-
Notifications
You must be signed in to change notification settings - Fork 0
/
UNSupervised_WNet_clean_version.py
673 lines (592 loc) · 38.1 KB
/
UNSupervised_WNet_clean_version.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
'''
Fully unsupervised version
'''
import gc
import os
import vtk
import argparse
import numpy as np
import pandas as pd
import tensorflow as tf
from tensorflow import keras
from tensorflow.python.framework import graph_util
from utils import fast_batch
from utils import image_preprocessing
from utils import get_batches_fn_random
from utils import centroids_similarity_loss
from utils import tf_crop_or_pad_along_axis
from dataio import read_params
# os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID" # see issue #152
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
print(tf.__version__)
vtk.vtkObject.GlobalWarningDisplayOff()
def parse_args():
"""
Use argparse module. Santize options and return the parser.
:return:
args
"""
parser = argparse.ArgumentParser()
parser.add_argument('-y','--yaml-path',help='Path to the yaml file',required=True)
return parser.parse_args()
def name_tag(name, tag):
'''
Create a name tag. Return None if tag or name is None.
This allows tensorflow to create a name if you don't provide one
'''
return None if tag is None or name is None else '{}_{}'.format(tag,name)
class WNetTensorflow(object):
'''
Fully unsupervised semantic segmentation following https://arxiv.org/pdf/1711.08506.pdf
separable convolutions https://towardsdatascience.com/types-of-convolutions-in-deep-learning-717013397f4d
'''
def __init__(self, params, variables):
"""
Initializes all necessary components of the TensorFlow
Graph.
"""
# Assign required variables first
self.varsM = variables
'''
https://github.com/mbrufau7/tfm_food_segm/blob/master/W_net_Unsupervised_%26_Centroid_Loss_1_2.ipynb
'''
# INITIALIZE GRAPH
self.graph = tf.Graph()
with self.graph.as_default():
self.n_input_variables = len(self.varsM)
# Placeholders
#self.input_images = tf.placeholder(tf.float32, shape=(None, None,None,None, self.n_input_variables),
# name='input_images')
self.input_images = tf.placeholder(tf.float32, shape=(None, None, self.n_input_variables),name='input_images')
self.z_voxels = tf.placeholder(tf.int32, name='z_voxels')
self.y_voxels = tf.placeholder(tf.int32, name='y_voxels')
self.x_voxels = tf.placeholder(tf.int32, name='x_voxels')
self.phase = tf.placeholder(tf.bool, name='phase')
self.keep_prob = tf.placeholder(tf.float32, name='keep_prob')
params_z_proc = params.image_params.CROP_PAD_IMAGE_Z
params_y_proc = params.image_params.CROP_PAD_IMAGE_Y
params_x_proc = params.image_params.CROP_PAD_IMAGE_X
# shape = tf.shape(self.input_images)
self.org_x = self.x_voxels # shape[3]
self.org_y = self.y_voxels # shape[2]
self.org_z = self.z_voxels # shape[1]
self.input_processed = image_preprocessing(self.input_images,
params_z_proc,
params_y_proc,
params_x_proc,
self.n_input_variables,
self.org_z,
self.org_y,
self.org_x)
# Global step - feed it in so no incrementing necessary
# self.global_step_m = tf.placeholder(tf.int32)
global_step = tf.Variable(0.0, trainable=False)
def shape_so(tensor):
