif block['type'] == 'shortcut':
layer_id = layer_id + 1
elif block['type'] == 'yolo':
layer_id = layer_id + 1
elif block['type'] == 'softmax':
layer_id = layer_id + 1
elif block['type'] == 'upsample':
layer_id = layer_id + 1
elif block['type'] == 'cost':
layer_id = layer_id + 1
else:
print('unknow layer type %s ' % block['type'])
layer_id = layer_id + 1
print('save prototxt to %s' % protofile)
save_prototxt(net_info , protofile, region=True)
print('save caffemodel to %s' % caffemodel)
net.save(caffemodel)
def load_conv2caffe(buf, start, conv_param):
weight = conv_param[0].data
bias = conv_param[1].data
conv_param[1].data[...] = np.reshape(buf[start:start+bias.size], bias.shape); start = start + bias.size
conv_param[0].data[...] = np.reshape(buf[start:start+weight.size], weight.shape); start = start + weight.size
return start
def load_fc2caffe(buf, start, fc_param):
weight = fc_param[0].data
bias = fc_param[1].data
fc_param[1].data[...] = np.reshape(buf[start:start+bias.size], bias.shape); start = start + bias.size
fc_param[0].data[...] = np.reshape(buf[start:start+weight.size], weight.shape); start = start + weight.size
return start
def load_conv_bn2caffe(buf, start, conv_param, bn_param, scale_param):
conv_weight = conv_param[0].data
running_mean = bn_param[0].data
running_var = bn_param[1].data
scale_weight = scale_param[0].data
scale_bias = scale_param[1].data
scale_param[1].data[...] = np.reshape(buf[start:start+scale_bias.size], scale_bias.shape); start = start + scale_bias.size
scale_param[0].data[...] = np.reshape(buf[start:start+scale_weight.size], scale_weight.shape); start = start + scale_weight.size
bn_param[0].data[...] = np.reshape(buf[start:start+running_mean.size], running_mean.shape); start = start + running_mean.size
bn_param[1].data[...] = np.reshape(buf[start:start+running_var.size], running_var.shape); start = start + running_var.size
bn_param[2].data[...] = np.array([1.0])
#bn_param[2].data[...] = np.array(buf[start:start + 1]); start = start + 1
conv_param[0].data[...] = np.reshape(buf[start:start+conv_weight.size], conv_weight.shape); start = start + conv_weight.size
return start
def cfg2prototxt(cfgfile):
blocks = parse_cfg(cfgfile)
layers = []
props = OrderedDict()
bottom = 'data'
layer_id = 0
topnames = dict()
for bidx in xrange(len(blocks)):
block = blocks[bidx]
if block['type'] == 'net':
props['name'] = 'Darkent2Caffe'
props['input'] = 'data'
props['input_dim'] = ['1']
props['input_dim'].append(block['channels'])
props['input_dim'].append(block['height'])
props['input_dim'].append(block['width'])
continue
elif block['type'] == 'convolutional':
conv_layer = OrderedDict()
conv_layer['bottom'] = bottom
if block.has_key('name'):
conv_layer['top'] = block['name']
conv_layer['name'] = block['name']
else:
conv_layer['top'] = 'layer%d-conv' % layer_id
conv_layer['name'] = 'layer%d-conv' % layer_id
conv_layer['type'] = 'Convolution'
convolution_param = OrderedDict()
convolution_param['num_output'] = block['filters']
convolution_param['kernel_size'] = block['size']
if block['pad'] == '1':
convolution_param['pad'] = str(int(convolution_param['kernel_size'])/2)
convolution_param['stride'] = block['stride']
if block['batch_normalize'] == '1':
convolution_param['bias_term'] = 'false'
else:
convolution_param['bias_term'] = 'true'
conv_layer['convolution_param'] = convolution_param
layers.append(conv_layer)
bottom = conv_layer['top']
if block['batch_normalize'] == '1':
bn_layer = OrderedDict()
bn_layer['bottom'] = bottom
bn_layer['top'] = bottom
if block.has_key('name'):
bn_layer['name'] = '%s-bn' % block['name']
else:
bn_layer['name'] = 'layer%d-bn' % layer_id
bn_layer['type'] = 'BatchNorm'
batch_norm_param = OrderedDict()
batch_norm_param['use_global_stats'] = 'true'
