-
Notifications
You must be signed in to change notification settings - Fork 0
/
nn_ds_neibs10.py
1515 lines (1353 loc) · 79.9 KB
/
nn_ds_neibs10.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
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
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/env python3
from numpy import float64
from tensorflow.contrib.losses.python.metric_learning.metric_loss_ops import npairs_loss
from debian.deb822 import PdiffIndex
__copyright__ = "Copyright 2018, Elphel, Inc."
__license__ = "GPL-3.0+"
__email__ = "[email protected]"
from PIL import Image
import os
import sys
import glob
import numpy as np
import itertools
import time
import matplotlib.pyplot as plt
import shutil
import sys
from threading import Thread
TIME_START = time.time()
TIME_LAST = TIME_START
DEBUG_LEVEL= 1
DISP_BATCH_BINS = 20 # Number of batch disparity bins
STR_BATCH_BINS = 10 # Number of batch strength bins
FILES_PER_SCENE = 5 # number of random offset files for the scene to select from (0 - use all available)
#MIN_BATCH_CHOICES = 10 # minimal number of tiles in a file for each bin to select from
#MAX_BATCH_FILES = 10 #maximal number of files to use in a batch
#MAX_EPOCH = 500
LR = 1e-3 # learning rate
LR100 = 3e-4 #LR # 1e-4
LR200 = 1e-4 #LR100 # 3e-5
LR400 = 3e-5 #LR200 # 1e-5
LR600 = 1e-5 #LR400 # 3e-6
USE_CONFIDENCE = False
ABSOLUTE_DISPARITY = False # True # False # True # False
DEBUG_PLT_LOSS = True
TILE_LAYERS = 4
FILE_TILE_SIDE = 9
TILE_SIDE = 9 # 7
TILE_SIZE = TILE_SIDE* TILE_SIDE # == 81
FEATURES_PER_TILE = TILE_LAYERS * TILE_SIZE# == 324
EPOCHS_TO_RUN = 3000#0 #0
EPOCHS_FULL_TEST = 5 # 10 # 25# repeat full image test after this number of epochs
#EPOCHS_SAME_FILE = 20
RUN_TOT_AVG = 100 # last batches to average. Epoch is 307 training batches
#BATCH_SIZE = 2*1080//9 # == 120 Each batch of tiles has balanced D/S tiles, shuffled batches but not inside batches
TWO_TRAINS = True # use 2 train sets
BATCH_SIZE = ([1,2][TWO_TRAINS])*2*1000//25 # == 80 Each batch of tiles has balanced D/S tiles, shuffled batches but not inside batches
SHUFFLE_EPOCH = True
NET_ARCH1 = 0 # 4 # #4 # 8 # 4 # 0 #3 # 0 # 0 # 0 # 0 # 8 # 0 # 7 # 2 #0 # 6 #0 # 4 # 3 # overwrite with argv?
NET_ARCH2 = 0 # 4 # 0 # 0 # 4 # 0 # 0 # 3 # 0 # 3 # 0 # 3 # 0 # 2 #0 # 6 # 0 # 3 # overwrite with argv?
SYM8_SUB = False # True #False # True # False # True # False # True # False # enforce inputs from 2d correlation have symmetrical ones (groups of 8)
ONLY_TILE = None # 4 # None # 0 # 4# None # (remove all but center tile data), put None here for normal operation)
ZIP_LHVAR = True # combine _lvar and _hvar as odd/even elements
#DEBUG_PACK_TILES = True
# CLUSTER_RADIUS should match input data
CLUSTER_RADIUS = 2 # 1 # 1 - 3x3, 2 - 5x5 tiles
SHUFFLE_FILES = True
WLOSS_LAMBDA = 0.5 #3.0 # 1.0 # 0.3 # 0.0 # 50.0 # 5.0 # 1.0 # fraction of the W_loss (input layers weight non-uniformity) added to G_loss
WBORDERS_ZERO = True # Border conditions for first layer weights: False - free, True - tied to 0
MAX_FILES_PER_GROUP = 6 # just to try, normally should be 8
FILE_UPDATE_EPOCHS = 2 # update train files each this many epochs. 0 - do not update
PARTIALS_WEIGHTS = [1.0,1.0,1.0] # weight of full 5x5, center 3x3 and center 1x1. len(PARTIALS_WEIGHTS) == CLUSTER_RADIUS + 1. Set to None
SUFFIX=str(NET_ARCH1)+'-'+str(NET_ARCH2)+ (["R","A"][ABSOLUTE_DISPARITY]) +(["NS","S8"][SYM8_SUB])+"LMBD"+str(WLOSS_LAMBDA)
NN_LAYOUTS = {0:[0, 0, 0, 32, 20, 16],
1:[0, 0, 0, 256, 128, 64],
2:[0, 128, 32, 32, 32, 16],
3:[0, 0, 40, 32, 20, 16],
4:[0, 0, 0, 0, 16, 16],
5:[0, 0, 64, 32, 32, 16],
6:[0, 0, 32, 16, 16, 16],
7:[0, 0, 64, 16, 16, 16],
8:[0, 0, 0, 64, 20, 16],
}
NN_LAYOUT1 = NN_LAYOUTS[NET_ARCH1]
NN_LAYOUT2 = NN_LAYOUTS[NET_ARCH2]
USE_PARTIALS = not PARTIALS_WEIGHTS is None # False - just a single Siamese net, True - partial outputs that use concentric squares of the first level subnets
#http://stackoverflow.com/questions/287871/print-in-terminal-with-colors-using-python
class bcolors:
HEADER = '\033[95m'
OKBLUE = '\033[94m'
OKGREEN = '\033[92m'
WARNING = '\033[38;5;214m'
FAIL = '\033[91m'
ENDC = '\033[0m'
BOLD = '\033[1m'
BOLDWHITE = '\033[1;37m'
UNDERLINE = '\033[4m'
def print_time(txt="",end="\n"):
global TIME_LAST
t = time.time()
if txt:
txt +=" "
print(("%s"+bcolors.BOLDWHITE+"at %.4fs (+%.4fs)"+bcolors.ENDC)%(txt,t-TIME_START,t-TIME_LAST), end = end, flush=True)
TIME_LAST = t
#reading to memory (testing)
train_next = [{'file':0, 'slot':0, 'files':0, 'slots':0},
{'file':0, 'slot':0, 'files':0, 'slots':0}]
if TWO_TRAINS:
train_next += [{'file':0, 'slot':0, 'files':0, 'slots':0},
{'file':0, 'slot':0, 'files':0, 'slots':0}]
def readTFRewcordsEpoch(train_filename):
# filenames = [train_filename]
# dataset = tf.data.TFRecorDataset(filenames)
if not '.tfrecords' in train_filename:
train_filename += '.tfrecords'
npy_dir_name = "npy"
dirname = os.path.dirname(train_filename)
npy_dir = os.path.join(dirname, npy_dir_name)
filebasename, file_extension = os.path.splitext(train_filename)
filebasename = os.path.basename(filebasename)
file_corr2d = os.path.join(npy_dir,filebasename + '_corr2d.npy')
file_target_disparity = os.path.join(npy_dir,filebasename + '_target_disparity.npy')
