BrainMapperUNet.py 46.6 KB
Newer Older
1
2
3
4
"""Brain Mapper U-Net Architecture

Description:

5
6
    This folder contains the Pytorch implementation of the core U-net architecture.
    This arcitecture predicts functional connectivity rsfMRI from structural connectivity information from dMRI.
7

8
9
10
11
12
13
Usage:

    To use this module, import it and instantiate is as you wish:

        from BrainMapperUNet import BrainMapperUNet
        deep_learning_model = BrainMapperUnet(parameters)
14
15
16
17
18
19

"""

import numpy as np
import torch
import torch.nn as nn
20
import utils.modules as modules
21

22

23
24
class BrainMapperUNet3D(nn.Module):
    """Architecture class for Traditional BrainMapper 3D U-net.
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

    This class contains the pytorch implementation of the U-net architecture underpinning the BrainMapper project.

    Args:
        parameters (dict): Contains information relevant parameters
        parameters = {
            'kernel_heigth': 5
            'kernel_width': 5
            'kernel_depth': 5
            'kernel_classification': 1
            'input_channels': 1
            'output_channels': 64
            'convolution_stride': 1
            'dropout': 0.2
            'pool_kernel_size': 2
            'pool_stride': 2
            'up_mode': 'upconv'
            'number_of_classes': 1
        }

    Returns:
        probability_map (torch.tensor): Output forward passed tensor through the U-net block
    """

    def __init__(self, parameters):
50
        super(BrainMapperUNet3D, self).__init__()
51
52
53
54

        original_input_channels = parameters['input_channels']
        original_output_channels = parameters['output_channels']

55
        self.encoderBlock1 = modules.EncoderBlock3D(parameters)
56
        parameters['input_channels'] = parameters['output_channels']
57
58
59
60
61
62
63
64
        parameters['output_channels'] = parameters['output_channels'] * 2
        self.encoderBlock2 = modules.EncoderBlock3D(parameters)
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] * 2
        self.encoderBlock3 = modules.EncoderBlock3D(parameters)
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] * 2
        self.encoderBlock4 = modules.EncoderBlock3D(parameters)
65

66
67
68
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] * 2
        self.bottleneck = modules.ConvolutionalBlock3D(parameters)
69

70
71
72
73
74
75
76
77
78
79
80
81
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] // 2
        self.decoderBlock1 = modules.DecoderBlock3D(parameters)
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] // 2
        self.decoderBlock2 = modules.DecoderBlock3D(parameters)
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] // 2
        self.decoderBlock3 = modules.DecoderBlock3D(parameters)
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] // 2
        self.decoderBlock4 = modules.DecoderBlock3D(parameters)
82

83
84
        parameters['input_channels'] = parameters['output_channels']
        self.classifier = modules.ClassifierBlock3D(parameters)
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

        parameters['input_channels'] = original_input_channels
        parameters['output_channels'] = original_output_channels

    def forward(self, X):
        """Forward pass for 3D U-net

        Function computing the forward pass through the 3D U-Net
        The input to the function is the dMRI map

        Args:
            X (torch.tensor): Input dMRI map, shape = (N x C x D x H x W) 

        Returns:
            probability_map (torch.tensor): Output forward passed tensor through the U-net block
        """

        Y_encoder_1, Y_np1, _ = self.encoderBlock1.forward(X)
        Y_encoder_2, Y_np2, _ = self.encoderBlock2.forward(
            Y_encoder_1)

        del Y_encoder_1

        Y_encoder_3, Y_np3, _ = self.encoderBlock3.forward(
            Y_encoder_2)

        del Y_encoder_2

        Y_encoder_4, Y_np4, _ = self.encoderBlock4.forward(
            Y_encoder_3)

        del Y_encoder_3

        Y_bottleNeck = self.bottleneck.forward(Y_encoder_4)

        del Y_encoder_4

        Y_decoder_1 = self.decoderBlock1.forward(
            Y_bottleNeck, Y_np4)

        del Y_bottleNeck, Y_np4

        Y_decoder_2 = self.decoderBlock2.forward(
            Y_decoder_1, Y_np3)

        del Y_decoder_1, Y_np3

        Y_decoder_3 = self.decoderBlock3.forward(
            Y_decoder_2, Y_np2)

        del Y_decoder_2, Y_np2

        Y_decoder_4 = self.decoderBlock4.forward(
            Y_decoder_3, Y_np1)

        del Y_decoder_3, Y_np1

        probability_map = self.classifier.forward(Y_decoder_4)

        del Y_decoder_4

        return probability_map

    def save(self, path):
        """Model Saver

        Function saving the model with all its parameters to a given path.
        The path must end with a *.model argument.

        Args:
            path (str): Path string
        """

        print("Saving Model... {}".format(path))
        torch.save(self, path)

    @property
    def test_if_cuda(self):
        """Cuda Test

        This function tests if the model parameters are allocated to a CUDA enabled GPU.

        Returns:
            bool: Flag indicating True if the tensor is stored on the GPU and Flase otherwhise
        """

        return next(self.parameters()).is_cuda

    def predict(self, X, device=0):
        """Post-training Output Prediction

        This function predicts the output of the of the U-net post-training

        Args:
            X (torch.tensor): input dMRI volume
            device (int/str): Device type used for training (int - GPU id, str- CPU)

        Returns:
            prediction (ndarray): predicted output after training

        """
        self.eval()  # PyToch module setting network to evaluation mode

        if type(X) is np.ndarray:
            X = torch.tensor(X, requires_grad=False).type(torch.FloatTensor)
        elif type(X) is torch.Tensor and not X.is_cuda:
            X = X.type(torch.FloatTensor).cuda(device, non_blocking=True)

        # .cuda() call transfers the densor from the CPU to the GPU if that is the case.
        # Non-blocking argument lets the caller bypas synchronization when necessary

        with torch.no_grad():  # Causes operations to have no gradients
            output = self.forward(X)

