File size: 18,680 Bytes
4ae3d87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4295788
4ae3d87
 
 
 
 
 
 
 
 
 
 
 
 
4295788
4ae3d87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4295788
4ae3d87
 
 
4295788
4ae3d87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dfc64a6
 
4ae3d87
 
 
 
 
 
 
 
dfc64a6
4ae3d87
dfc64a6
4ae3d87
 
 
 
 
 
dfc64a6
 
4ae3d87
 
 
 
 
dfc64a6
 
4ae3d87
dfc64a6
4ae3d87
 
dfc64a6
 
4ae3d87
dfc64a6
4ae3d87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Create the BertClassfier class
import numpy as np
import torch
import torch.nn as nn
from transformers import AdamW, get_linear_schedule_with_warmup
device='cuda'

import random
import time
import torch.nn as nn

# Specify loss function
loss_fn = nn.CrossEntropyLoss()

class PretrainedBert(nn.Module):
    """Bert Model for Classification Tasks.
    """
    def __init__(self, freeze_bert=False):
        """
        @param    bert: a BertModel object
        @param    classifier: a torch.nn.Module classifier
        @param    freeze_bert (bool): Set `False` to fine-tune the BERT model
        """
        super(PretrainedBert, self).__init__()
        # Specify hidden size of BERT, hidden size of our classifier, and number of labels
        D_in, H, D_out = 768, 50, 14
        # Instantiate BERT model
        from transformers import BertConfig

        config = BertConfig(
          # we align this to the tokenizer vocab_size
        max_position_embeddings=5000,
        hidden_size=768,
        num_attention_heads=2,
        num_hidden_layers=2,
        type_vocab_size=1
)
        from transformers import BertForMaskedLM

        self.bert =BertModel(config)
        # Instantiate an one-layer feed-forward classifier
        self.classifier = nn.Sequential(
            nn.Linear(D_in, H),
            nn.ReLU(),
            #nn.Dropout(0.5),
            nn.Linear(H, D_out)
        )

        # Freeze the BERT model
        if freeze_bert:
            for param in self.bert.parameters():
                param.requires_grad = False
        
    def forward(self, input_ids, attention_mask):
        """
        Feed input to BERT and the classifier to compute logits.
        @param    input_ids (torch.Tensor): an input tensor with shape (batch_size,
                      max_length)
        @param    attention_mask (torch.Tensor): a tensor that hold attention mask
                      information with shape (batch_size, max_length)
        @return   logits (torch.Tensor): an output tensor with shape (batch_size,
                      num_labels)
        """
        # Feed input to BERT
        outputs = self.bert(input_ids=input_ids,
                            attention_mask=attention_mask)
        
        # Extract the last hidden state of the token `[CLS]` for classification task
        last_hidden_state_cls = outputs[0][:, 0, :]

        # Feed input to classifier to compute logits
        logits = self.classifier(last_hidden_state_cls)

        return logits
from transformers import AdamW, get_linear_schedule_with_warmup
device='cuda'


def valid_evaluate(model, val_dataloader):
    """After the completion of each training epoch, measure the model's performance
    on our validation set.
    """
    # Put the model into the evaluation mode. The dropout layers are disabled during
    # the test time.
    model.eval()

    # Tracking variables
    val_accuracy = []
    val_loss = []

    # For each batch in our validation set...
    for batch in val_dataloader:
        # Load batch to GPU
        b_input_ids, b_attn_mask, b_labels = tuple(t.to(device) for t in batch)

        # Compute logits
        with torch.no_grad():
            logits = model(b_input_ids, b_attn_mask)

        # Compute loss
        loss = loss_fn(logits, b_labels)
        val_loss.append(loss.item())

        # Get the predictions
        preds = torch.argmax(logits, dim=1).flatten()

        # Calculate the accuracy rate
        accuracy = (preds == b_labels).cpu().numpy().mean() * 100
        val_accuracy.append(accuracy)

