-
Notifications
You must be signed in to change notification settings - Fork 69
/
data_transformer.cpp
568 lines (503 loc) · 18.4 KB
/
data_transformer.cpp
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
#ifndef OSX
#include <opencv2/core/core.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#endif
#include <string>
#include <vector>
#include "caffe/data_transformer.hpp"
#include "caffe/util/io.hpp"
#include "caffe/util/math_functions.hpp"
#include "caffe/util/rng.hpp"
namespace caffe {
template<typename Dtype>
DataTransformer<Dtype>::DataTransformer(const TransformationParameter& param)
: param_(param) {
phase_ = Caffe::phase();
// check if we want to use mean_file
if (param_.has_mean_file()) {
CHECK_EQ(param_.mean_value_size(), 0) <<
"Cannot specify mean_file and mean_value at the same time";
const string& mean_file = param.mean_file();
LOG(INFO) << "Loading mean file from" << mean_file;
BlobProto blob_proto;
ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);
data_mean_.FromProto(blob_proto);
}
// check if we want to use mean_value
if (param_.mean_value_size() > 0) {
CHECK(param_.has_mean_file() == false) <<
"Cannot specify mean_file and mean_value at the same time";
for (int c = 0; c < param_.mean_value_size(); ++c) {
mean_values_.push_back(param_.mean_value(c));
}
}
}
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const Datum& datum,
Dtype* transformed_data) {
const string& data = datum.data();
const int datum_channels = datum.channels();
const int datum_height = datum.height();
const int datum_width = datum.width();
const int crop_size = param_.crop_size();
const Dtype scale = param_.scale();
const bool do_mirror = param_.mirror() && Rand(2);
const bool has_mean_file = param_.has_mean_file();
const bool has_uint8 = data.size() > 0;
const bool has_mean_values = mean_values_.size() > 0;
CHECK_GT(datum_channels, 0);
CHECK_GE(datum_height, crop_size);
CHECK_GE(datum_width, crop_size);
Dtype* mean = NULL;
if (has_mean_file) {
CHECK_EQ(datum_channels, data_mean_.channels());
CHECK_EQ(datum_height, data_mean_.height());
CHECK_EQ(datum_width, data_mean_.width());
mean = data_mean_.mutable_cpu_data();
}
if (has_mean_values) {
CHECK(mean_values_.size() == 1 || mean_values_.size() == datum_channels) <<
"Specify either 1 mean_value or as many as channels: " << datum_channels;
if (datum_channels > 1 && mean_values_.size() == 1) {
// Replicate the mean_value for simplicity
for (int c = 1; c < datum_channels; ++c) {
mean_values_.push_back(mean_values_[0]);
}
}
}
int height = datum_height;
int width = datum_width;
int h_off = 0;
int w_off = 0;
if (crop_size) {
height = crop_size;
width = crop_size;
// We only do random crop when we do training.