        _, idx = torch.max(output, 1)

        # We retrieve the tensor held by idx (.data), and map it to a cpu as an ndarray
        idx = idx.data.cpu().numpy()

        prediction = np.squeeze(idx)

        del X, output, idx

        return prediction

    def reset_parameters(self):
        """Parameter Initialization

        This function (re)initializes the parameters of the defined network.
        This function is a wrapper for the reset_parameters() function defined for each module. 
        More information can be found here: https://discuss.pytorch.org/t/what-is-the-default-initialization-of-a-conv2d-layer-and-linear-layer/16055 + https://discuss.pytorch.org/t/how-to-reset-model-weights-to-effectively-implement-crossvalidation/53859 
        An alternative (re)initialization method is described here: https://discuss.pytorch.org/t/how-to-reset-variables-values-in-nn-modules/32639 
        """

        print("Initializing network parameters...")

        for _, module in self.named_children():
            for _, submodule in module.named_children():
                for _, subsubmodule in submodule.named_children():
                    if isinstance(subsubmodule, (torch.nn.PReLU, torch.nn.Dropout3d, torch.nn.MaxPool3d)) == False:
                        subsubmodule.reset_parameters()

        print("Initialized network parameters!")


230
231
class BrainMapperCompResUNet3D(nn.Module):
    """Architecture class for Competitive Residual DenseBlock BrainMapper 3D U-net.
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

    This class contains the pytorch implementation of the U-net architecture underpinning the BrainMapper project.

    Args:
        parameters (dict): Contains information relevant parameters
        parameters = {
            'kernel_heigth': 5
            'kernel_width': 5
            'kernel_depth': 5
            'kernel_classification': 1
            'input_channels': 1
            'output_channels': 64
            'convolution_stride': 1
            'dropout': 0.2
            'pool_kernel_size': 2
            'pool_stride': 2
            'up_mode': 'upconv'
            'number_of_classes': 1
        }

    Returns:
        probability_map (torch.tensor): Output forward passed tensor through the U-net block
    """

    def __init__(self, parameters):
257
        super(BrainMapperCompResUNet3D, self).__init__()
258
259
260
261

        original_input_channels = parameters['input_channels']
        original_output_channels = parameters['output_channels']

262
        self.encoderBlock1 = modules.InCompDensEncoderBlock3D(parameters)
263
        parameters['input_channels'] = parameters['output_channels']
264
265
266
        self.encoderBlock2 = modules.CompDensEncoderBlock3D(parameters)
        self.encoderBlock3 = modules.CompDensEncoderBlock3D(parameters)
        self.encoderBlock4 = modules.CompDensEncoderBlock3D(parameters)
267

268
        self.bottleneck = modules.CompDensBlock3D(parameters)
269

270
271
272
273
        self.decoderBlock1 = modules.CompDensDecoderBlock3D(parameters)
        self.decoderBlock2 = modules.CompDensDecoderBlock3D(parameters)
        self.decoderBlock3 = modules.CompDensDecoderBlock3D(parameters)
        self.decoderBlock4 = modules.CompDensDecoderBlock3D(parameters)
274

275
        self.classifier = modules.CompDensClassifierBlock3D(parameters)
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

        parameters['input_channels'] = original_input_channels
        parameters['output_channels'] = original_output_channels

    def forward(self, X):
        """Forward pass for 3D U-net

        Function computing the forward pass through the 3D U-Net
        The input to the function is the dMRI map

        Args:
            X (torch.tensor): Input dMRI map, shape = (N x C x D x H x W) 

        Returns:
            probability_map (torch.tensor): Output forward passed tensor through the U-net block
        """

        Y_encoder_1, Y_np1, _ = self.encoderBlock1.forward(X)
        Y_encoder_2, Y_np2, _ = self.encoderBlock2.forward(
            Y_encoder_1)

        del Y_encoder_1

        Y_encoder_3, Y_np3, _ = self.encoderBlock3.forward(
            Y_encoder_2)

        del Y_encoder_2

304
305
        Y_encoder_4, Y_np4, _ = self.encoderBlock4.forward(
            Y_encoder_3)
306
307
308

        del Y_encoder_3

309
310
311
312
        Y_bottleNeck = self.bottleneck.forward(Y_encoder_4)

        del Y_encoder_4

313
        Y_decoder_1 = self.decoderBlock1.forward(
314
            Y_bottleNeck, Y_np4)
315

316
        del Y_bottleNeck, Y_np4
317
318

        Y_decoder_2 = self.decoderBlock2.forward(
319
            Y_decoder_1, Y_np3)
320

321
        del Y_decoder_1, Y_np3
322
323

        Y_decoder_3 = self.decoderBlock3.forward(
324
            Y_decoder_2, Y_np2)
325

326
        del Y_decoder_2, Y_np2
327

328
329
        Y_decoder_4 = self.decoderBlock4.forward(
            Y_decoder_3, Y_np1)
330

331
332
333
334
335
        del Y_decoder_3, Y_np1

        probability_map = self.classifier.forward(Y_decoder_4)

        del Y_decoder_4
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

        return probability_map

    def save(self, path):
        """Model Saver

        Function saving the model with all its parameters to a given path.
        The path must end with a *.model argument.

        Args:
            path (str): Path string
        """

        print("Saving Model... {}".format(path))
        torch.save(self, path)

    @property
    def test_if_cuda(self):
        """Cuda Test

        This function tests if the model parameters are allocated to a CUDA enabled GPU.