file_gt_ds = os.path.join(npy_dir,filebasename + '_gt_ds.npy')
if (os.path.exists(file_corr2d) and
os.path.exists(file_target_disparity) and
os.path.exists(file_gt_ds)):
corr2d= np.load (file_corr2d)
target_disparity = np.load(file_target_disparity)
gt_ds = np.load(file_gt_ds)
pass
else:
record_iterator = tf.python_io.tf_record_iterator(path=train_filename)
corr2d_list=[]
target_disparity_list=[]
gt_ds_list = []
for string_record in record_iterator:
example = tf.train.Example()
example.ParseFromString(string_record)
corr2d_list.append (np.array(example.features.feature['corr2d'].float_list.value, dtype=np.float32))
target_disparity_list.append (np.array(example.features.feature['target_disparity'].float_list.value, dtype=np.float32))
gt_ds_list.append (np.array(example.features.feature['gt_ds'].float_list.value, dtype= np.float32))
pass
corr2d= np.array(corr2d_list)
target_disparity = np.array(target_disparity_list)
gt_ds = np.array(gt_ds_list)
try:
os.makedirs(os.path.dirname(file_corr2d))
except:
pass
np.save(file_corr2d, corr2d)
np.save(file_target_disparity, target_disparity)
np.save(file_gt_ds, gt_ds)
return corr2d, target_disparity, gt_ds
def getMoreFiles(fpaths,rslt):
for fpath in fpaths:
corr2d, target_disparity, gt_ds = readTFRewcordsEpoch(fpath)
dataset = {"corr2d": corr2d,
"target_disparity": target_disparity,
"gt_ds": gt_ds}
if FILE_TILE_SIDE > TILE_SIDE:
reduce_tile_size([dataset], TILE_LAYERS, TILE_SIDE)
reformat_to_clusters([dataset])
rslt.append(dataset)
#from http://warmspringwinds.github.io/tensorflow/tf-slim/2016/12/21/tfrecords-guide/
def read_and_decode(filename_queue):
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(
serialized_example,
# Defaults are not specified since both keys are required.
features={
'corr2d': tf.FixedLenFeature([FEATURES_PER_TILE],tf.float32), #string),
'target_disparity': tf.FixedLenFeature([1], tf.float32), #.string),
'gt_ds': tf.FixedLenFeature([2], tf.float32) #.string)
})
corr2d = features['corr2d'] # tf.decode_raw(features['corr2d'], tf.float32)
target_disparity = features['target_disparity'] # tf.decode_raw(features['target_disparity'], tf.float32)
gt_ds = tf.cast(features['gt_ds'], tf.float32) # tf.decode_raw(features['gt_ds'], tf.float32)
in_features = tf.concat([corr2d,target_disparity],0)
# still some nan-s in correlation data?
# in_features_clean = tf.where(tf.is_nan(in_features), tf.zeros_like(in_features), in_features)
# corr2d_out, target_disparity_out, gt_ds_out = tf.train.shuffle_batch( [in_features_clean, target_disparity, gt_ds],
corr2d_out, target_disparity_out, gt_ds_out = tf.train.shuffle_batch( [in_features, target_disparity, gt_ds],
batch_size=1000, # 2,
capacity=30,
num_threads=2,
min_after_dequeue=10)
return corr2d_out, target_disparity_out, gt_ds_out
#http://adventuresinmachinelearning.com/introduction-tensorflow-queuing/
def add_margins(npa,radius, val = np.nan):
npa_ext = np.empty((npa.shape[0]+2*radius, npa.shape[1]+2*radius, npa.shape[2]), dtype = npa.dtype)
npa_ext[radius:radius + npa.shape[0],radius:radius + npa.shape[1]] = npa
npa_ext[0:radius,:,:] = val
npa_ext[radius + npa.shape[0]:,:,:] = val
npa_ext[:,0:radius,:] = val
npa_ext[:, radius + npa.shape[1]:,:] = val
return npa_ext
def add_neibs(npa_ext,radius):
height = npa_ext.shape[0]-2*radius
width = npa_ext.shape[1]-2*radius
side = 2 * radius + 1
size = side * side
npa_neib = np.empty((height, width, side, side, npa_ext.shape[2]), dtype = npa_ext.dtype)
for dy in range (side):
for dx in range (side):
npa_neib[:,:,dy, dx,:]= npa_ext[dy:dy+height, dx:dx+width]
return npa_neib.reshape(height, width, -1)
def extend_img_to_clusters(datasets_img,radius):
side = 2 * radius + 1
size = side * side
width = 324
if len(datasets_img) ==0:
return
num_tiles = datasets_img[0]['corr2d'].shape[0]
height = num_tiles // width
for rec in datasets_img:
rec['corr2d'] = add_neibs(add_margins(rec['corr2d'].reshape((height,width,-1)), radius, np.nan), radius).reshape((num_tiles,-1))
rec['target_disparity'] = add_neibs(add_margins(rec['target_disparity'].reshape((height,width,-1)), radius, np.nan), radius).reshape((num_tiles,-1))
rec['gt_ds'] = add_neibs(add_margins(rec['gt_ds'].reshape((height,width,-1)), radius, np.nan), radius).reshape((num_tiles,-1))
pass
def reformat_to_clusters(datasets_data):
cluster_size = (2 * CLUSTER_RADIUS + 1) * (2 * CLUSTER_RADIUS + 1)
# Reformat input data
for rec in datasets_data:
rec['corr2d'] = rec['corr2d'].reshape( (rec['corr2d'].shape[0]//cluster_size, rec['corr2d'].shape[1] * cluster_size))
rec['target_disparity'] = rec['target_disparity'].reshape((rec['target_disparity'].shape[0]//cluster_size, rec['target_disparity'].shape[1] * cluster_size))
rec['gt_ds'] = rec['gt_ds'].reshape( (rec['gt_ds'].shape[0]//cluster_size, rec['gt_ds'].shape[1] * cluster_size))
def replace_nan(datasets_data):
cluster_size = (2 * CLUSTER_RADIUS + 1) * (2 * CLUSTER_RADIUS + 1)
# Reformat input data
for rec in datasets_data:
np.nan_to_num(rec['corr2d'], copy = False)
np.nan_to_num(rec['target_disparity'], copy = False)
np.nan_to_num(rec['gt_ds'], copy = False)
def permute_to_swaps(perm):
pairs = []
for i in range(len(perm)):
w = np.where(perm == i)[0][0]
if w != i:
pairs.append([i,w])
perm[w] = perm[i]
perm[i] = i
return pairs