if (phase_ == Caffe::TRAIN) {
h_off = Rand(datum_height - crop_size + 1);
w_off = Rand(datum_width - crop_size + 1);
} else {
h_off = (datum_height - crop_size) / 2;
w_off = (datum_width - crop_size) / 2;
}
}
Dtype datum_element;
int top_index, data_index;
for (int c = 0; c < datum_channels; ++c) {
for (int h = 0; h < height; ++h) {
for (int w = 0; w < width; ++w) {
data_index = (c * datum_height + h_off + h) * datum_width + w_off + w;
if (do_mirror) {
top_index = (c * height + h) * width + (width - 1 - w);
} else {
top_index = (c * height + h) * width + w;
}
if (has_uint8) {
datum_element =
static_cast<Dtype>(static_cast<uint8_t>(data[data_index]));
} else {
datum_element = datum.float_data(data_index);
}
if (has_mean_file) {
transformed_data[top_index] =
(datum_element - mean[data_index]) * scale;
} else {
if (has_mean_values) {
transformed_data[top_index] =
(datum_element - mean_values_[c]) * scale;
} else {
transformed_data[top_index] = datum_element * scale;
}
}
}
}
}
}
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const Datum& datum,
Blob<Dtype>* transformed_blob) {
const int datum_channels = datum.channels();
const int datum_height = datum.height();
const int datum_width = datum.width();
const int channels = transformed_blob->channels();
const int height = transformed_blob->height();
const int width = transformed_blob->width();
const int num = transformed_blob->num();
CHECK_EQ(channels, datum_channels);
CHECK_LE(height, datum_height);
CHECK_LE(width, datum_width);
CHECK_GE(num, 1);
const int crop_size = param_.crop_size();
if (crop_size) {
CHECK_EQ(crop_size, height);
CHECK_EQ(crop_size, width);
} else {
CHECK_EQ(datum_height, height);
CHECK_EQ(datum_width, width);
}
Dtype* transformed_data = transformed_blob->mutable_cpu_data();
Transform(datum, transformed_data);
}
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const vector<Datum> & datum_vector,
Blob<Dtype>* transformed_blob) {
const int datum_num = datum_vector.size();
const int num = transformed_blob->num();
const int channels = transformed_blob->channels();
const int height = transformed_blob->height();
const int width = transformed_blob->width();
CHECK_GT(datum_num, 0) << "There is no datum to add";
CHECK_LE(datum_num, num) <<
"The size of datum_vector must be smaller than transformed_blob->num()";
Blob<Dtype> uni_blob(1, channels, height, width);
for (int item_id = 0; item_id < datum_num; ++item_id) {
int offset = transformed_blob->offset(item_id);
uni_blob.set_cpu_data(transformed_blob->mutable_cpu_data() + offset);
Transform(datum_vector[item_id], &uni_blob);
}
}
#ifndef OSX
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const cv::Mat& cv_img,
Blob<Dtype>* transformed_blob) {
const int img_channels = cv_img.channels();
const int img_height = cv_img.rows;
const int img_width = cv_img.cols;
const int channels = transformed_blob->channels();
const int height = transformed_blob->height();
const int width = transformed_blob->width();
const int num = transformed_blob->num();
CHECK_EQ(channels, img_channels);
CHECK_LE(height, img_height);
CHECK_LE(width, img_width);
CHECK_GE(num, 1);
CHECK(cv_img.depth() == CV_8U) << "Image data type must be unsigned byte";
const int crop_size = param_.crop_size();
const Dtype scale = param_.scale();
const bool do_mirror = param_.mirror() && Rand(2);
const bool has_mean_file = param_.has_mean_file();
const bool has_mean_values = mean_values_.size() > 0;
CHECK_GT(img_channels, 0);
CHECK_GE(img_height, crop_size);
CHECK_GE(img_width, crop_size);
Dtype* mean = NULL;
if (has_mean_file) {
CHECK_EQ(img_channels, data_mean_.channels());
CHECK_EQ(img_height, data_mean_.height());
CHECK_EQ(img_width, data_mean_.width());
mean = data_mean_.mutable_cpu_data();
}
if (has_mean_values) {
CHECK(mean_values_.size() == 1 || mean_values_.size() == img_channels) <<
"Specify either 1 mean_value or as many as channels: " << img_channels;
if (img_channels > 1 && mean_values_.size() == 1) {
// Replicate the mean_value for simplicity
for (int c = 1; c < img_channels; ++c) {
mean_values_.push_back(mean_values_[0]);
}
}
}
int h_off = 0;
int w_off = 0;
cv::Mat cv_cropped_img = cv_img;
if (crop_size) {
CHECK_EQ(crop_size, height);
CHECK_EQ(crop_size, width);
// We only do random crop when we do training.