bn_layer['batch_norm_param'] = batch_norm_param
layers.append(bn_layer)
scale_layer = OrderedDict()
scale_layer['bottom'] = bottom
scale_layer['top'] = bottom
if block.has_key('name'):
scale_layer['name'] = '%s-scale' % block['name']
else:
scale_layer['name'] = 'layer%d-scale' % layer_id
scale_layer['type'] = 'Scale'
scale_param = OrderedDict()
scale_param['bias_term'] = 'true'
scale_layer['scale_param'] = scale_param
layers.append(scale_layer)
if block['activation'] != 'linear':
relu_layer = OrderedDict()
relu_layer['bottom'] = bottom
relu_layer['top'] = bottom
if block.has_key('name'):
relu_layer['name'] = '%s-act' % block['name']
else:
relu_layer['name'] = 'layer%d-act' % layer_id
relu_layer['type'] = 'ReLU'
if block['activation'] == 'leaky':
relu_param = OrderedDict()
relu_param['negative_slope'] = '0.1'
relu_layer['relu_param'] = relu_param
layers.append(relu_layer)
topnames[layer_id] = bottom
layer_id = layer_id+1
elif block['type'] == 'maxpool':
max_layer = OrderedDict()
max_layer['bottom'] = bottom
if block.has_key('name'):
max_layer['top'] = block['name']
max_layer['name'] = block['name']
else:
max_layer['top'] = 'layer%d-maxpool' % layer_id
max_layer['name'] = 'layer%d-maxpool' % layer_id
max_layer['type'] = 'Pooling'
pooling_param = OrderedDict()
pooling_param['kernel_size'] = block['size']
pooling_param['stride'] = block['stride']
pooling_param['pool'] = 'MAX'
if block.has_key('pad') and int(block['pad']) == 1:
pooling_param['pad'] = str((int(block['size'])-1)/2)
elif int(block['stride']) == 1:
pooling_param['pad'] = str((int(block['size'])-1)/2)
max_layer['pooling_param'] = pooling_param
print max_layer
layers.append(max_layer)
bottom = max_layer['top']
topnames[layer_id] = bottom
layer_id = layer_id+1
elif block['type'] == 'avgpool':
avg_layer = OrderedDict()
avg_layer['bottom'] = bottom
if block.has_key('name'):
avg_layer['top'] = block['name']
avg_layer['name'] = block['name']
else:
avg_layer['top'] = 'layer%d-avgpool' % layer_id
avg_layer['name'] = 'layer%d-avgpool' % layer_id
avg_layer['type'] = 'Pooling'
pooling_param = OrderedDict()
pooling_param['kernel_size'] = 7
pooling_param['stride'] = 1
pooling_param['pool'] = 'AVE'
avg_layer['pooling_param'] = pooling_param
layers.append(avg_layer)
bottom = avg_layer['top']
topnames[layer_id] = bottom
layer_id = layer_id + 1
elif block['type'] == 'route':
if DEBUG:
print("block:%s" % block)
from_layers = block['layers'].split(',')
bottom_tmp = []
if len(from_layers) == 1:
if int(from_layers[0]) < 0:
prev_layer_id = layer_id + int(from_layers[0])
else:
prev_layer_id = int(from_layers[0])
bottom = topnames[prev_layer_id]
topnames[layer_id] = bottom
layer_id = layer_id + 1
else:
for index in range(len(from_layers)):
if int(from_layers[index]) < 0:
prev_layer_id = layer_id + int(from_layers[index])
else:
prev_layer_id = int(from_layers[index])
bottom = topnames[prev_layer_id]
bottom_tmp.append(bottom)
concat_layer = OrderedDict()
concat_layer['bottom'] = bottom_tmp
if block.has_key('name'):
concat_layer['top'] = block['name']
concat_layer['name'] = block['name']
else:
concat_layer['top'] = 'layer%d-concat' % layer_id
concat_layer['name'] = 'layer%d-concat' % layer_id
concat_layer['type'] = 'Concat'
if DEBUG:
print("concat_layer: %s" % concat_layer)
layers.append(concat_layer)
bottom = concat_layer['top']
topnames[layer_id] = bottom
layer_id = layer_id+1
elif block['type'] == 'shortcut':
prev_layer_id1 = layer_id + int(block['from'])
prev_layer_id2 = layer_id - 1
bottom1 = topnames[prev_layer_id1]
bottom2= topnames[prev_layer_id2]
shortcut_layer = OrderedDict()
shortcut_layer['bottom'] = [bottom1, bottom2]
if block.has_key('name'):
shortcut_layer['top'] = block['name']