# s = tensor.get_shape()
# return tuple([s[i].value for i in range(0,len(s))])
return tuple([d.value for d in tensor.get_shape()])
def conv_block(inputs, filters, prev_filters, kernel, activation, phase, dil_rate, tag=None):
# @TODO 'channels_last' is default? is this acutally a separable conv
net_2 = tf.layers.conv3d(inputs,
filters,
kernel,
strides=[1, 1, 1],
dilation_rate=dil_rate,
padding='SAME',
activation=activation,
kernel_initializer=keras.initializers.he_normal(),
data_format='channels_last',
name=name_tag('conv3d_1', tag))
# net_2 = tf.layers.max_pooling3d(net_2, pool_size=kernel, strides = [1, 1, 1],
# padding = 'SAME', data_format='channels_last',
# name=name_tag('max_pooling3d', tag))
net_2 = tf.layers.conv3d(net_2,
filters,
kernel,
strides=[1, 1, 1],
dilation_rate=[1, 1, 1],
padding='SAME',
activation=activation,
kernel_initializer=keras.initializers.he_normal(),
data_format='channels_last',
name=name_tag('conv3d_2', tag))
net_2 = tf.layers.max_pooling3d(net_2,
pool_size=kernel,
strides=[2, 2, 2],
padding='SAME',
data_format='channels_last',
name=name_tag('max_pooling3d', tag))
# net_2 = tf.layers.batch_normalization(net_2, center=True, scale=True, training=phase
# ,name=name_tag('batch_norm', tag)
# net_2 = tf.layers.dropout(net_2,rate=0.20, training=phase,
# name=name_tag('dropout', tag))
return net_2
def deconv_block(inputs,filters, prev_filters,kernel,activation, phase, dil_rate,tag=None):
''' @TODO 'channels_last' is default? is this acutally a separable conv.
W-Net : https://arxiv.org/pdf/1711.08506.pdf
U-Net : https://arxiv.org/pdf/1505.04597.pdf
U-ENC for W-Net should be:
depthwise separable conv -> depthwise separable conv -> dconv
One important modification in our architecture is that all of the modules use the depthwise
separable convolution layers introduced in U-Net except modules 1, 9, 10, and 18.
A depthwise separable convolution operation consists of a depthwise convolution and a
pointwise convolution. The idea behind such an operation is to examine spatial
cor-relations and cross-channel correlations independently a depthwise convolution performs
spatial convolutions independently over each channel and then a pointwise convolution projects
the feature channels by the depthwise convolution onto a new channel space. As a consequence,
the network gains performance more efficiently with the same number of parameters.
'''
# net_3 = tf.layers.conv3d(inputs, filters, kernel, strides=[1, 1,1], dilation_rate=[1, 1, 1],
# padding='SAME', activation=activation,
# kernel_initializer=keras.initializers.he_normal() ,
# data_format='channels_last')
net_3 = tf.layers.conv3d_transpose(inputs,
filters,
kernel,
strides=[2, 2, 2],
padding='SAME',
activation=activation,
kernel_initializer=keras.initializers.he_normal(),
data_format='channels_last',
name=name_tag('dconv3d', tag))
# net_3 = tf.layers.max_pooling3d(net_3, pool_size=kernel,
# strides = [1, 1, 1], padding = 'SAME', data_format='channels_last')
net_3 = tf.layers.conv3d(net_3,
filters,
kernel,
strides=[1, 1, 1],
padding='SAME',
activation=activation,
kernel_initializer=keras.initializers.he_normal(),
data_format='channels_last', # @TODO: conv or separable conv?