def shuffle_in_place(datasets_data, indx, period):
swaps = permute_to_swaps(np.random.permutation(len(datasets_data)))
num_entries = datasets_data[0]['corr2d'].shape[0] // period
for swp in swaps:
ds0 = datasets_data[swp[0]]
ds1 = datasets_data[swp[1]]
tmp = ds0['corr2d'][indx::period].copy()
ds0['corr2d'][indx::period] = ds1['corr2d'][indx::period]
ds1['corr2d'][indx::period] = tmp
tmp = ds0['target_disparity'][indx::period].copy()
ds0['target_disparity'][indx::period] = ds1['target_disparity'][indx::period]
ds1['target_disparity'][indx::period] = tmp
tmp = ds0['gt_ds'][indx::period].copy()
ds0['gt_ds'][indx::period] = ds1['gt_ds'][indx::period]
ds1['gt_ds'][indx::period] = tmp
def shuffle_chunks_in_place(datasets_data, tiles_groups_per_chunk):
"""
Improve shuffling by preserving indices inside batches (0 <->0, ... 39 <->39 for 40 tile group batches)
"""
num_files = len(datasets_data)
#chunks_per_file = datasets_data[0]['target_disparity']
for nf, ds in enumerate(datasets_data):
groups_per_file = ds['corr2d'].shape[0]
chunks_per_file = groups_per_file//tiles_groups_per_chunk
permut = np.random.permutation(chunks_per_file)
ds['corr2d'] = ds['corr2d']. reshape((chunks_per_file,-1))[permut].reshape((groups_per_file,-1))
ds['target_disparity'] = ds['target_disparity'].reshape((chunks_per_file,-1))[permut].reshape((groups_per_file,-1))
ds['gt_ds'] = ds['gt_ds']. reshape((chunks_per_file,-1))[permut].reshape((groups_per_file,-1))
def _setFileSlot(train_next,files):
train_next['files'] = files
train_next['slots'] = min(train_next['files'], MAX_FILES_PER_GROUP)
def _nextFileSlot(train_next):
train_next['file'] = (train_next['file'] + 1) % train_next['files']
train_next['slot'] = (train_next['slot'] + 1) % train_next['slots']
def replaceNextDataset(datasets_data, new_dataset, train_next, nset,period):
replaceDataset(datasets_data, new_dataset, nset, period, findx = train_next['slot'])
# _nextFileSlot(train_next[nset])
def replaceDataset(datasets_data, new_dataset, nset, period, findx):
"""
Replace one file in the dataset
"""
datasets_data[findx]['corr2d'] [nset::period] = new_dataset['corr2d']
datasets_data[findx]['target_disparity'][nset::period] = new_dataset['target_disparity']
datasets_data[findx]['gt_ds'] [nset::period] = new_dataset['gt_ds']
def zip_lvar_hvar(datasets_all_data, del_src = True):
# cluster_size = (2 * CLUSTER_RADIUS + 1) * (2 * CLUSTER_RADIUS + 1)
# Reformat input data
num_sets_to_combine = len(datasets_all_data)
datasets_data = []
if num_sets_to_combine:
for nrec in range(len(datasets_all_data[0])):
recs = [[] for _ in range(num_sets_to_combine)]
for nset, datasets in enumerate(datasets_all_data):
recs[nset] = datasets[nrec]
rec = {'corr2d': np.empty((recs[0]['corr2d'].shape[0]*num_sets_to_combine, recs[0]['corr2d'].shape[1]),dtype=np.float32),
'target_disparity': np.empty((recs[0]['target_disparity'].shape[0]*num_sets_to_combine,recs[0]['target_disparity'].shape[1]),dtype=np.float32),
'gt_ds': np.empty((recs[0]['gt_ds'].shape[0]*num_sets_to_combine, recs[0]['gt_ds'].shape[1]),dtype=np.float32)}
for nset, reci in enumerate(recs):
rec['corr2d'] [nset::num_sets_to_combine] = recs[nset]['corr2d']
rec['target_disparity'][nset::num_sets_to_combine] = recs[nset]['target_disparity']
rec['gt_ds'] [nset::num_sets_to_combine] = recs[nset]['gt_ds']
if del_src:
for nset in range(num_sets_to_combine):
datasets_all_data[nset][nrec] = None
datasets_data.append(rec)
return datasets_data
# list of dictionaries
def reduce_tile_size(datasets_data, num_tile_layers, reduced_tile_side):
if (not datasets_data is None) and (len (datasets_data) > 0):
tsz = (datasets_data[0]['corr2d'].shape[1])// num_tile_layers # 81 # list index out of range
tss = int(np.sqrt(tsz)+0.5)
offs = (tss - reduced_tile_side) // 2
for rec in datasets_data:
rec['corr2d'] = (rec['corr2d'].reshape((-1, num_tile_layers, tss, tss))
[..., offs:offs+reduced_tile_side, offs:offs+reduced_tile_side].
reshape(-1,num_tile_layers*reduced_tile_side*reduced_tile_side))
def eval_results(rslt_path, absolute,
min_disp = -0.1, #minimal GT disparity
max_disp = 20.0, # maximal GT disparity
max_ofst_target = 1.0,
max_ofst_result = 1.0,
str_pow = 2.0,
radius = 0):
# for min_disparity, max_disparity, max_offset_target, max_offset_result, strength_pow in [
variants = [[ -0.1, 5.0, 0.5, 0.5, 1.0],
[ -0.1, 5.0, 0.5, 0.5, 2.0],
[ -0.1, 5.0, 0.2, 0.2, 1.0],
[ -0.1, 5.0, 0.2, 0.2, 2.0],
[ -0.1, 20.0, 0.5, 0.5, 1.0],
[ -0.1, 20.0, 0.5, 0.5, 2.0],
[ -0.1, 20.0, 0.2, 0.2, 1.0],
[ -0.1, 20.0, 0.2, 0.2, 2.0],
[ -0.1, 20.0, 1.0, 1.0, 1.0],
[min_disp, max_disp, max_ofst_target, max_ofst_result, str_pow]]
rslt = np.load(result_file)
not_nan = ~np.isnan(rslt[...,0])
not_nan &= ~np.isnan(rslt[...,1])
not_nan &= ~np.isnan(rslt[...,2])
not_nan &= ~np.isnan(rslt[...,3])
not_nan_ext = np.zeros((rslt.shape[0] + 2*radius,rslt.shape[1] + 2 * radius),dtype=np.bool)
not_nan_ext[radius:-radius,radius:-radius] = not_nan
for dy in range(2*radius+1):
for dx in range(2*radius+1):
not_nan_ext[dy:dy+not_nan.shape[0], dx:dx+not_nan.shape[1]] &= not_nan
not_nan = not_nan_ext[radius:-radius,radius:-radius]
if not absolute:
rslt[...,0] += rslt[...,1]
nn_disparity = np.nan_to_num(rslt[...,0], copy = False)
target_disparity = np.nan_to_num(rslt[...,1], copy = False)