if (phase_ == Caffe::TRAIN) {
h_off = Rand(img_height - crop_size + 1);
w_off = Rand(img_width - crop_size + 1);
} else {
h_off = (img_height - crop_size) / 2;
w_off = (img_width - crop_size) / 2;
}
cv::Rect roi(w_off, h_off, crop_size, crop_size);
cv_cropped_img = cv_img(roi);
} else {
CHECK_EQ(img_height, height);
CHECK_EQ(img_width, width);
}
CHECK(cv_cropped_img.data);
Dtype* transformed_data = transformed_blob->mutable_cpu_data();
int top_index;
for (int h = 0; h < height; ++h) {
const uchar* ptr = cv_cropped_img.ptr<uchar>(h);
int img_index = 0;
for (int w = 0; w < width; ++w) {
for (int c = 0; c < img_channels; ++c) {
if (do_mirror) {
top_index = (c * height + h) * width + (width - 1 - w);
} else {
top_index = (c * height + h) * width + w;
}
// int top_index = (c * height + h) * width + w;
Dtype pixel = static_cast<Dtype>(ptr[img_index++]);
if (has_mean_file) {
int mean_index = (c * img_height + h_off + h) * img_width + w_off + w;
transformed_data[top_index] =
(pixel - mean[mean_index]) * scale;
} else {
if (has_mean_values) {
transformed_data[top_index] =
(pixel - mean_values_[c]) * scale;
} else {
transformed_data[top_index] = pixel * scale;
}
}
}
}
}
}
/*
notice:
this code is based on the following implementation.
https://bitbucket.org/deeplab/deeplab-public/
*/
template<typename Dtype>
void DataTransformer<Dtype>::TransformImgAndSeg(const std::vector<cv::Mat>& cv_img_seg,
Blob<Dtype>* transformed_data_blob, Blob<Dtype>* transformed_label_blob, const int ignore_label) {
CHECK(cv_img_seg.size() == 2) << "Input must contain image and seg.";
const int img_channels = cv_img_seg[0].channels();
// height and width may change due to pad for cropping
int img_height = cv_img_seg[0].rows;
int img_width = cv_img_seg[0].cols;
const int seg_channels = cv_img_seg[1].channels();
int seg_height = cv_img_seg[1].rows;
int seg_width = cv_img_seg[1].cols;
const int data_channels = transformed_data_blob->channels();
const int data_height = transformed_data_blob->height();
const int data_width = transformed_data_blob->width();
const int label_channels = transformed_label_blob->channels();
const int label_height = transformed_label_blob->height();
const int label_width = transformed_label_blob->width();
CHECK_EQ(seg_channels, 1);
CHECK_EQ(img_channels, data_channels);
CHECK_EQ(img_height, seg_height);
CHECK_EQ(img_width, seg_width);
CHECK_EQ(label_channels, 1);
CHECK_EQ(data_height, label_height);
CHECK_EQ(data_width, label_width);
CHECK(cv_img_seg[0].depth() == CV_8U) << "Image data type must be unsigned byte";
CHECK(cv_img_seg[1].depth() == CV_8U) << "Seg data type must be unsigned byte";
const int crop_size = param_.crop_size();
const Dtype scale = param_.scale();
const bool do_mirror = param_.mirror() && Rand(2);
const bool has_mean_file = param_.has_mean_file();
const bool has_mean_values = mean_values_.size() > 0;
CHECK_GT(img_channels, 0);
Dtype* mean = NULL;
if (has_mean_file) {
CHECK_EQ(img_channels, data_mean_.channels());
CHECK_EQ(img_height, data_mean_.height());
CHECK_EQ(img_width, data_mean_.width());
mean = data_mean_.mutable_cpu_data();
}
if (has_mean_values) {
CHECK(mean_values_.size() == 1 || mean_values_.size() == img_channels) <<
"Specify either 1 mean_value or as many as channels: " << img_channels;
if (img_channels > 1 && mean_values_.size() == 1) {
// Replicate the mean_value for simplicity
for (int c = 1; c < img_channels; ++c) {
mean_values_.push_back(mean_values_[0]);
}
}
}
int h_off = 0;
int w_off = 0;
cv::Mat cv_cropped_img = cv_img_seg[0];
cv::Mat cv_cropped_seg = cv_img_seg[1];