shortcut_layer['name'] = block['name']
else:
shortcut_layer['top'] = 'layer%d-shortcut' % layer_id
shortcut_layer['name'] = 'layer%d-shortcut' % layer_id
shortcut_layer['type'] = 'Eltwise'
eltwise_param = OrderedDict()
eltwise_param['operation'] = 'SUM'
shortcut_layer['eltwise_param'] = eltwise_param
layers.append(shortcut_layer)
bottom = shortcut_layer['top']
if block['activation'] != 'linear':
relu_layer = OrderedDict()
relu_layer['bottom'] = bottom
relu_layer['top'] = bottom
if block.has_key('name'):
relu_layer['name'] = '%s-act' % block['name']
else:
relu_layer['name'] = 'layer%d-act' % layer_id
relu_layer['type'] = 'ReLU'
if block['activation'] == 'leaky':
relu_param = OrderedDict()
relu_param['negative_slope'] = '0.1'
relu_layer['relu_param'] = relu_param
layers.append(relu_layer)
topnames[layer_id] = bottom
layer_id = layer_id+1
elif block['type'] == 'connected':
fc_layer = OrderedDict()
fc_layer['bottom'] = bottom
if block.has_key('name'):
fc_layer['top'] = block['name']
fc_layer['name'] = block['name']
else:
fc_layer['top'] = 'layer%d-fc' % layer_id
fc_layer['name'] = 'layer%d-fc' % layer_id
fc_layer['type'] = 'InnerProduct'
fc_param = OrderedDict()
fc_param['num_output'] = int(block['output'])
fc_layer['inner_product_param'] = fc_param
layers.append(fc_layer)
bottom = fc_layer['top']
if block['activation'] != 'linear':
relu_layer = OrderedDict()
relu_layer['bottom'] = bottom
relu_layer['top'] = bottom
if block.has_key('name'):
relu_layer['name'] = '%s-act' % block['name']
else:
relu_layer['name'] = 'layer%d-act' % layer_id
relu_layer['type'] = 'ReLU'
if block['activation'] == 'leaky':
relu_param = OrderedDict()
relu_param['negative_slope'] = '0.1'
relu_layer['relu_param'] = relu_param
layers.append(relu_layer)
topnames[layer_id] = bottom
layer_id = layer_id+1
##add reorg layer yolov2###############
elif block['type'] == 'reorg':
reorg_layer = OrderedDict()
reorg_layer['bottom'] = bottom
if block.has_key('name'):
reorg_layer['top'] = block['name']
reorg_layer['name'] = block['name']
else:
reorg_layer['top'] = 'layer%d-reorg' % layer_id
reorg_layer['name'] = 'layer%d-reorg' % layer_id
reorg_layer['type'] = 'Reorg'
reorg_param = OrderedDict()
reorg_param['stride'] = 2
reorg_layer['reorg_param'] = reorg_param
layers.append(reorg_layer)
bottom = reorg_layer['top']
topnames[layer_id] = bottom
layer_id = layer_id + 1
##add upsample layer yolov3###############
elif block['type'] == 'upsample' :
upsample_layer = OrderedDict()
upsample_layer['bottom'] = bottom
if block.has_key('name'):
upsample_layer['top'] = block['name']
upsample_layer['name'] = block['name']
else:
upsample_layer['top'] = 'layer%d-upsample' % layer_id
upsample_layer['name'] = 'layer%d-upsample' % layer_id
upsample_layer['type'] = 'DeephiResize'
upsample_param = OrderedDict()
upsample_param['scale_h'] = 2
upsample_param['scale_w'] = 2
upsample_layer['deephi_resize_param'] = upsample_param
layers.append(upsample_layer)
bottom = upsample_layer['top']
topnames[layer_id] = bottom
layer_id = layer_id + 1
elif block['type'] == 'region' or block['type'] == 'yolo':
layer_id = layer_id + 1
#######################################
else:
print('unknow layer type %s ' % block['type'])
topnames[layer_id] = bottom
layer_id = layer_id + 1
net_info = OrderedDict()
net_info['props'] = props
net_info['layers'] = layers
return net_info
if __name__ == '__main__':
import sys
if len(sys.argv) != 5:
print('try:')
print('python convert.py yolov3.cfg yolov3.weights yolov3.prototxt yolov3.caffemodel')
print('')
print('please add name field for each block to avoid generated name')
exit()
cfgfile = sys.argv[1]
weightfile = sys.argv[2]
protofile = sys.argv[3]
caffemodel = sys.argv[4]
darknet2caffe(cfgfile, weightfile, protofile, caffemodel)