gt_disparity = np.nan_to_num(rslt[...,2], copy = False)
gt_strength = np.nan_to_num(rslt[...,3], copy = False)
rslt = []
for min_disparity, max_disparity, max_offset_target, max_offset_result, strength_pow in variants:
good_tiles = not_nan.copy();
good_tiles &= (gt_disparity >= min_disparity)
good_tiles &= (gt_disparity <= max_disparity)
good_tiles &= (target_disparity != gt_disparity)
good_tiles &= (np.abs(target_disparity - gt_disparity) <= max_offset_target)
good_tiles &= (np.abs(target_disparity - nn_disparity) <= max_offset_result)
gt_w = gt_strength * good_tiles
gt_w = np.power(gt_w,strength_pow)
sw = gt_w.sum()
diff0 = target_disparity - gt_disparity
diff1 = nn_disparity - gt_disparity
diff0_2w = gt_w*diff0*diff0
diff1_2w = gt_w*diff1*diff1
rms0 = np.sqrt(diff0_2w.sum()/sw)
rms1 = np.sqrt(diff1_2w.sum()/sw)
print ("%7.3f<disp<%7.3f, offs_tgt<%5.2f, offs_rslt<%5.2f pwr=%05.3f, rms0=%7.4f, rms1=%7.4f (gain=%7.4f) num good tiles = %5d"%(
min_disparity, max_disparity, max_offset_target, max_offset_result, strength_pow, rms0, rms1, rms0/rms1, good_tiles.sum() ))
rslt.append([rms0,rms1])
return rslt
def concentricSquares(radius):
side = 2 * radius + 1
return [[((i // side) >= var) and
((i // side) < (side - var)) and
((i % side) >= var) and
((i % side) < (side - var)) for i in range (side*side) ] for var in range(radius+1)]
"""
Start of the main code
"""
"""
try:
train_filenameTFR = sys.argv[1]
except IndexError:
train_filenameTFR = "/mnt/dde6f983-d149-435e-b4a2-88749245cc6c/home/eyesis/x3d_data/data_sets/tf_data/train_00.tfrecords"
try:
test_filenameTFR = sys.argv[2]
except IndexError:
test_filenameTFR = "/mnt/dde6f983-d149-435e-b4a2-88749245cc6c/home/eyesis/x3d_data/data_sets/tf_data/test.tfrecords"
#FILES_PER_SCENE
train_filenameTFR1 = "/mnt/dde6f983-d149-435e-b4a2-88749245cc6c/home/eyesis/x3d_data/data_sets/tf_data/train_01.tfrecords"
"""
data_dir = "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main_1" # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_dbg" #"/home/eyesis/x3d_data/data_sets/tf_data_5x5_dbg"
data_dir1 = "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main_4" # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_dbg" #"/home/eyesis/x3d_data/data_sets/tf_data_5x5_dbg"
#img_dir = "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main_1" # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_dbg"
img_dir = "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main_5" # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_dbg"
dir_train_lvar = data_dir #"/home/eyesis/x3d_data/data_sets/tf_data_5x5_main_1" # data_dir # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
dir_train_hvar = data_dir # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
dir_train_lvar1 = data_dir1 #"/home/eyesis/x3d_data/data_sets/tf_data_5x5_main_1" # data_dir # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
dir_train_hvar1 = data_dir1 # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
dir_test_lvar = data_dir # data_dir #"/home/eyesis/x3d_data/data_sets/tf_data_5x5_center/" # data_dir # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
#dir_test_hvar = "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main_3" # data_dir #"/home/eyesis/x3d_data/data_sets/tf_data_5x5_center" # data_dir # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
dir_test_hvar = "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main_5" # data_dir #"/home/eyesis/x3d_data/data_sets/tf_data_5x5_center" # data_dir # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
dir_img = os.path.join(img_dir,"img") # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main/img"
dir_result = os.path.join(data_dir,"result") # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main/result"
files_train_lvar = ["train000_R2_LE_1.5.tfrecords",
"train001_R2_LE_1.5.tfrecords",
"train002_R2_LE_1.5.tfrecords",
"train003_R2_LE_1.5.tfrecords",
"train004_R2_LE_1.5.tfrecords",
"train005_R2_LE_1.5.tfrecords",
"train006_R2_LE_1.5.tfrecords",
"train007_R2_LE_1.5.tfrecords",
"train008_R2_LE_1.5.tfrecords",
"train009_R2_LE_1.5.tfrecords",
"train010_R2_LE_1.5.tfrecords",
"train011_R2_LE_1.5.tfrecords",
"train012_R2_LE_1.5.tfrecords",
"train013_R2_LE_1.5.tfrecords",
"train014_R2_LE_1.5.tfrecords",
"train015_R2_LE_1.5.tfrecords",
"train016_R2_LE_1.5.tfrecords",
"train017_R2_LE_1.5.tfrecords",
"train018_R2_LE_1.5.tfrecords",
"train019_R2_LE_1.5.tfrecords",
"train020_R2_LE_1.5.tfrecords",
"train021_R2_LE_1.5.tfrecords",
"train022_R2_LE_1.5.tfrecords",
"train023_R2_LE_1.5.tfrecords",
"train024_R2_LE_1.5.tfrecords",
"train025_R2_LE_1.5.tfrecords",
"train026_R2_LE_1.5.tfrecords",
"train027_R2_LE_1.5.tfrecords",
"train028_R2_LE_1.5.tfrecords",
"train029_R2_LE_1.5.tfrecords",
"train030_R2_LE_1.5.tfrecords",
"train031_R2_LE_1.5.tfrecords",
]
files_train_hvar = ["train000_R2_GT_1.5.tfrecords",
"train001_R2_GT_1.5.tfrecords",
"train002_R2_GT_1.5.tfrecords",
"train003_R2_GT_1.5.tfrecords",
"train004_R2_GT_1.5.tfrecords",
"train005_R2_GT_1.5.tfrecords",
"train006_R2_GT_1.5.tfrecords",
"train007_R2_GT_1.5.tfrecords",
"train008_R2_GT_1.5.tfrecords",
"train009_R2_GT_1.5.tfrecords",
"train010_R2_GT_1.5.tfrecords",
"train011_R2_GT_1.5.tfrecords",
"train012_R2_GT_1.5.tfrecords",