// transform to double, since we will pad mean pixel values
cv_cropped_img.convertTo(cv_cropped_img, CV_64F);
// Check if we need to pad img to fit for crop_size
// copymakeborder
int pad_height = std::max(crop_size - img_height, 0);
int pad_width = std::max(crop_size - img_width, 0);
if (pad_height > 0 || pad_width > 0) {
cv::copyMakeBorder(cv_cropped_img, cv_cropped_img, 0, pad_height,
0, pad_width, cv::BORDER_CONSTANT,
cv::Scalar(mean_values_[0], mean_values_[1], mean_values_[2]));
cv::copyMakeBorder(cv_cropped_seg, cv_cropped_seg, 0, pad_height,
0, pad_width, cv::BORDER_CONSTANT,
cv::Scalar(ignore_label));
// update height/width
img_height = cv_cropped_img.rows;
img_width = cv_cropped_img.cols;
seg_height = cv_cropped_seg.rows;
seg_width = cv_cropped_seg.cols;
}
// crop img/seg
if (crop_size) {
CHECK_EQ(crop_size, data_height);
CHECK_EQ(crop_size, data_width);
// We only do random crop when we do training.
if (phase_ == Caffe::TRAIN) {
h_off = Rand(img_height - crop_size + 1);
w_off = Rand(img_width - crop_size + 1);
} else {
// CHECK: use middle crop
h_off = (img_height - crop_size) / 2;
w_off = (img_width - crop_size) / 2;
}
cv::Rect roi(w_off, h_off, crop_size, crop_size);
cv_cropped_img = cv_cropped_img(roi);
cv_cropped_seg = cv_cropped_seg(roi);
}
CHECK(cv_cropped_img.data);
CHECK(cv_cropped_seg.data);
Dtype* transformed_data = transformed_data_blob->mutable_cpu_data();
Dtype* transformed_label = transformed_label_blob->mutable_cpu_data();
int top_index;
const double* data_ptr;
const uchar* label_ptr;
for (int h = 0; h < data_height; ++h) {
data_ptr = cv_cropped_img.ptr<double>(h);
label_ptr = cv_cropped_seg.ptr<uchar>(h);
int data_index = 0;
int label_index = 0;
for (int w = 0; w < data_width; ++w) {
// for image
for (int c = 0; c < img_channels; ++c) {
if (do_mirror) {
top_index = (c * data_height + h) * data_width + (data_width - 1 - w);
} else {
top_index = (c * data_height + h) * data_width + w;
}
Dtype pixel = static_cast<Dtype>(data_ptr[data_index++]);
if (has_mean_file) {
int mean_index = (c * img_height + h_off + h) * img_width + w_off + w;
transformed_data[top_index] =
(pixel - mean[mean_index]) * scale;
} else {
if (has_mean_values) {
transformed_data[top_index] =
(pixel - mean_values_[c]) * scale;
} else {
transformed_data[top_index] = pixel * scale;
}
}
}
// for segmentation
if (do_mirror) {
top_index = h * data_width + data_width - 1 - w;
} else {
top_index = h * data_width + w;
}
Dtype pixel = static_cast<Dtype>(label_ptr[label_index++]);
transformed_label[top_index] = pixel;
}
}
}
#endif
template<typename Dtype>
void DataTransformer<Dtype>::Transform(Blob<Dtype>* input_blob,
Blob<Dtype>* transformed_blob) {
const int input_num = input_blob->num();
const int input_channels = input_blob->channels();
const int input_height = input_blob->height();
const int input_width = input_blob->width();
const int num = transformed_blob->num();
const int channels = transformed_blob->channels();
const int height = transformed_blob->height();
const int width = transformed_blob->width();
const int size = transformed_blob->count();
CHECK_LE(input_num, num);
CHECK_EQ(input_channels, channels);
CHECK_GE(input_height, height);
CHECK_GE(input_width, width);
const int crop_size = param_.crop_size();
const Dtype scale = param_.scale();
const bool do_mirror = param_.mirror() && Rand(2);
const bool has_mean_file = param_.has_mean_file();
const bool has_mean_values = mean_values_.size() > 0;
int h_off = 0;
int w_off = 0;
if (crop_size) {
CHECK_EQ(crop_size, height);
CHECK_EQ(crop_size, width);
// We only do random crop when we do training.