name=name_tag('conv3d', tag))
net_3 = tf.layers.max_pooling3d(net_3,
pool_size=kernel,
strides=[1, 1, 1],
padding='SAME',
data_format='channels_last',
name=name_tag('max_pooling3d', tag))
# net_3 = tf.layers.batch_normalization(net_3, center=True, scale=True, training=phase)
# net_3 = tf.layers.dropout(net_3,rate=0.20, training=phase)
return net_3
def middle_block(inputs, filters, prev_filters, kernel, activation, phase, tag=None):
net_1 = tf.layers.conv3d(inputs,
filters,
kernel,
strides=[1, 1, 1],
dilation_rate=[1, 1, 1],
padding='SAME',
activation=activation,
kernel_initializer=keras.initializers.lecun_normal(),
data_format='channels_last',
name=name_tag('conv3d_1', tag))
# net_1 = tf.layers.max_pooling3d(net_1, pool_size=kernel,
# strides = [1, 1, 1], padding = 'SAME', data_format='channels_last',
# name=name_tag('max_pooling3d', tag))
net_1 = tf.layers.conv3d(net_1,
filters,
kernel,
strides=[1, 1, 1],
dilation_rate=[1, 1, 1],
padding='SAME',
activation=activation,
kernel_initializer=keras.initializers.he_normal(),
data_format='channels_last',
name=name_tag('conv3d_2', tag))
net_1 = tf.layers.max_pooling3d(net_1,
pool_size=kernel,
strides=[1, 1, 1],
padding='SAME',
name=name_tag('max_pooling3d', tag))
# net_1 = tf.layers.batch_normalization(net_1, center=True, scale=True, training=phase)
# net_1 = tf.layers.dropout(net_1,rate=0.20, training=phase)
return net_1
def middle_block_fc(inputs, filters, prev_filters, kernel, activation, phase, tag=None):
net_1 = tf.layers.conv3d(inputs,
filters,
kernel,
strides=[1, 1, 1],
padding='SAME',
activation=activation,
kernel_initializer=keras.initializers.he_normal(),
name=name_tag('conv3d_1', tag))
net_1 = tf.layers.flatten(net_1)
# @TODO refactor hardcoded dimensions? 6, 12, 6 = 432
net_1 = tf.layers.dense(net_1, 432,
activation=activation,
kernel_initializer=keras.initializers.lecun_normal(),
name=name_tag('fc', tag))
# @TODO refactor hardcoded dimensions? 6, 12, 6 = 432
net_1 = tf.reshape(net_1,
shape=(-1, 6, 12, 6, 1),
name=name_tag('reshape', tag))
net_1 = tf.layers.conv3d(net_1,
prev_filters,
kernel,
strides=[1, 1, 1],
padding='SAME',
activation=activation,
kernel_initializer=keras.initializers.he_normal(),
name=name_tag('conv3d_2', tag))
# net_1 = tf.layers.batch_normalization(net_1, center=True, scale=True, training=phase
# name=name_tag('bn', tag))
# net_1 = tf.layers.dropout(net_1,rate=0.20, training=phase
# name=name_tag('dropout', tag))
return net_1
def wnet(inputs, z, y, x, phase, keep_prob, params, n_input_variables):
# encoder
with tf.name_scope("U-encoder") as scope:
print('inputs {}', shape_so(inputs))
net_e1_1 = conv_block(inputs,
filters=params.graph_params.LAYER_1,
prev_filters=params.graph_params.LAYER_1,
kernel=params.graph_params.KERNEL1,
activation=tf.nn.leaky_relu,
phase=phase,
dil_rate=[1, 1, 1],
tag='uenc_conv_block_1')