"train013_R2_GT_1.5.tfrecords",
"train014_R2_GT_1.5.tfrecords",
"train015_R2_GT_1.5.tfrecords",
"train016_R2_GT_1.5.tfrecords",
"train017_R2_GT_1.5.tfrecords",
"train018_R2_GT_1.5.tfrecords",
"train019_R2_GT_1.5.tfrecords",
"train020_R2_GT_1.5.tfrecords",
"train021_R2_GT_1.5.tfrecords",
"train022_R2_GT_1.5.tfrecords",
"train023_R2_GT_1.5.tfrecords",
"train024_R2_GT_1.5.tfrecords",
"train025_R2_GT_1.5.tfrecords",
"train026_R2_GT_1.5.tfrecords",
"train027_R2_GT_1.5.tfrecords",
"train028_R2_GT_1.5.tfrecords",
"train029_R2_GT_1.5.tfrecords",
"train030_R2_GT_1.5.tfrecords",
"train031_R2_GT_1.5.tfrecords",
]
files_train_lvar1 = ["train000_R2_LE_1.5.tfrecords",
"train001_R2_LE_1.5.tfrecords",
"train002_R2_LE_1.5.tfrecords",
"train003_R2_LE_1.5.tfrecords",
"train004_R2_LE_1.5.tfrecords",
"train005_R2_LE_1.5.tfrecords",
"train006_R2_LE_1.5.tfrecords",
"train007_R2_LE_1.5.tfrecords",
"train008_R2_LE_1.5.tfrecords",
"train009_R2_LE_1.5.tfrecords",
"train010_R2_LE_1.5.tfrecords",
"train011_R2_LE_1.5.tfrecords",
"train012_R2_LE_1.5.tfrecords",
"train013_R2_LE_1.5.tfrecords",
"train014_R2_LE_1.5.tfrecords",
"train015_R2_LE_1.5.tfrecords",
"train016_R2_LE_1.5.tfrecords",
"train017_R2_LE_1.5.tfrecords",
"train018_R2_LE_1.5.tfrecords",
"train019_R2_LE_1.5.tfrecords",
"train020_R2_LE_1.5.tfrecords",
"train021_R2_LE_1.5.tfrecords",
"train022_R2_LE_1.5.tfrecords",
"train023_R2_LE_1.5.tfrecords",
]
files_train_hvar1 = ["train000_R2_GT_1.5.tfrecords",
"train001_R2_GT_1.5.tfrecords",
"train002_R2_GT_1.5.tfrecords",
"train003_R2_GT_1.5.tfrecords",
"train004_R2_GT_1.5.tfrecords",
"train005_R2_GT_1.5.tfrecords",
"train006_R2_GT_1.5.tfrecords",
"train007_R2_GT_1.5.tfrecords",
"train008_R2_GT_1.5.tfrecords",
"train009_R2_GT_1.5.tfrecords",
"train010_R2_GT_1.5.tfrecords",
"train011_R2_GT_1.5.tfrecords",
"train012_R2_GT_1.5.tfrecords",
"train013_R2_GT_1.5.tfrecords",
"train014_R2_GT_1.5.tfrecords",
"train015_R2_GT_1.5.tfrecords",
"train016_R2_GT_1.5.tfrecords",
"train017_R2_GT_1.5.tfrecords",
"train018_R2_GT_1.5.tfrecords",
"train019_R2_GT_1.5.tfrecords",
"train020_R2_GT_1.5.tfrecords",
"train021_R2_GT_1.5.tfrecords",
"train022_R2_GT_1.5.tfrecords",
"train023_R2_GT_1.5.tfrecords",
]
"""
Try again - all hvar training, train than different hvar testing.
tensorboard --logdir="attic/nn_ds_neibs6_graph0-0RNS-bothtrain-test-hvar" --port=7069
Seems that even different (but used) hvar perfectly match each other, but training for both lvar and hvar never get
match for either of hvar/lvar, even those that were used for training
tensorboard --logdir="attic/nn_ds_neibs6_graph0-0RNS-19-tested_with_same_hvar_lvar_as_trained" --port=7070
try same with higher LR - will they eventually converge?
Compare with other (not used) train sets (use 7 of each instead of 8, 8-th as test)
"""
#just testing:
#files_train_lvar = files_train_hvar
files_test_lvar = ["train004_R2_GT_1.5.tfrecords"]# ["train007_R2_LE_1.5.tfrecords"]# "testTEST_R2_LE_1.5.tfrecords"] # testTEST_R2_LE_1.5.tfrecords"]
files_test_hvar = ["testTEST_R2_GT_1.5.tfrecords"] # Now same size as train! # ["train000_R2_GT_1.5.tfrecords"]#"testTEST_R2_GT_1.5.tfrecords"] # "testTEST_R2_GT_1.5.tfrecords"]
#files_img = ['1527257933_150165-v04'] # overlook
#files_img = ['1527256858_150165-v01'] # State Street
#files_img = ['1527256816_150165-v02'] # State Street
#files_img = ['1527182802_096892-v02'] # plane near
files_img = ['1527182805_096892-v02'] # plane midrange
#files_img = ['1527182810_096892-v02'] # plane far
#MAX_FILES_PER_GROUP
for i, path in enumerate(files_train_lvar):
files_train_lvar[i]=os.path.join(dir_train_lvar, path)
for i, path in enumerate(files_train_hvar):
files_train_hvar[i]=os.path.join(dir_train_hvar, path)
# Second set of files
for i, path in enumerate(files_train_lvar1):
files_train_lvar1[i]=os.path.join(dir_train_lvar1, path)
for i, path in enumerate(files_train_hvar1):
files_train_hvar1[i]=os.path.join(dir_train_hvar1, path)
for i, path in enumerate(files_test_lvar):
files_test_lvar[i]=os.path.join(dir_test_lvar, path)
for i, path in enumerate(files_test_hvar):
files_test_hvar[i]=os.path.join(dir_test_hvar, path)
result_files=[]
for i, path in enumerate(files_img):
files_img[i] = os.path.join(dir_img, path+'.tfrecords')
result_files.append(os.path.join(dir_result, path+"_"+SUFFIX+'.npy'))
files_train = [files_train_lvar,files_train_hvar,files_train_lvar1,files_train_hvar1]
#file_test_hvar= None
weight_hvar = 0.26
weight_lvar = 1.0 - weight_hvar
partials = None
partials = concentricSquares(CLUSTER_RADIUS)
PARTIALS_WEIGHTS = [1.0*pw/sum(PARTIALS_WEIGHTS) for pw in PARTIALS_WEIGHTS]
if not USE_PARTIALS:
partials = partials[0:1]
PARTIALS_WEIGHTS = [1.0]
import tensorflow as tf
import tensorflow.contrib.slim as slim
for result_file in result_files:
try:
eval_results(result_file, ABSOLUTE_DISPARITY,radius=CLUSTER_RADIUS)
#exit(0)
except:
pass
datasets_img = []
for fpath in files_img:
print_time("Importing test image data from "+fpath, end="")
corr2d, target_disparity, gt_ds = readTFRewcordsEpoch(fpath)
datasets_img.append( {"corr2d": corr2d,
"target_disparity": target_disparity,
"gt_ds": gt_ds})
print_time(" Done")
gtruth = datasets_img[0]['gt_ds'].copy()
t_disp = datasets_img[0]['target_disparity'].reshape([-1,1]).copy()