        Returns:
            bool: Flag indicating True if the tensor is stored on the GPU and Flase otherwhise
        """

        return next(self.parameters()).is_cuda

    def predict(self, X, device=0):
        """Post-training Output Prediction

        This function predicts the output of the of the U-net post-training

        Args:
            X (torch.tensor): input dMRI volume
            device (int/str): Device type used for training (int - GPU id, str- CPU)

        Returns:
            prediction (ndarray): predicted output after training

        """
        self.eval()  # PyToch module setting network to evaluation mode

        if type(X) is np.ndarray:
            X = torch.tensor(X, requires_grad=False).type(torch.FloatTensor)
        elif type(X) is torch.Tensor and not X.is_cuda:
            X = X.type(torch.FloatTensor).cuda(device, non_blocking=True)

        # .cuda() call transfers the densor from the CPU to the GPU if that is the case.
        # Non-blocking argument lets the caller bypas synchronization when necessary

        with torch.no_grad():  # Causes operations to have no gradients
            output = self.forward(X)

        _, idx = torch.max(output, 1)

        # We retrieve the tensor held by idx (.data), and map it to a cpu as an ndarray
        idx = idx.data.cpu().numpy()

        prediction = np.squeeze(idx)

        del X, output, idx

        return prediction

    def reset_parameters(self):
        """Parameter Initialization

        This function (re)initializes the parameters of the defined network.
        This function is a wrapper for the reset_parameters() function defined for each module. 
        More information can be found here: https://discuss.pytorch.org/t/what-is-the-default-initialization-of-a-conv2d-layer-and-linear-layer/16055 + https://discuss.pytorch.org/t/how-to-reset-model-weights-to-effectively-implement-crossvalidation/53859 
        An alternative (re)initialization method is described here: https://discuss.pytorch.org/t/how-to-reset-variables-values-in-nn-modules/32639 
        """

        print("Initializing network parameters...")

        for _, module in self.named_children():
            for _, submodule in module.named_children():
                for _, subsubmodule in submodule.named_children():
                    if isinstance(subsubmodule, (torch.nn.PReLU, torch.nn.Dropout3d, torch.nn.MaxPool3d)) == False:
                        subsubmodule.reset_parameters()

        print("Initialized network parameters!")


421
class BrainMapperResUNet3Dshallow(nn.Module):
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
    """Architecture class for Residual DenseBlock BrainMapper 3D U-net.

    This class contains the pytorch implementation of the U-net architecture underpinning the BrainMapper project.

    Args:
        parameters (dict): Contains information relevant parameters
        parameters = {
            'kernel_heigth': 5
            'kernel_width': 5
            'kernel_depth': 5
            'kernel_classification': 1
            'input_channels': 1
            'output_channels': 64
            'convolution_stride': 1
            'dropout': 0.2
            'pool_kernel_size': 2
            'pool_stride': 2
            'up_mode': 'upconv'
            'number_of_classes': 1
        }

    Returns:
        probability_map (torch.tensor): Output forward passed tensor through the U-net block
    """

    def __init__(self, parameters):
448
        super(BrainMapperResUNet3Dshallow, self).__init__()
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

        original_input_channels = parameters['input_channels']
        original_output_channels = parameters['output_channels']

        self.encoderBlock1 = modules.DensEncoderBlock3D(parameters)
        parameters['input_channels'] = parameters['output_channels']
        self.encoderBlock2 = modules.DensEncoderBlock3D(parameters)
        self.encoderBlock3 = modules.DensEncoderBlock3D(parameters)

        self.bottleneck = modules.DensBlock3D(parameters)

        parameters['input_channels'] = parameters['output_channels'] * 2
        self.decoderBlock1 = modules.DensDecoderBlock3D(parameters)
        self.decoderBlock2 = modules.DensDecoderBlock3D(parameters)
        self.decoderBlock3 = modules.DensDecoderBlock3D(parameters)

        parameters['input_channels'] = parameters['output_channels']
        self.classifier = modules.DensClassifierBlock3D(parameters)

        parameters['input_channels'] = original_input_channels
        parameters['output_channels'] = original_output_channels

    def forward(self, X):
        """Forward pass for 3D U-net

        Function computing the forward pass through the 3D U-Net
        The input to the function is the dMRI map

        Args:
            X (torch.tensor): Input dMRI map, shape = (N x C x D x H x W) 

        Returns:
            probability_map (torch.tensor): Output forward passed tensor through the U-net block
        """

        Y_encoder_1, Y_np1, _ = self.encoderBlock1.forward(X)
        Y_encoder_2, Y_np2, _ = self.encoderBlock2.forward(
            Y_encoder_1)

        del Y_encoder_1

        Y_encoder_3, Y_np3, _ = self.encoderBlock3.forward(
            Y_encoder_2)

        del Y_encoder_2

495
        Y_bottleNeck = self.bottleneck.forward(Y_encoder_3)
496
497
498
499

        del Y_encoder_3

        Y_decoder_1 = self.decoderBlock1.forward(
500
            Y_bottleNeck, Y_np3)
501

502
        del Y_bottleNeck, Y_np3
503
504

        Y_decoder_2 = self.decoderBlock2.forward(
505
            Y_decoder_1, Y_np2)
506

507
        del Y_decoder_1, Y_np2
508
509

        Y_decoder_3 = self.decoderBlock3.forward(
510
            Y_decoder_2, Y_np1)
511

512
        del Y_decoder_2, Y_np1
513

514
        probability_map = self.classifier.forward(Y_decoder_3)
515

516
        del Y_decoder_3
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

        return probability_map

    def save(self, path):
        """Model Saver

        Function saving the model with all its parameters to a given path.
        The path must end with a *.model argument.

        Args:
            path (str): Path string
        """

        print("Saving Model... {}".format(path))
        torch.save(self, path)

    @property
    def test_if_cuda(self):
        """Cuda Test

        This function tests if the model parameters are allocated to a CUDA enabled GPU.