print('e1_1 {}', shape_so(net_e1_1))
net_e2_1 = conv_block(net_e1_1,
filters=params.graph_params.LAYER_2,
prev_filters=params.graph_params.LAYER_2,
kernel=params.graph_params.KERNEL1,
activation=tf.nn.leaky_relu,
phase=phase,
dil_rate=[1, 1, 1],
tag='uenc_conv_block_2')
# print('e2_1 {}',shape_so(net_e2_1))
net_e3_1 = conv_block(net_e2_1,
filters=params.graph_params.LAYER_3,
prev_filters=params.graph_params.LAYER_3,
kernel=params.graph_params.KERNEL2,
activation=tf.nn.leaky_relu,
phase=phase,
dil_rate=[1, 1, 1],
tag='uenc_conv_block_3')
print('e3_1 {}', shape_so(net_e3_1))
## middle layer
# inputs,filters,prev_filters,kernel,activation,phase
net_m1_1 = middle_block(net_e3_1,
filters=params.graph_params.LAYER_4,
prev_filters=params.graph_params.LAYER_3,
kernel=params.graph_params.KERNEL2,
activation=tf.nn.leaky_relu,
phase=phase,
tag='uenc_conv_middle_block_4')
print('m1_1 {}',shape_so(net_m1_1))
# net_c3_1 = tf.concat([net_m1_1, net_e3_1], axis=-1)
# inputs,filters,prev_filters,kernel,activation,phase,dil_rate
net_d3_1 = deconv_block(net_m1_1,
filters=params.graph_params.LAYER_3,
prev_filters=params.graph_params.LAYER_2,
kernel=params.graph_params.KERNEL2,
activation=tf.nn.leaky_relu,
phase=phase,
dil_rate=[1, 1, 1],
tag='uenc_dconv_block_5')
# net_c2_1 = tf.concat([net_d3_1, net_e2_1], axis=-1) #
net_d2_1 = deconv_block(net_d3_1,
filters=params.graph_params.LAYER_2,
prev_filters=params.graph_params.LAYER_1,
kernel=params.graph_params.KERNEL1,
activation=tf.nn.leaky_relu,
phase=phase,
dil_rate=[1, 1, 1],
tag='uenc_dconv_block_6')
# net_c1_1 = tf.concat([net_d2_1,net_e1_1], axis=-1) #
net_d1_1 = deconv_block(net_d2_1,
params.graph_params.LAYER_1,
params.graph_params.LAYER_1,
params.graph_params.KERNEL1,
tf.nn.leaky_relu,
phase,
[1, 1, 1],
tag='uenc_dconv_block_7')
# net_d1_1 = tf.layers.batch_normalization(net_d1_1, center=True, scale=True,
# training=phase, momentum=0.90)
# final layer for first U
# net_c0_1 = tf.concat([net_d1_1,net_a], axis=-1)
net_feed = tf.layers.conv3d(net_d1_1,
params.graph_params.N_CLASSES,
params.graph_params.KERNEL2,
dilation_rate=[1, 1, 1],
strides=[1, 1, 1],
padding='SAME',
activation=tf.nn.softmax,
kernel_initializer=keras.initializers.he_normal(),
data_format='channels_last',
name=name_tag('conv3d_final_layer','uenc_conv_block_7'))
# net_feed = tf.nn.softmax(net_feed, axis=4)
# decoder
with tf.name_scope("U-decoder"):
net_d_1 = tf.layers.conv3d(net_feed,params.graph_params.LAYER_1,params.graph_params.KERNEL1,
dilation_rate=[1, 1, 1],
strides=[1, 1, 1],
padding='SAME',
activation=tf.nn.leaky_relu,
name=name_tag('conv3d_first_layer','udec_conv_block_1'))
# inputs,filters,prev_filters,kernel,activation,phase,dil_rate,tag = None
net_de1_1 = conv_block(net_d_1,
filters=params.graph_params.LAYER_1,
prev_filters=params.graph_params.LAYER_1,
kernel=params.graph_params.KERNEL1,