    # Compute the average accuracy and loss over the validation set.
    val_loss = np.mean(val_loss)
    val_accuracy = np.mean(val_accuracy)

    return val_loss, val_accuracy



import torch
import torch.nn as nn
from transformers import BertModel

# Create the BertClassfier class
class FinetunningBert(nn.Module):
    """Bert Model for Classification Tasks.
    """
    def __init__(self, freeze_bert=False):
        """
        @param    bert: a BertModel object
        @param    classifier: a torch.nn.Module classifier
        @param    freeze_bert (bool): Set `False` to fine-tune the BERT model
        """
        super(FinetunningBert, self).__init__()
        # Specify hidden size of BERT, hidden size of our classifier, and number of labels
        D_in, H, D_out = 768, 50, 7
        # Instantiate BERT model
        from transformers import BertConfig

        from transformers import BertForMaskedLM
        bert_classifier = PretrainedBert(freeze_bert=False)
        bert_classifier.load_state_dict(torch.load('/home/user/app/virBERT.pt'))
        self.bert =bert_classifier.bert.to(device)
        # Instantiate an one-layer feed-forward classifier
        self.classifier = nn.Sequential(
            nn.Linear(D_in, H),
            nn.ReLU(),
            #nn.Dropout(0.5),
            nn.Linear(H, D_out)
        )

        # Freeze the BERT model
        if freeze_bert:
            for param in self.bert.parameters():
                param.requires_grad = False
        
    def forward(self, input_ids, attention_mask):
        """
        Feed input to BERT and the classifier to compute logits.
        @param    input_ids (torch.Tensor): an input tensor with shape (batch_size,
                      max_length)
        @param    attention_mask (torch.Tensor): a tensor that hold attention mask
                      information with shape (batch_size, max_length)
        @return   logits (torch.Tensor): an output tensor with shape (batch_size,
                      num_labels)
        """
        # Feed input to BERT
        outputs = self.bert(input_ids=input_ids,
                            attention_mask=attention_mask)
        
        # Extract the last hidden state of the token `[CLS]` for classification task
        last_hidden_state_cls = outputs[0][:, 0, :]

        # Feed input to classifier to compute logits
        logits = self.classifier(last_hidden_state_cls)

        return logits
from transformers import AdamW, get_linear_schedule_with_warmup
device='cuda'
def initialize_finetunningBert(train_dataloader,epochs=4):
    """Initialize the Bert Classifier, the optimizer and the learning rate scheduler.
    """
    # Instantiate Bert Classifier
    bert_classifier = FinetunningBert(freeze_bert=False)

    # Tell PyTorch to run the model on GPU
    bert_classifier.to(device)

    # Create the optimizer
    optimizer = AdamW(bert_classifier.parameters(),
                      lr=5e-5,    # Default learning rate
                      eps=1e-8    # Default epsilon value
                      )

    # Total number of training steps
    total_steps = len(train_dataloader) * epochs

    # Set up the learning rate scheduler
    scheduler = get_linear_schedule_with_warmup(optimizer,
                                                num_warmup_steps=0, # Default value
                                                num_training_steps=total_steps)
    return bert_classifier, optimizer, scheduler
import random
import time
import torch.nn as nn

# Specify loss function
loss_fn = nn.CrossEntropyLoss()


def finetunningBert_training(model, optimizer, scheduler, train_dataloader, val_dataloader=None, epochs=4, evaluation=False):
    """Train the BertClassifier model.
    """
    # Start training loop
    print("Start training...\n")
    for epoch_i in range(epochs):
        # =======================================
        #               Training
        # =======================================
        # Print the header of the result table
        print(f"{'Epoch':^7} | {'Batch':^7} | {'Train Loss':^12} | {'Val Loss':^10} | {'Val Acc':^9} | {'Elapsed':^9}")
        print("-"*70)

        # Measure the elapsed time of each epoch
        t0_epoch, t0_batch = time.time(), time.time()

        # Reset tracking variables at the beginning of each epoch
        total_loss, batch_loss, batch_counts = 0, 0, 0

        # Put the model into the training mode
        model.train()

        # For each batch of training data...
        for step, batch in enumerate(train_dataloader):
            batch_counts +=1
            # Load batch to GPU
            b_input_ids, b_attn_mask, b_labels = tuple(t.to(device) for t in batch)