        Returns:
            bool: Flag indicating True if the tensor is stored on the GPU and Flase otherwhise
        """

        return next(self.parameters()).is_cuda

    def predict(self, X, device=0):
        """Post-training Output Prediction

        This function predicts the output of the of the U-net post-training

        Args:
            X (torch.tensor): input dMRI volume
            device (int/str): Device type used for training (int - GPU id, str- CPU)

        Returns:
            prediction (ndarray): predicted output after training

        """
        self.eval()  # PyToch module setting network to evaluation mode

        if type(X) is np.ndarray:
            X = torch.tensor(X, requires_grad=False).type(torch.FloatTensor)
        elif type(X) is torch.Tensor and not X.is_cuda:
            X = X.type(torch.FloatTensor).cuda(device, non_blocking=True)

        # .cuda() call transfers the densor from the CPU to the GPU if that is the case.
        # Non-blocking argument lets the caller bypas synchronization when necessary

        with torch.no_grad():  # Causes operations to have no gradients
            output = self.forward(X)

        _, idx = torch.max(output, 1)

        # We retrieve the tensor held by idx (.data), and map it to a cpu as an ndarray
        idx = idx.data.cpu().numpy()

        prediction = np.squeeze(idx)

        del X, output, idx

        return prediction

    def reset_parameters(self):
        """Parameter Initialization

        This function (re)initializes the parameters of the defined network.
        This function is a wrapper for the reset_parameters() function defined for each module. 
        More information can be found here: https://discuss.pytorch.org/t/what-is-the-default-initialization-of-a-conv2d-layer-and-linear-layer/16055 + https://discuss.pytorch.org/t/how-to-reset-model-weights-to-effectively-implement-crossvalidation/53859 
        An alternative (re)initialization method is described here: https://discuss.pytorch.org/t/how-to-reset-variables-values-in-nn-modules/32639 
        """

        print("Initializing network parameters...")

        for _, module in self.named_children():
            for _, submodule in module.named_children():
                for _, subsubmodule in submodule.named_children():
                    if isinstance(subsubmodule, (torch.nn.PReLU, torch.nn.Dropout3d, torch.nn.MaxPool3d)) == False:
                        subsubmodule.reset_parameters()

        print("Initialized network parameters!")


602
603
class BrainMapperResUNet3D(nn.Module):
    """Architecture class for Residual DenseBlock BrainMapper 3D U-net.
604
605
606
607
608
609
610
611

    This class contains the pytorch implementation of the U-net architecture underpinning the BrainMapper project.

    Args:
        parameters (dict): Contains information relevant parameters
        parameters = {
            'kernel_heigth': 5
            'kernel_width': 5
612
            'kernel_depth': 5
613
614
615
616
617
618
619
620
621
622
            'kernel_classification': 1
            'input_channels': 1
            'output_channels': 64
            'convolution_stride': 1
            'dropout': 0.2
            'pool_kernel_size': 2
            'pool_stride': 2
            'up_mode': 'upconv'
            'number_of_classes': 1
        }
623

624
625
    Returns:
        probability_map (torch.tensor): Output forward passed tensor through the U-net block
626
    """
627

628
    def __init__(self, parameters):
629
        super(BrainMapperResUNet3D, self).__init__()
630

631
632
        original_input_channels = parameters['input_channels']
        original_output_channels = parameters['output_channels']
633

634
        self.encoderBlock1 = modules.DensEncoderBlock3D(parameters)
635
        parameters['input_channels'] = parameters['output_channels']
636
637
638
        self.encoderBlock2 = modules.DensEncoderBlock3D(parameters)
        self.encoderBlock3 = modules.DensEncoderBlock3D(parameters)
        self.encoderBlock4 = modules.DensEncoderBlock3D(parameters)
639

640
        self.bottleneck = modules.DensBlock3D(parameters)
641

642
643
644
645
646
        parameters['input_channels'] = parameters['output_channels'] * 2
        self.decoderBlock1 = modules.DensDecoderBlock3D(parameters)
        self.decoderBlock2 = modules.DensDecoderBlock3D(parameters)
        self.decoderBlock3 = modules.DensDecoderBlock3D(parameters)
        self.decoderBlock4 = modules.DensDecoderBlock3D(parameters)
647
648

        parameters['input_channels'] = parameters['output_channels']
649
        self.classifier = modules.DensClassifierBlock3D(parameters)
650
651
652

        parameters['input_channels'] = original_input_channels
        parameters['output_channels'] = original_output_channels
653
654

    def forward(self, X):
655
        """Forward pass for 3D U-net
656

657
        Function computing the forward pass through the 3D U-Net
658
659
660
        The input to the function is the dMRI map

        Args:
661
            X (torch.tensor): Input dMRI map, shape = (N x C x D x H x W) 
662
663
664

        Returns:
            probability_map (torch.tensor): Output forward passed tensor through the U-net block
665
        """
666

667
668
        Y_encoder_1, Y_np1, _ = self.encoderBlock1.forward(X)
        Y_encoder_2, Y_np2, _ = self.encoderBlock2.forward(
669
            Y_encoder_1)
670
671
672

        del Y_encoder_1

673
        Y_encoder_3, Y_np3, _ = self.encoderBlock3.forward(
674
            Y_encoder_2)
675
676
677

        del Y_encoder_2

678
        Y_encoder_4, Y_np4, _ = self.encoderBlock4.forward(
679
680
            Y_encoder_3)

681
682
        del Y_encoder_3

683
684
        Y_bottleNeck = self.bottleneck.forward(Y_encoder_4)

685
686
        del Y_encoder_4

687
        Y_decoder_1 = self.decoderBlock1.forward(
688
            Y_bottleNeck, Y_np4)
689

690
        del Y_bottleNeck, Y_np4
691

692
        Y_decoder_2 = self.decoderBlock2.forward(
693
            Y_decoder_1, Y_np3)
694

695
        del Y_decoder_1, Y_np3
696

697
        Y_decoder_3 = self.decoderBlock3.forward(
698
            Y_decoder_2, Y_np2)
699

700
        del Y_decoder_2, Y_np2
701

702
        Y_decoder_4 = self.decoderBlock4.forward(
703
            Y_decoder_3, Y_np1)
704

705
        del Y_decoder_3, Y_np1
706

707
708
        probability_map = self.classifier.forward(Y_decoder_4)

709
710
        del Y_decoder_4

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
        return probability_map

    def save(self, path):
        """Model Saver

        Function saving the model with all its parameters to a given path.
        The path must end with a *.model argument.