activation=tf.nn.leaky_relu,
phase=phase,
dil_rate=[1, 1, 1],
tag='udec_conv_block_1')
# net_bridge1 = tf.concat([net_de1_1,net_e1_1], axis=-1)
net_de2_1 = conv_block(net_de1_1,
filters=params.graph_params.LAYER_2,
prev_filters=params.graph_params.LAYER_2,
kernel=params.graph_params.KERNEL1,
activation=tf.nn.leaky_relu,
phase=phase,
dil_rate=[1, 1, 1],
tag='udec_conv_block_2')
# net_bridge2 = tf.concat([net_de2_1,net_e2_1], axis=-1)
net_de3_1 = conv_block(net_de2_1,
params.graph_params.LAYER_3,
params.graph_params.LAYER_3,
params.graph_params.KERNEL2,
tf.nn.leaky_relu,
phase,
[1, 1, 1],
tag='udec_conv_block_3')
# net_bridge3 = tf.concat([net_de3_1,net_e3_1], axis=-1)
## middle layer
# net_cA = tf.concat([net_de3_1, net_m1_1], axis=-1)
net_dm1_1 = middle_block(net_de3_1,
params.graph_params.LAYER_4,
params.graph_params.LAYER_3,
params.graph_params.KERNEL2,
tf.nn.leaky_relu,
phase,
tag='udec_conv_middle_block_4')
# net_dc3_1 = tf.concat([net_dm1_1, net_de3_1], axis=-1) # #net_e3_1 , net_m1_1
net_dd3_1 = deconv_block(net_dm1_1,
params.graph_params.LAYER_3,
params.graph_params.LAYER_2,
params.graph_params.KERNEL2,
tf.nn.leaky_relu,
phase,
[1, 1, 1],
tag='udec_dconv_block_5')
# net_dc2_1 = tf.concat([net_dd3_1, net_de2_1], axis=-1) # #net_e2_1, , neprint(total_out[1].get_shape())t_d3_1
net_dd2_1 = deconv_block(net_dd3_1,
params.graph_params.LAYER_2,
params.graph_params.LAYER_1,
params.graph_params.KERNEL1,
tf.nn.leaky_relu,
phase,
[1, 1, 1],
tag='udec_dconv_block_6')
# net_dc1_1 = tf.concat([net_dd2_1,net_de1_1], axis=-1) # #net_e1_1 , net_d2_1
net_dd1_1 = deconv_block(net_dd2_1,
params.graph_params.LAYER_1,
params.graph_params.LAYER_1,
params.graph_params.KERNEL1,
tf.nn.leaky_relu,
phase,
[1, 1, 1],
tag='udec_dconv_block_7')
# net_dd1_1 = tf.layers.batch_normalization(net_dd1_1, center=True, scale=True, training=phase, momentum=0.90)
# final layer for second U
# net_t = tf.concat([net_dd1_1, net_feed], axis=-1)
net_r = tf.layers.conv3d(net_dd1_1,
n_input_variables,
params.graph_params.KERNEL2,
dilation_rate=[1, 1, 1],
strides=[1, 1, 1],
padding='SAME',
activation=tf.nn.leaky_relu,
kernel_initializer=keras.initializers.he_normal(),
name=name_tag('conv3d_final_layer','udec_conv_block_7'))
return net_feed, net_r
# Network
total_out = wnet(self.input_processed,
params.image_params.CROP_PAD_IMAGE_Z,
params.image_params.CROP_PAD_IMAGE_Y,
params.image_params.CROP_PAD_IMAGE_X,
self.phase,
self.keep_prob,
params,
self.n_input_variables)
print(total_out[0].get_shape())
print(total_out[1].get_shape())
wnet_categories = total_out[0]
predictionsOut_1 = tf.argmax(wnet_categories, axis=4)
predictionsOut_1 = tf.expand_dims(predictionsOut_1, axis=4)
predictionsOut_1 = tf.reshape(predictionsOut_1,
shape=(-1,
params.image_params.CROP_PAD_IMAGE_X,
params.image_params.CROP_PAD_IMAGE_Y,
params.image_params.CROP_PAD_IMAGE_Z,
1))