extend_img_to_clusters(datasets_img, radius = CLUSTER_RADIUS)
#reformat_to_clusters(datasets_img) already this format
replace_nan(datasets_img)
pass
pass
datasets_train_lvar = []
datasets_train_hvar = []
datasets_train_lvar1 = []
datasets_train_hvar1 = []
datasets_train_all = [[],[],[],[]]
#files_train = [files_train_lvar,files_train_hvar,files_train_lvar1,files_train_hvar1]
for n_train, f_train in enumerate(files_train):
if len(f_train) and ((n_train<2) or TWO_TRAINS):
_setFileSlot(train_next[n_train], len(f_train))
for i, fpath in enumerate(f_train):
if i >= MAX_FILES_PER_GROUP:
break
print_time("Importing train data "+(["low variance","high variance", "low variance1","high variance1"][n_train]) +" from "+fpath, end="")
corr2d, target_disparity, gt_ds = readTFRewcordsEpoch(fpath)
datasets_train_all[n_train].append({"corr2d":corr2d,
"target_disparity":target_disparity,
"gt_ds":gt_ds})
_nextFileSlot(train_next[n_train])
print_time(" Done")
datasets_test_lvar = []
for fpath in files_test_lvar:
print_time("Importing test data (low variance) from "+fpath, end="")
corr2d, target_disparity, gt_ds = readTFRewcordsEpoch(fpath)
datasets_test_lvar.append({"corr2d":corr2d,
"target_disparity":target_disparity,
"gt_ds":gt_ds})
print_time(" Done")
datasets_test_hvar = []
for fpath in files_test_hvar:
print_time("Importing test data (high variance) from "+fpath, end="")
corr2d, target_disparity, gt_ds = readTFRewcordsEpoch(fpath)
datasets_test_hvar.append({"corr2d":corr2d,
"target_disparity":target_disparity,
"gt_ds":gt_ds})
print_time(" Done")
#CLUSTER_RADIUS
cluster_size = (2 * CLUSTER_RADIUS + 1) * (2 * CLUSTER_RADIUS + 1)
center_tile_index = 2 * CLUSTER_RADIUS * (CLUSTER_RADIUS + 1)
# Reformat input data
if FILE_TILE_SIDE > TILE_SIDE:
print_time("Reducing correlation tile size from %d to %d"%(FILE_TILE_SIDE, TILE_SIDE), end="")
for d_train in datasets_train_all:
reduce_tile_size(d_train, TILE_LAYERS, TILE_SIDE)
reduce_tile_size(datasets_test_lvar, TILE_LAYERS, TILE_SIDE)
reduce_tile_size(datasets_test_hvar, TILE_LAYERS, TILE_SIDE)
print_time(" Done")
pass
# Reformat to 1/9/25 tile clusters
for n_train, d_train in enumerate(datasets_train_all):
print_time("Reshaping train data ("+(["low variance","high variance", "low variance1","high variance1"][n_train])+") ", end="")
reformat_to_clusters(d_train)
print_time(" Done")
print_time("Reshaping test data (low variance)", end="")
reformat_to_clusters(datasets_test_lvar)
print_time(" Done")
print_time("Reshaping test data (high variance)", end="")
reformat_to_clusters(datasets_test_hvar)
print_time(" Done")
pass
"""
datasets_train_lvar & datasets_train_hvar ( that will increase batch size and placeholders twice
test has to have even original, batches will not zip - just use two batches for one big one
"""
if ZIP_LHVAR:
print_time("Zipping together datasets datasets_train_lvar and datasets_train_hvar", end="")
datasets_train = zip_lvar_hvar(datasets_train_all, del_src = True) # no shuffle, delete src
print_time(" Done")
else:
#Alternate lvar/hvar
datasets_train = []
datasets_weights_train = []
for indx in range(max(len(datasets_train_lvar),len(datasets_train_hvar))):
if (indx < len(datasets_train_lvar)):
datasets_train.append(datasets_train_lvar[indx])
datasets_weights_train.append(weight_lvar)
if (indx < len(datasets_train_hvar)):
datasets_train.append(datasets_train_hvar[indx])
datasets_weights_train.append(weight_hvar)
datasets_test = []
datasets_weights_test = []
for dataset_test_lvar in datasets_test_lvar:
datasets_test.append(dataset_test_lvar)
datasets_weights_test.append(weight_lvar)
for dataset_test_hvar in datasets_test_hvar:
datasets_test.append(dataset_test_hvar)
datasets_weights_test.append(weight_hvar)
corr2d_train_placeholder = tf.placeholder(datasets_train[0]['corr2d'].dtype, (None,FEATURES_PER_TILE * cluster_size)) # corr2d_train.shape)
target_disparity_train_placeholder = tf.placeholder(datasets_train[0]['target_disparity'].dtype, (None,1 * cluster_size)) #target_disparity_train.shape)
gt_ds_train_placeholder = tf.placeholder(datasets_train[0]['gt_ds'].dtype, (None,2 * cluster_size)) #gt_ds_train.shape)
#dataset_tt TensorSliceDataset: <TensorSliceDataset shapes: {gt_ds: (50,), corr2d: (8100,), target_disparity: (25,)}, types: {gt_ds: tf.float32, corr2d: tf.float32, target_disparity: tf.float32}>
dataset_tt = tf.data.Dataset.from_tensor_slices({
"corr2d":corr2d_train_placeholder,
"target_disparity": target_disparity_train_placeholder,
"gt_ds": gt_ds_train_placeholder})
#dataset_train_size = len(corr2d_train)
#dataset_train_size = len(datasets_train_lvar[0]['corr2d'])
dataset_train_size = len(datasets_train[0]['corr2d'])
dataset_train_size //= BATCH_SIZE
dataset_test_size = len(datasets_test_lvar[0]['corr2d'])
dataset_test_size //= BATCH_SIZE
dataset_img_size = len(datasets_img[0]['corr2d'])
dataset_img_size //= BATCH_SIZE
#print_time("dataset_tt.output_types "+str(dataset_train.output_types)+", dataset_train.output_shapes "+str(dataset_train.output_shapes)+", number of elements="+str(dataset_train_size))
dataset_tt = dataset_tt.batch(BATCH_SIZE)
dataset_tt = dataset_tt.prefetch(BATCH_SIZE)
iterator_tt = dataset_tt.make_initializable_iterator()
next_element_tt = iterator_tt.get_next()