        Args:
            path (str): Path string
        """

        print("Saving Model... {}".format(path))
        torch.save(self, path)

    @property
    def test_if_cuda(self):
        """Cuda Test

        This function tests if the model parameters are allocated to a CUDA enabled GPU.

        Returns:
            bool: Flag indicating True if the tensor is stored on the GPU and Flase otherwhise
        """

        return next(self.parameters()).is_cuda

    def predict(self, X, device=0):
        """Post-training Output Prediction

        This function predicts the output of the of the U-net post-training

        Args:
            X (torch.tensor): input dMRI volume
            device (int/str): Device type used for training (int - GPU id, str- CPU)

        Returns:
            prediction (ndarray): predicted output after training

        """
        self.eval()  # PyToch module setting network to evaluation mode

        if type(X) is np.ndarray:
            X = torch.tensor(X, requires_grad=False).type(torch.FloatTensor)
        elif type(X) is torch.Tensor and not X.is_cuda:
            X = X.type(torch.FloatTensor).cuda(device, non_blocking=True)

        # .cuda() call transfers the densor from the CPU to the GPU if that is the case.
        # Non-blocking argument lets the caller bypas synchronization when necessary

        with torch.no_grad():  # Causes operations to have no gradients
            output = self.forward(X)

        _, idx = torch.max(output, 1)

        # We retrieve the tensor held by idx (.data), and map it to a cpu as an ndarray
        idx = idx.data.cpu().numpy()

        prediction = np.squeeze(idx)

        del X, output, idx

        return prediction

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
    def reset_parameters(self):
        """Parameter Initialization

        This function (re)initializes the parameters of the defined network.
        This function is a wrapper for the reset_parameters() function defined for each module. 
        More information can be found here: https://discuss.pytorch.org/t/what-is-the-default-initialization-of-a-conv2d-layer-and-linear-layer/16055 + https://discuss.pytorch.org/t/how-to-reset-model-weights-to-effectively-implement-crossvalidation/53859 
        An alternative (re)initialization method is described here: https://discuss.pytorch.org/t/how-to-reset-variables-values-in-nn-modules/32639 
        """

        print("Initializing network parameters...")

        for _, module in self.named_children():
            for _, submodule in module.named_children():
                for _, subsubmodule in submodule.named_children():
                    if isinstance(subsubmodule, (torch.nn.PReLU, torch.nn.Dropout3d, torch.nn.MaxPool3d)) == False:
                        subsubmodule.reset_parameters()

        print("Initialized network parameters!")


class BrainMapperUNet3Dsimple(nn.Module):
    """Architecture class for  Simple BrainMapper 3D U-net.

    This class contains the pytorch implementation of the U-net architecture underpinning the BrainMapper project.

    Args:
        parameters (dict): Contains information relevant parameters
        parameters = {
            'kernel_heigth': 5
            'kernel_width': 5
            'kernel_depth': 5
            'kernel_classification': 1
            'input_channels': 1
            'output_channels': 64
            'convolution_stride': 1
            'dropout': 0.2
            'pool_kernel_size': 2
            'pool_stride': 2
            'up_mode': 'upconv'
            'number_of_classes': 1
        }

    Returns:
        probability_map (torch.tensor): Output forward passed tensor through the U-net block
    """

    def __init__(self, parameters):
        super(BrainMapperUNet3D, self).__init__()

        original_input_channels = parameters['input_channels']
        original_output_channels = parameters['output_channels']

        self.encoderBlock1 = modules.EncoderBlock3Dsimple(parameters)
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] * 2
        self.encoderBlock2 = modules.EncoderBlock3Dsimple(parameters)
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] * 2
        self.encoderBlock3 = modules.EncoderBlock3Dsimple(parameters)
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] * 2
        self.encoderBlock4 = modules.EncoderBlock3Dsimple(parameters)

        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] * 2
        self.bottleneck = modules.ConvolutionalBlock3Dsimple(parameters)

        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] // 2
        self.decoderBlock1 = modules.DecoderBlock3Dsimple(parameters)
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] // 2
        self.decoderBlock2 = modules.DecoderBlock3Dsimple(parameters)
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] // 2
        self.decoderBlock3 = modules.DecoderBlock3Dsimple(parameters)
        parameters['input_channels'] = parameters['output_channels']
        parameters['output_channels'] = parameters['output_channels'] // 2
        self.decoderBlock4 = modules.DecoderBlock3Dsimple(parameters)

        parameters['input_channels'] = parameters['output_channels']
        self.classifier = modules.ClassifierBlock3Dsimple(parameters)

        parameters['input_channels'] = original_input_channels
        parameters['output_channels'] = original_output_channels

    def forward(self, X):
        """Forward pass for 3D U-net

        Function computing the forward pass through the 3D U-Net
        The input to the function is the dMRI map

        Args:
            X (torch.tensor): Input dMRI map, shape = (N x C x D x H x W) 

        Returns:
            probability_map (torch.tensor): Output forward passed tensor through the U-net block
        """