# @TODO is this the how depthwise separable conv is being handled?
predictionsOut_1 = tf.transpose(predictionsOut_1, perm=[0, 3, 2, 1, 4]) # @TODO Parameterize these
predictionsOut_1 = tf_crop_or_pad_along_axis(predictionsOut_1, self.org_z, 1)
predictionsOut_1 = tf_crop_or_pad_along_axis(predictionsOut_1, self.org_y, 2)
predictionsOut_1 = tf_crop_or_pad_along_axis(predictionsOut_1, self.org_x, 3)
# predictionsOut_1 = tf.transpose(predictionsOut_1, perm = [0,3,2,1,4])
predictionsOut_1 = tf.reshape(predictionsOut_1, shape=(-1,
self.org_z,
self.org_y,
self.org_x))
predictionsOut = tf.reshape(tf.cast(predictionsOut_1, tf.int64),
shape=(-1, self.org_x * self.org_y * self.org_z),
name='outputs')
probs = tf.identity(wnet_categories,name='probs') # tf.nn.softmax(wnet_categories, axis=2, name = 'probs')
## decoder - output
wnet_original = tf.identity(total_out[1],name='decoder_outputs')
original_image = tf.identity(self.input_processed,name='encoder_inputs')
unprocessed_image = tf.identity(self.input_images,name='process_inputs')
loss_dec = tf.losses.mean_squared_error(self.input_processed,wnet_original)
print(loss_dec.get_shape())
loss_enc = tf.map_fn(elems=np.arange(params.runtime_params.BATCH_SIZE),
fn=lambda i: centroids_similarity_loss(self.input_processed[i, :, :, :, :],
wnet_categories[i, :, :, :, :],
params.image_params.CROP_PAD_IMAGE_Z,
params.image_params.CROP_PAD_IMAGE_Y,
params.image_params.CROP_PAD_IMAGE_X,
params.graph_params.N_CLASSES,
self.n_input_variables),
dtype=(tf.float32))
print(loss_enc.get_shape())
self.loss_decf = tf.reduce_sum(loss_dec) # + tf.reduce_sum(loss_enc)
self.loss_encf = tf.reduce_sum(loss_enc)
# Training operations
learning_rate = tf.train.cosine_decay_restarts(learning_rate=0.0001,
global_step=global_step,
first_decay_steps=10,
t_mul=2.0,
m_mul=1.0,
alpha=0.01)
trainer = tf.train.AdamOptimizer(learning_rate)
self.saver = tf.train.Saver(max_to_keep=1000)
self.update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(self.update_ops):
# self.training_step_add = trainer.minimize(self.loss_misc)
self.training_step_enc = trainer.minimize(self.loss_encf)
self.training_step_dec = trainer.minimize(self.loss_decf)
## end graph
def trainGraph(self,params,config,datatopulltrain,datatopulltest,variables):
"""
Trains the segmentation
"""
varsM = variables
with tf.Session(graph=self.graph,config=config) as session:
tf.global_variables_initializer().run()
tf.local_variables_initializer().run()
# session.graph.finalize()
# tf.train.start_queue_runners(sess=session, start = True)
result = []
best_test_error_Image = 100000000.0
best_test_error_Cluster = 100000000.0
best_mult = 100.0
counter2 = 1.0
for e in range(1,params.runtime_params.N_EPOCHS + 1):
counter = 0
vtk.vtkObject.GlobalWarningDisplayOff()
total_train_loss = 0.0
total_test_loss = 0.0
total_batch = params.runtime_params.NUM_ITERATIONS
for i in range(1,params.runtime_params.NUM_ITERATIONS):
train_x = get_batches_fn_random(params.runtime_params.BATCH_SIZE,
datatopulltrain,
params,
varsM,
i,
'Train')
op2,train_loss = session.run([self.training_step_dec,self.loss_decf],
feed_dict={self.input_images: train_x,
self.phase: True,
self.keep_prob: 1.0,
self.x_voxels: 52,
self.y_voxels: 336,
self.z_voxels: 65})
test_x = get_batches_fn_random(params.runtime_params.BATCH_SIZE,
datatopulltest,
params,
varsM,
i,
'Test')
test_loss = session.run(self.loss_encf, feed_dict={self.input_images: test_x,
self.phase: False,
self.keep_prob: 1.0,
self.x_voxels: 52,
self.y_voxels: 336,
self.z_voxels: 65})
total_train_loss += train_loss
if (i % 10 == 0):
counter+=1