#print("dataset_tt.output_types "+str(dataset_tt.output_types)+", dataset_tt.output_shapes "+str(dataset_tt.output_shapes)+", number of elements="+str(dataset_train_size))
#BatchDataset: <BatchDataset shapes: {gt_ds: (?, 50), corr2d: (?, 8100), target_disparity: (?, 25)}, types: {gt_ds: tf.float32, corr2d: tf.float32, target_disparity: tf.float32}>
"""
next_element_tt dict: {'gt_ds': <tf.Tensor 'IteratorGetNext:1' shape=(?, 50) dtype=float32>, 'corr2d': <tf.Tensor 'IteratorGetNext:0' shape=(?, 8100) dtype=float32>, 'target_disparity': <tf.Tensor 'IteratorGetNext:2' shape=(?, 25) dtype=float32>}
'corr2d' (140405473715624) Tensor: Tensor("IteratorGetNext:0", shape=(?, 8100), dtype=float32)
'gt_ds' (140405473715680) Tensor: Tensor("IteratorGetNext:1", shape=(?, 50), dtype=float32)
'target_disparity' (140405501995888) Tensor: Tensor("IteratorGetNext:2", shape=(?, 25), dtype=float32)
"""
#https://www.tensorflow.org/versions/r1.5/programmers_guide/datasets
result_dir = './attic/result_neibs_'+ SUFFIX+'/'
checkpoint_dir = './attic/result_neibs_'+ SUFFIX+'/'
save_freq = 500
def lrelu(x):
return tf.maximum(x*0.2,x)
# return tf.nn.relu(x)
def sym_inputs8(inp):
"""
get input vector [?:4*9*9+1] (last being target_disparity) and reorder for horizontal flip,
vertical flip and transpose (8 variants, mode + 1 - hor, +2 - vert, +4 - transpose)
return same lengh, reordered
"""
with tf.name_scope("sym_inputs8"):
td = inp[:,-1:] # tf.reshape(inp,[-1], name = "td")[-1]
inp_corr = tf.reshape(inp[:,:-1],[-1,4,TILE_SIDE,TILE_SIDE], name = "inp_corr")
inp_corr_h = tf.stack([-inp_corr [:,0,:,-1::-1], inp_corr [:,1,:,-1::-1], -inp_corr [:,3,:,-1::-1], -inp_corr [:,2,:,-1::-1]], axis=1, name = "inp_corr_h")
inp_corr_v = tf.stack([ inp_corr [:,0,-1::-1,:],-inp_corr [:,1,-1::-1,:], inp_corr [:,3,-1::-1,:], inp_corr [:,2,-1::-1,:]], axis=1, name = "inp_corr_v")
inp_corr_hv = tf.stack([ inp_corr_h[:,0,-1::-1,:],-inp_corr_h[:,1,-1::-1,:], inp_corr_h[:,3,-1::-1,:], inp_corr_h[:,2,-1::-1,:]], axis=1, name = "inp_corr_hv")
inp_corr_t = tf.stack([tf.transpose(inp_corr [:,1], perm=[0,2,1]),
tf.transpose(inp_corr [:,0], perm=[0,2,1]),
tf.transpose(inp_corr [:,2], perm=[0,2,1]),
-tf.transpose(inp_corr [:,3], perm=[0,2,1])], axis=1, name = "inp_corr_t")
inp_corr_ht = tf.stack([tf.transpose(inp_corr_h [:,1], perm=[0,2,1]),
tf.transpose(inp_corr_h [:,0], perm=[0,2,1]),
tf.transpose(inp_corr_h [:,2], perm=[0,2,1]),
-tf.transpose(inp_corr_h [:,3], perm=[0,2,1])], axis=1, name = "inp_corr_ht")
inp_corr_vt = tf.stack([tf.transpose(inp_corr_v [:,1], perm=[0,2,1]),
tf.transpose(inp_corr_v [:,0], perm=[0,2,1]),
tf.transpose(inp_corr_v [:,2], perm=[0,2,1]),
-tf.transpose(inp_corr_v [:,3], perm=[0,2,1])], axis=1, name = "inp_corr_vt")
inp_corr_hvt = tf.stack([tf.transpose(inp_corr_hv[:,1], perm=[0,2,1]),
tf.transpose(inp_corr_hv[:,0], perm=[0,2,1]),
tf.transpose(inp_corr_hv[:,2], perm=[0,2,1]),
-tf.transpose(inp_corr_hv[:,3], perm=[0,2,1])], axis=1, name = "inp_corr_hvt")
# return td, [inp_corr, inp_corr_h, inp_corr_v, inp_corr_hv, inp_corr_t, inp_corr_ht, inp_corr_vt, inp_corr_hvt]
"""
return [tf.concat([tf.reshape(inp_corr, [inp_corr.shape[0],-1]),td], axis=1,name = "out_corr"),
tf.concat([tf.reshape(inp_corr_h, [inp_corr.shape[0],-1]),td], axis=1,name = "out_corr_h"),
tf.concat([tf.reshape(inp_corr_v, [inp_corr.shape[0],-1]),td], axis=1,name = "out_corr_v"),
tf.concat([tf.reshape(inp_corr_hv, [inp_corr.shape[0],-1]),td], axis=1,name = "out_corr_hv"),
tf.concat([tf.reshape(inp_corr_t, [inp_corr.shape[0],-1]),td], axis=1,name = "out_corr_t"),
tf.concat([tf.reshape(inp_corr_ht, [inp_corr.shape[0],-1]),td], axis=1,name = "out_corr_ht"),
tf.concat([tf.reshape(inp_corr_vt, [inp_corr.shape[0],-1]),td], axis=1,name = "out_corr_vt"),
tf.concat([tf.reshape(inp_corr_hvt,[inp_corr.shape[0],-1]),td], axis=1,name = "out_corr_hvt")]
"""
cl = 4 * TILE_SIDE * TILE_SIDE
return [tf.concat([tf.reshape(inp_corr, [-1,cl]),td], axis=1,name = "out_corr"),
tf.concat([tf.reshape(inp_corr_h, [-1,cl]),td], axis=1,name = "out_corr_h"),
tf.concat([tf.reshape(inp_corr_v, [-1,cl]),td], axis=1,name = "out_corr_v"),
tf.concat([tf.reshape(inp_corr_hv, [-1,cl]),td], axis=1,name = "out_corr_hv"),
tf.concat([tf.reshape(inp_corr_t, [-1,cl]),td], axis=1,name = "out_corr_t"),
tf.concat([tf.reshape(inp_corr_ht, [-1,cl]),td], axis=1,name = "out_corr_ht"),
tf.concat([tf.reshape(inp_corr_vt, [-1,cl]),td], axis=1,name = "out_corr_vt"),
tf.concat([tf.reshape(inp_corr_hvt,[-1,cl]),td], axis=1,name = "out_corr_hvt")]
# inp_corr_h, inp_corr_v, inp_corr_hv, inp_corr_t, inp_corr_ht, inp_corr_vt, inp_corr_hvt]
def network_sub(input, layout, reuse, sym8 = False):
last_indx = None;
fc = []
inp_weights = []
for i, num_outs in enumerate (layout):
if num_outs:
if fc:
inp = fc[-1]
fc.append(slim.fully_connected(inp, num_outs, activation_fn=lrelu, scope='g_fc_sub'+str(i), reuse = reuse))
else:
inp = input
if sym8:
inp8 = sym_inputs8(inp)
num_non_sum = num_outs % len(inp8) # if number of first layer outputs is not multiple of 8
num_sym8 = num_outs // len(inp8) # number of symmetrical groups
fc_sym = []
for j in range (len(inp8)): # ==8
reuse_this = reuse | (j > 0)
scp = 'g_fc_sub'+str(i)
fc_sym.append(slim.fully_connected(inp8[j], num_sym8, activation_fn=lrelu, scope= scp, reuse = reuse_this))