        Y_encoder_1, Y_np1, _ = self.encoderBlock1.forward(X)
        Y_encoder_2, Y_np2, _ = self.encoderBlock2.forward(
            Y_encoder_1)

        del Y_encoder_1

        Y_encoder_3, Y_np3, _ = self.encoderBlock3.forward(
            Y_encoder_2)

        del Y_encoder_2

        Y_encoder_4, Y_np4, _ = self.encoderBlock4.forward(
            Y_encoder_3)

        del Y_encoder_3

        Y_bottleNeck = self.bottleneck.forward(Y_encoder_4)

        del Y_encoder_4

        Y_decoder_1 = self.decoderBlock1.forward(
            Y_bottleNeck, Y_np4)

        del Y_bottleNeck, Y_np4

        Y_decoder_2 = self.decoderBlock2.forward(
            Y_decoder_1, Y_np3)

        del Y_decoder_1, Y_np3

        Y_decoder_3 = self.decoderBlock3.forward(
            Y_decoder_2, Y_np2)

        del Y_decoder_2, Y_np2

        Y_decoder_4 = self.decoderBlock4.forward(
            Y_decoder_3, Y_np1)

        del Y_decoder_3, Y_np1

        probability_map = self.classifier.forward(Y_decoder_4)

        del Y_decoder_4

        return probability_map

    def save(self, path):
        """Model Saver

        Function saving the model with all its parameters to a given path.
        The path must end with a *.model argument.

        Args:
            path (str): Path string
        """

        print("Saving Model... {}".format(path))
        torch.save(self, path)

    @property
    def test_if_cuda(self):
        """Cuda Test

        This function tests if the model parameters are allocated to a CUDA enabled GPU.

        Returns:
            bool: Flag indicating True if the tensor is stored on the GPU and Flase otherwhise
        """

        return next(self.parameters()).is_cuda

    def predict(self, X, device=0):
        """Post-training Output Prediction

        This function predicts the output of the of the U-net post-training

        Args:
            X (torch.tensor): input dMRI volume
            device (int/str): Device type used for training (int - GPU id, str- CPU)

        Returns:
            prediction (ndarray): predicted output after training

        """
        self.eval()  # PyToch module setting network to evaluation mode

        if type(X) is np.ndarray:
            X = torch.tensor(X, requires_grad=False).type(torch.FloatTensor)
        elif type(X) is torch.Tensor and not X.is_cuda:
            X = X.type(torch.FloatTensor).cuda(device, non_blocking=True)

        # .cuda() call transfers the densor from the CPU to the GPU if that is the case.
        # Non-blocking argument lets the caller bypas synchronization when necessary

        with torch.no_grad():  # Causes operations to have no gradients
            output = self.forward(X)

        _, idx = torch.max(output, 1)

        # We retrieve the tensor held by idx (.data), and map it to a cpu as an ndarray
        idx = idx.data.cpu().numpy()

        prediction = np.squeeze(idx)

        del X, output, idx

        return prediction

982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
    def reset_parameters(self):
        """Parameter Initialization

        This function (re)initializes the parameters of the defined network.
        This function is a wrapper for the reset_parameters() function defined for each module. 
        More information can be found here: https://discuss.pytorch.org/t/what-is-the-default-initialization-of-a-conv2d-layer-and-linear-layer/16055 + https://discuss.pytorch.org/t/how-to-reset-model-weights-to-effectively-implement-crossvalidation/53859 
        An alternative (re)initialization method is described here: https://discuss.pytorch.org/t/how-to-reset-variables-values-in-nn-modules/32639 
        """

        print("Initializing network parameters...")

        for _, module in self.named_children():
            for _, submodule in module.named_children():
                if isinstance(submodule, (torch.nn.PReLU, torch.nn.Dropout3d, torch.nn.MaxPool3d)) == False:
                    submodule.reset_parameters()

        print("Initialized network parameters!")

1000

1001
1002
# DEPRECATED ARCHITECTURES!

1003

1004
1005
class BrainMapperUNet(nn.Module):
    """Architecture class BrainMapper U-net.
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028

    This class contains the pytorch implementation of the U-net architecture underpinning the BrainMapper project.

    Args:
        parameters (dict): Contains information relevant parameters
        parameters = {
            'kernel_heigth': 5
            'kernel_width': 5
            'kernel_classification': 1
            'input_channels': 1
            'output_channels': 64
            'convolution_stride': 1
            'dropout': 0.2
            'pool_kernel_size': 2
            'pool_stride': 2
            'up_mode': 'upconv'
            'number_of_classes': 1
        }

    Returns:
        probability_map (torch.tensor): Output forward passed tensor through the U-net block
    """

1029
    def __init__(self, parameters):
1030
        super(BrainMapperUNet, self).__init__()
1031

1032
        # TODO: currently, architecture based on QuickNAT - need to adjust parameter values accordingly!
1033

1034
        self.encoderBlock1 = modules.EncoderBlock(parameters)
1035
        parameters['input_channels'] = parameters['output_channels']
1036
1037
1038
        self.encoderBlock2 = modules.EncoderBlock(parameters)
        self.encoderBlock3 = modules.EncoderBlock(parameters)
        self.encoderBlock4 = modules.EncoderBlock(parameters)
1039

1040
        self.bottleneck = modules.ConvolutionalBlock(parameters)
1041

1042
1043
1044
1045
1046
        parameters['input_channels'] = parameters['output_channels'] * 2.0
        self.decoderBlock1 = modules.DecoderBlock(parameters)
        self.decoderBlock2 = modules.DecoderBlock(parameters)
        self.decoderBlock3 = modules.DecoderBlock(parameters)
        self.decoderBlock4 = modules.DecoderBlock(parameters)
1047
1048

        parameters['input_channels'] = parameters['output_channels']
1049
        self.classifier = modules.ClassifierBlock(parameters)
1050
1051

    def forward(self, X):
1052
        """Forward pass for U-net
1053

1054
        Function computing the forward pass through the U-Net
1055
1056
1057
        The input to the function is the dMRI map

        Args:
1058
            X (torch.tensor): Input dMRI map, shape = (N x C x H x W) 
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087