if (phase_ == Caffe::TRAIN) {
h_off = Rand(input_height - crop_size + 1);
w_off = Rand(input_width - crop_size + 1);
} else {
h_off = (input_height - crop_size) / 2;
w_off = (input_width - crop_size) / 2;
}
} else {
CHECK_EQ(input_height, height);
CHECK_EQ(input_width, width);
}
Dtype* input_data = input_blob->mutable_cpu_data();
if (has_mean_file) {
CHECK_EQ(input_channels, data_mean_.channels());
CHECK_EQ(input_height, data_mean_.height());
CHECK_EQ(input_width, data_mean_.width());
for (int n = 0; n < input_num; ++n) {
int offset = input_blob->offset(n);
caffe_sub(data_mean_.count(), input_data + offset,
data_mean_.cpu_data(), input_data + offset);
}
}
if (has_mean_values) {
CHECK(mean_values_.size() == 1 || mean_values_.size() == input_channels) <<
"Specify either 1 mean_value or as many as channels: " << input_channels;
if (mean_values_.size() == 1) {
caffe_add_scalar(input_blob->count(), -(mean_values_[0]), input_data);
} else {
for (int n = 0; n < input_num; ++n) {
for (int c = 0; c < input_channels; ++c) {
int offset = input_blob->offset(n, c);
caffe_add_scalar(input_height * input_width, -(mean_values_[c]),
input_data + offset);
}
}
}
}
Dtype* transformed_data = transformed_blob->mutable_cpu_data();
for (int n = 0; n < input_num; ++n) {
int top_index_n = n * channels;
int data_index_n = n * channels;
for (int c = 0; c < channels; ++c) {
int top_index_c = (top_index_n + c) * height;
int data_index_c = (data_index_n + c) * input_height + h_off;
for (int h = 0; h < height; ++h) {
int top_index_h = (top_index_c + h) * width;
int data_index_h = (data_index_c + h) * input_width + w_off;
if (do_mirror) {
int top_index_w = top_index_h + width - 1;
for (int w = 0; w < width; ++w) {
transformed_data[top_index_w-w] = input_data[data_index_h + w];
}
} else {
for (int w = 0; w < width; ++w) {
transformed_data[top_index_h + w] = input_data[data_index_h + w];
}
}
}
}
}
if (scale != Dtype(1)) {
DLOG(INFO) << "Scale: " << scale;
caffe_scal(size, scale, transformed_data);
}
}
template <typename Dtype>
void DataTransformer<Dtype>::InitRand() {
const bool needs_rand = param_.mirror() ||
(phase_ == Caffe::TRAIN && param_.crop_size());
if (needs_rand) {
const unsigned int rng_seed = caffe_rng_rand();
rng_.reset(new Caffe::RNG(rng_seed));
} else {
rng_.reset();
}
}
template <typename Dtype>
int DataTransformer<Dtype>::Rand(int n) {
CHECK(rng_);
CHECK_GT(n, 0);
caffe::rng_t* rng =
static_cast<caffe::rng_t*>(rng_->generator());
return ((*rng)() % n);
}
INSTANTIATE_CLASS(DataTransformer);
} // namespace caffe