if not reuse_this:
with tf.variable_scope(scp,reuse=True) : # tf.AUTO_REUSE):
inp_weights.append(tf.get_variable('weights')) # ,shape=[inp.shape[1],num_outs]))
if num_non_sum > 0:
reuse_this = reuse
scp = 'g_fc_sub'+str(i)+"r"
fc_sym.append(slim.fully_connected(inp, num_non_sum, activation_fn=lrelu, scope=scp, reuse = reuse_this))
if not reuse_this:
with tf.variable_scope(scp,reuse=True) : # tf.AUTO_REUSE):
inp_weights.append(tf.get_variable('weights')) # ,shape=[inp.shape[1],num_outs]))
fc.append(tf.concat(fc_sym, 1, name='sym_input_layer'))
else:
scp = 'g_fc_sub'+str(i)
fc.append(slim.fully_connected(inp, num_outs, activation_fn=lrelu, scope= scp, reuse = reuse))
if not reuse:
with tf.variable_scope(scp, reuse=True) : # tf.AUTO_REUSE):
inp_weights.append(tf.get_variable('weights')) # ,shape=[inp.shape[1],num_outs]))
return fc[-1], inp_weights
def network_inter(input, layout, reuse=False):
last_indx = None;
fc = []
for i, num_outs in enumerate (layout):
if num_outs:
if fc:
inp = fc[-1]
else:
inp = input
fc.append(slim.fully_connected(inp, num_outs, activation_fn=lrelu, scope='g_fc_inter'+str(i), reuse = reuse))
if USE_CONFIDENCE:
fc_out = slim.fully_connected(fc[-1], 2, activation_fn=lrelu, scope='g_fc_inter_out', reuse = reuse)
else:
fc_out = slim.fully_connected(fc[-1], 1, activation_fn=None, scope='g_fc_inter_out', reuse = reuse)
#If using residual disparity, split last layer into 2 or remove activation and add rectifier to confidence only
return fc_out
def networks_siam(input, # now [?,9,325]-> [?,25,325]
layout1,
layout2,
sym8 = False,
only_tile = None, # just for debugging - feed only data from the center sub-network
partials = None):
with tf.name_scope("Siam_net"):
inp_weights = []
num_legs = input.shape[1] # == 25
if partials is None:
partials = [[True] * num_legs]
# inter_list = []
inter_lists = [[] for _ in partials]
reuse = False
for i in range (num_legs):
if ((only_tile is None) or (i == only_tile)) and any([p[i] for p in partials]) :
ns, ns_weights = network_sub(input[:,i,:],
layout= layout1,
reuse= reuse,
sym8 = sym8)
for n, partial in enumerate(partials):
if partial[i]:
inter_lists[n].append(ns)
else:
# inter_lists[n].append(tf.constant(0.0,dtype=tf.float32, shape=ns.shape))
# inter_lists[n].append(ns * 0.0)
inter_lists[n].append(tf.zeros_like(ns))
# inter_list.append(ns)
inp_weights += ns_weights
reuse = True
outs = []
for n, _ in enumerate(partials):
# outs.append(network_inter (tf.concat(inter_list, 1, name='inter_tensor'+str(n)), layout2, reuse = (n > 0)))
outs.append(network_inter (tf.concat(inter_lists[n], 1, name='inter_tensor'+str(n)), layout2, reuse = (n > 0)))
# inter_tensors.append(tf.concat(inter_list, 1, name='inter_tensor'+str(n)))
# inter_tensor = tf.concat(inter_list, 1, name='inter_tensor')
# return network_inter (inter_tensor, layout2), inp_weights
return outs, inp_weights
def debug_gt_variance(
indx, # This tile index (0..8)
center_indx, # center tile index
gt_ds_batch # [?:9:2]
):
with tf.name_scope("Debug_GT_Variance"):
tf_num_tiles = tf.shape(gt_ds_batch)[0]
d_gt_this = tf.reshape(gt_ds_batch[:,2 * indx],[-1], name = "d_this")
d_gt_center = tf.reshape(gt_ds_batch[:,2 * center_indx],[-1], name = "d_center")
d_gt_diff = tf.subtract(d_gt_this, d_gt_center, name = "d_diff")
d_gt_diff2 = tf.multiply(d_gt_diff, d_gt_diff, name = "d_diff2")
d_gt_var = tf.reduce_mean(d_gt_diff2, name = "d_gt_var")
return d_gt_var
def batchLoss(out_batch, # [batch_size,(1..2)] tf_result
target_disparity_batch, # [batch_size] tf placeholder
gt_ds_batch, # [batch_size,2] tf placeholder
absolute_disparity = True, #when false there should be no activation on disparity output !
use_confidence = True,
lambda_conf_avg = 0.01,
lambda_conf_pwr = 0.1,
conf_pwr = 2.0,
gt_conf_offset = 0.08,
gt_conf_pwr = 1.0,
error2_offset = 0.0025, # 0.0, # 0.0025, # (0.05^2) ~= coring
disp_wmin = 1.0, # minimal disparity to apply weight boosting for small disparities
disp_wmax = 8.0, # maximal disparity to apply weight boosting for small disparities
use_out = False): # use calculated disparity for disparity weight boosting (False - use target disparity)
with tf.name_scope("BatchLoss"):
"""
Here confidence should be after relU. Disparity - may be also if absolute, but no activation if output is residual disparity
"""
tf_lambda_conf_avg = tf.constant(lambda_conf_avg, dtype=tf.float32, name="tf_lambda_conf_avg")
tf_lambda_conf_pwr = tf.constant(lambda_conf_pwr, dtype=tf.float32, name="tf_lambda_conf_pwr")
tf_conf_pwr = tf.constant(conf_pwr, dtype=tf.float32, name="tf_conf_pwr")
tf_gt_conf_offset = tf.constant(gt_conf_offset, dtype=tf.float32, name="tf_gt_conf_offset")
tf_gt_conf_pwr = tf.constant(gt_conf_pwr, dtype=tf.float32, name="tf_gt_conf_pwr")
tf_num_tiles = tf.shape(gt_ds_batch)[0]
tf_0f = tf.constant(0.0, dtype=tf.float32, name="tf_0f")
tf_1f = tf.constant(1.0, dtype=tf.float32, name="tf_1f")
tf_maxw = tf.constant(1.0, dtype=tf.float32, name="tf_maxw")
if gt_conf_pwr == 0:
w = tf.ones((out_batch.shape[0]), dtype=tf.float32,name="w_ones")
else:
# w_slice = tf.slice(gt_ds_batch,[0,1],[-1,1], name = "w_gt_slice")
w_slice = tf.reshape(gt_ds_batch[:,1],[-1], name = "w_gt_slice")
w_sub = tf.subtract (w_slice, tf_gt_conf_offset, name = "w_sub")