        Returns:
            probability_map (torch.tensor): Output forward passed tensor through the U-net block
        """

        Y_encoder_1, Y_np1, pool_indices1 = self.encoderBlock1.forward(X)
        Y_encoder_2, Y_np2, pool_indices2 = self.encoderBlock2.forward(
            Y_encoder_1)

        del Y_encoder_1

        Y_encoder_3, Y_np3, pool_indices3 = self.encoderBlock3.forward(
            Y_encoder_2)

        del Y_encoder_2

        Y_encoder_4, Y_np4, pool_indices4 = self.encoderBlock4.forward(
            Y_encoder_3)

        del Y_encoder_3

        Y_bottleNeck = self.bottleneck.forward(Y_encoder_4)

        del Y_encoder_4

        Y_decoder_1 = self.decoderBlock1.forward(
            Y_bottleNeck, Y_np4, pool_indices4)

        del Y_bottleNeck, Y_np4, pool_indices4
1088

1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
        Y_decoder_2 = self.decoderBlock2.forward(
            Y_decoder_1, Y_np3, pool_indices3)

        del Y_decoder_1, Y_np3, pool_indices3

        Y_decoder_3 = self.decoderBlock3.forward(
            Y_decoder_2, Y_np2, pool_indices2)

        del Y_decoder_2, Y_np2, pool_indices2

1099
        Y_decoder_4 = self.decoderBlock4.forward(
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
            Y_decoder_3, Y_np1, pool_indices1)

        del Y_decoder_3, Y_np1, pool_indices1

        probability_map = self.classifier.forward(Y_decoder_4)

        del Y_decoder_4

        return probability_map

    def save(self, path):
        """Model Saver

        Function saving the model with all its parameters to a given path.
        The path must end with a *.model argument.

        Args:
            path (str): Path string
        """

        print("Saving Model... {}".format(path))
        torch.save(self, path)

    @property
    def test_if_cuda(self):
        """Cuda Test

        This function tests if the model parameters are allocated to a CUDA enabled GPU.

        Returns:
            bool: Flag indicating True if the tensor is stored on the GPU and Flase otherwhise
        """

        return next(self.parameters()).is_cuda

    def predict(self, X, device=0):
        """Post-training Output Prediction

        This function predicts the output of the of the U-net post-training

        Args:
            X (torch.tensor): input dMRI volume
            device (int/str): Device type used for training (int - GPU id, str- CPU)

        Returns:
            prediction (ndarray): predicted output after training

        """
        self.eval()  # PyToch module setting network to evaluation mode

        if type(X) is np.ndarray:
            X = torch.tensor(X, requires_grad=False).type(torch.FloatTensor)
        elif type(X) is torch.Tensor and not X.is_cuda:
            X = X.type(torch.FloatTensor).cuda(device, non_blocking=True)

        # .cuda() call transfers the densor from the CPU to the GPU if that is the case.
        # Non-blocking argument lets the caller bypas synchronization when necessary

        with torch.no_grad():  # Causes operations to have no gradients
            output = self.forward(X)

        _, idx = torch.max(output, 1)

        # We retrieve the tensor held by idx (.data), and map it to a cpu as an ndarray
        idx = idx.data.cpu().numpy()

        prediction = np.squeeze(idx)

        del X, output, idx

        return prediction

1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
    def reset_parameters(self):
        """Parameter Initialization

        This function (re)initializes the parameters of the defined network.
        This function is a wrapper for the reset_parameters() function defined for each module. 
        More information can be found here: https://discuss.pytorch.org/t/what-is-the-default-initialization-of-a-conv2d-layer-and-linear-layer/16055 + https://discuss.pytorch.org/t/how-to-reset-model-weights-to-effectively-implement-crossvalidation/53859 
        An alternative (re)initialization method is described here: https://discuss.pytorch.org/t/how-to-reset-variables-values-in-nn-modules/32639 
        """

        print("Initializing network parameters...")

        for _, module in self.named_children():
            for _, submodule in module.named_children():
                if isinstance(submodule, (torch.nn.PReLU, torch.nn.Dropout3d, torch.nn.MaxPool3d)) == False:
                    submodule.reset_parameters()

        print("Initialized network parameters!")
1189

1190

1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
class BrainMapperUNet3D_Simple(nn.Module):
    """Architecture class BrainMapper 3D U-net.

    This class contains the pytorch implementation of the U-net architecture underpinning the BrainMapper project.

    Args:
        parameters (dict): Contains information relevant parameters
        parameters = {
            'kernel_heigth': 5
            'kernel_width': 5
            'kernel_depth': 5
            'kernel_classification': 1
            'input_channels': 1
            'output_channels': 64
            'convolution_stride': 1
            'dropout': 0.2
            'pool_kernel_size': 2
            'pool_stride': 2
            'up_mode': 'upconv'
            'number_of_classes': 1
        }

    Returns:
        probability_map (torch.tensor): Output forward passed tensor through the U-net block
    """

1217
    def __init__(self, parameters):
1218
        super(BrainMapperUNet3D_Simple, self).__init__()
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229

        # TODO: currently, architecture based on QuickNAT - need to adjust parameter values accordingly!

        self.encoderBlock1 = modules.EncoderBlock3D(parameters)
        parameters['input_channels'] = parameters['output_channels']
        self.encoderBlock2 = modules.EncoderBlock3D(parameters)
        self.encoderBlock3 = modules.EncoderBlock3D(parameters)
        self.encoderBlock4 = modules.EncoderBlock3D(parameters)

        self.bottleneck = modules.ConvolutionalBlock3D(parameters)