total_test_loss += test_loss
op3 = session.run([self.training_step_enc],
feed_dict={self.input_images: train_x,
self.phase: True,
self.keep_prob: 1.0,
self.x_voxels: 52,
self.y_voxels: 336,
self.z_voxels: 65})
print('batch {} - Train loss: {} -Test loss: {}'.format(i, np.round(total_train_loss/np.float(i),3), np.round(total_test_loss/np.float(counter),3)))
if (i % 30 == 0):
self.saver.save(session, params.runtime_params.MODEL_PATH + '_epoch_' + str(e) + '_batch_' + str(i))
tf.train.write_graph(session.graph_def, '.',params.runtime_params.MODEL_PATH + '_epoch_' + str(e) + '_batch_' + str(i) + '.pb', False)
result.append([e, i, np.round(total_train_loss / np.float(i), 3), np.round(total_test_loss / np.float(counter), 3)])
np.savetxt(params.runtime_params.MODEL_PATH + '_test.csv', result, delimiter=',')
mult = np.round(total_test_loss / np.float(counter), 3) * np.round(total_train_loss / np.float(i), 3)
if (mult < best_mult): # (np.round(total_test_loss/np.float(counter),3)<best_test_error_Cluster and total_train_loss/np.float(i) <= best_test_error_Image ):
best_test_error_Cluster = np.round(total_test_loss / np.float(counter), 3)
best_test_error_Image = total_train_loss / np.float(i)
best_mult = best_test_error_Cluster * best_test_error_Image
print (best_test_error_Cluster)
self.saver.save(session, params.runtime_params.MODEL_PATH + 'bestModel')
tf.train.write_graph(session.graph_def, '.', params.runtime_params.MODEL_PATH + 'bestModel' + '.pb', False)
# del train_x, test_x, train_loss, #op2#, op3
gc.collect()
counter2+=1
print('Epoch {} -Train loss: {} -Test loss: {}'.format(e,np.round(total_train_loss / np.float(i),3), np.round(test_loss / np.float(counter2), 3)))
result.append([e, i, np.round(total_train_loss / np.float(i), 3), np.round(total_test_loss / np.float(counter2), 3)])
np.savetxt(params.runtime_params.MODEL_PATH + 'test.csv', result, delimiter=',')
gc.collect()
############### main function #####################
def main(yaml_path):
params = read_params(yaml_path)
datatopull = pd.read_csv('MergedListCleanNFS.csv')
datatopull = datatopull.apply(np.random.permutation,axis=0)
print(len(np.unique(datatopull.run)))
train = np.unique(np.random.choice(datatopull.run,size=np.int(len(datatopull.run) * 0.93),replace=False))
print(len(train))
test = np.array(np.setdiff1d(datatopull.run,train))
n_in_train = len(train)
print(len(train))
train = np.random.choice(train,
size=(n_in_train // params.runtime_params.BATCH_SIZE) * params.runtime_params.BATCH_SIZE,
replace=False)
print(len(train))
print(len(datatopull.run))
datatopulltrain = datatopull[datatopull.run.isin(train)]
print(len(datatopulltrain.run))
datatopulltest = datatopull[datatopull.run.isin(test)]
total_batch_train = len(datatopulltrain['run'].values)
total_batch_test = len(datatopulltest['run'].values)
print(total_batch_train)
print(total_batch_test)
params.runtime_params.NUM_ITERATIONS = total_batch_train // params.runtime_params.BATCH_SIZE
print(params.runtime_params.NUM_ITERATIONS)
variables = params.runtime_params.VARIABLES
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.9,allow_growth=True)
config = tf.ConfigProto(intra_op_parallelism_threads=8, # multiprocessing.cpu_count(),
inter_op_parallelism_threads=8, # multiprocessing.cpu_count(),
log_device_placement=True,
gpu_options=gpu_options,
allow_soft_placement=True,
device_count={'GPU': 1,
'CPU': 8}
)
graph = WNetTensorflow(params,variables)
graph.trainGraph(params,config,datatopulltrain,datatopulltest,variables)
return graph
if __name__ == "__main__":
args = parse_args()
print(args)
main(**vars(args))