1230
        parameters['input_channels'] = parameters['output_channels'] * 2
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
        self.decoderBlock1 = modules.DecoderBlock3D(parameters)
        self.decoderBlock2 = modules.DecoderBlock3D(parameters)
        self.decoderBlock3 = modules.DecoderBlock3D(parameters)
        self.decoderBlock4 = modules.DecoderBlock3D(parameters)

        parameters['input_channels'] = parameters['output_channels']
        self.classifier = modules.ClassifierBlock3D(parameters)

    def forward(self, X):
        """Forward pass for 3D U-net

        Function computing the forward pass through the 3D U-Net
        The input to the function is the dMRI map

        Args:
            X (torch.tensor): Input dMRI map, shape = (N x C x D x H x W) 

        Returns:
            probability_map (torch.tensor): Output forward passed tensor through the U-net block
        """

1252
        Y_encoder_1, Y_np1, pool_indices1 = self.encoderBlock1.forward(X)
1253
1254
        Y_encoder_2, Y_np2, pool_indices2 = self.encoderBlock2.forward(
            Y_encoder_1)
1255
1256
1257

        del Y_encoder_1

1258
1259
        Y_encoder_3, Y_np3, pool_indices3 = self.encoderBlock3.forward(
            Y_encoder_2)
1260
1261
1262

        del Y_encoder_2

1263
1264
        Y_encoder_4, Y_np4, pool_indices4 = self.encoderBlock4.forward(
            Y_encoder_3)
1265

1266
1267
        del Y_encoder_3

1268
1269
        Y_bottleNeck = self.bottleneck.forward(Y_encoder_4)

1270
1271
        del Y_encoder_4

1272
1273
        Y_decoder_1 = self.decoderBlock1.forward(
            Y_bottleNeck, Y_np4, pool_indices4)
1274
1275

        del Y_bottleNeck, Y_np4, pool_indices4
1276

1277
1278
        Y_decoder_2 = self.decoderBlock2.forward(
            Y_decoder_1, Y_np3, pool_indices3)
1279
1280
1281

        del Y_decoder_1, Y_np3, pool_indices3

1282
1283
        Y_decoder_3 = self.decoderBlock3.forward(
            Y_decoder_2, Y_np2, pool_indices2)
1284
1285
1286

        del Y_decoder_2, Y_np2, pool_indices2

1287
        Y_decoder_4 = self.decoderBlock4.forward(
1288
            Y_decoder_3, Y_np1, pool_indices1)
1289

1290
1291
1292
1293
1294
1295
        del Y_decoder_3, Y_np1, pool_indices1

        probability_map = self.classifier.forward(Y_decoder_4)

        del Y_decoder_4

1296
        probability_map = self.classifier.forward(Y_decoder_4)
1297

1298
        return probability_map
1299

1300
    def save(self, path):
Andrei-Claudiu Roibu's avatar
Andrei-Claudiu Roibu committed
1301
        """Model Saver
1302

Andrei-Claudiu Roibu's avatar
Andrei-Claudiu Roibu committed
1303
1304
        Function saving the model with all its parameters to a given path.
        The path must end with a *.model argument.
1305

Andrei-Claudiu Roibu's avatar
Andrei-Claudiu Roibu committed
1306
1307
1308
        Args:
            path (str): Path string
        """
1309

Andrei-Claudiu Roibu's avatar
Andrei-Claudiu Roibu committed
1310
1311
        print("Saving Model... {}".format(path))
        torch.save(self, path)
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323

    @property
    def test_if_cuda(self):
        """Cuda Test

        This function tests if the model parameters are allocated to a CUDA enabled GPU.

        Returns:
            bool: Flag indicating True if the tensor is stored on the GPU and Flase otherwhise
        """

        return next(self.parameters()).is_cuda
1324
1325

    def predict(self, X, device=0):
1326
        """Post-training Output Prediction
1327

1328
1329
1330
1331
        This function predicts the output of the of the U-net post-training

        Args:
            X (torch.tensor): input dMRI volume
1332
            device (int/str): Device type used for training (int - GPU id, str- CPU)
1333
1334
1335
1336

        Returns:
            prediction (ndarray): predicted output after training

1337
        """
1338
        self.eval()  # PyToch module setting network to evaluation mode
1339
1340
1341
1342
1343
1344
1345
1346
1347

        if type(X) is np.ndarray:
            X = torch.tensor(X, requires_grad=False).type(torch.FloatTensor)
        elif type(X) is torch.Tensor and not X.is_cuda:
            X = X.type(torch.FloatTensor).cuda(device, non_blocking=True)

        # .cuda() call transfers the densor from the CPU to the GPU if that is the case.
        # Non-blocking argument lets the caller bypas synchronization when necessary

1348
        with torch.no_grad():  # Causes operations to have no gradients
1349
1350
1351
1352
            output = self.forward(X)

        _, idx = torch.max(output, 1)

1353
1354
1355
        # We retrieve the tensor held by idx (.data), and map it to a cpu as an ndarray
        idx = idx.data.cpu().numpy()

1356
1357
1358
1359
1360
1361
        prediction = np.squeeze(idx)

        del X, output, idx

        return prediction

1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
    def reset_parameters(self):
        """Parameter Initialization

        This function (re)initializes the parameters of the defined network.
        This function is a wrapper for the reset_parameters() function defined for each module. 
        More information can be found here: https://discuss.pytorch.org/t/what-is-the-default-initialization-of-a-conv2d-layer-and-linear-layer/16055 + https://discuss.pytorch.org/t/how-to-reset-model-weights-to-effectively-implement-crossvalidation/53859 
        An alternative (re)initialization method is described here: https://discuss.pytorch.org/t/how-to-reset-variables-values-in-nn-modules/32639 
        """

        print("Initializing network parameters...")

        for _, module in self.named_children():
            for _, submodule in module.named_children():
                if isinstance(submodule, (torch.nn.PReLU, torch.nn.Dropout3d, torch.nn.MaxPool3d)) == False:
                    submodule.reset_parameters()

        print("Initialized network parameters!")

1380