            # Zero out any previously calculated gradients
            model.zero_grad()

            # Perform a forward pass. This will return logits.
            logits = model(b_input_ids, b_attn_mask)

            # Compute loss and accumulate the loss values
            loss = loss_fn(logits, b_labels)
            batch_loss += loss.item()
            total_loss += loss.item()

            # Perform a backward pass to calculate gradients
            loss.backward()

            # Clip the norm of the gradients to 1.0 to prevent "exploding gradients"
            torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)

            # Update parameters and the learning rate
            optimizer.step()
            scheduler.step()

            # Print the loss values and time elapsed for every 20 batches
            if (step % 20 == 0 and step != 0) or (step == len(train_dataloader) - 1):
                # Calculate time elapsed for 20 batches
                time_elapsed = time.time() - t0_batch

                # Print training results
                print(f"{epoch_i + 1:^7} | {step:^7} | {batch_loss / batch_counts:^12.6f} | {'-':^10} | {'-':^9} | {time_elapsed:^9.2f}")

                # Reset batch tracking variables
                batch_loss, batch_counts = 0, 0
                t0_batch = time.time()

        # Calculate the average loss over the entire training data
        avg_train_loss = total_loss / len(train_dataloader)
        torch.save(model.state_dict(), '{}model.pt'.format("VirDNA4Baltimore"))
        print("-"*70)
        # =======================================
        #               Evaluation
        # =======================================
        if evaluation == True:
            # After the completion of each training epoch, measure the model's performance
            # on our validation set.
            val_loss, val_accuracy = valid_evaluate(model, val_dataloader)

            # Print performance over the entire training data
            time_elapsed = time.time() - t0_epoch
            
            print(f"{epoch_i + 1:^7} | {'-':^7} | {avg_train_loss:^12.6f} | {val_loss:^10.6f} | {val_accuracy:^9.2f} | {time_elapsed:^9.2f}")
            print("-"*70)
        print("\n")
    
    print("Training complete!")

def bertPredictions(torch,model, val_dataloader):
    """After the completion of each training epoch, measure the model's performance
    on our validation set.
    """
    # Put the model into the evaluation mode. The dropout layers are disabled during
    # the test time.
    model.eval()
    device = 0
    print("working3")

    # Tracking variables
    val_accuracy = []
    val_loss = []
    pred=[]
    actual=[]
    # For each batch in our validation set...
    for batch in val_dataloader:
        device = 0
        # Load batch to GPU
        b_input_ids, b_attn_mask, b_labels = tuple(t for t in batch)

        # Compute logits
        with torch.no_grad():
            logits = model(b_input_ids, b_attn_mask)

        # Compute loss
        #loss = loss_fn(logits, b_labels)
        #val_loss.append(loss.item())

        # Get the predictions
        preds = torch.argmax(logits, dim=1).flatten()

        # Calculate the accuracy rate
        #accuracy = (preds == b_labels).cpu().numpy().mean() * 100
        #val_accuracy.append(accuracy)
        pred.append(preds.cpu())
        #actual.append(b_labels.cpu())

    # Compute the average accuracy and loss over the validation set.
    #val_loss = np.mean(val_loss)
    #val_accuracy = np.mean(val_accuracy)

    return pred













    import torch
import torch.nn as nn
from transformers import BertModel

# Create the BertClassfier class
class ScratchBert(nn.Module):
    """Bert Model for Classification Tasks.
    """
    def __init__(self, freeze_bert=False):
        """
        @param    bert: a BertModel object
        @param    classifier: a torch.nn.Module classifier
        @param    freeze_bert (bool): Set `False` to fine-tune the BERT model
        """
        super(ScratchBert, self).__init__()
        # Specify hidden size of BERT, hidden size of our classifier, and number of labels
        D_in, H, D_out = 768, 50, 2
        # Instantiate BERT model
        from transformers import BertConfig


        config = BertConfig(
          # we align this to the tokenizer vocab_size
        max_position_embeddings=5000,
        hidden_size=768,
        num_attention_heads=2,
        num_hidden_layers=2,
        type_vocab_size=1
)
        from transformers import BertForMaskedLM

        self.bert =BertModel(config)
        # Instantiate an one-layer feed-forward classifier
        self.classifier = nn.Sequential(
            nn.Linear(D_in, H),
            nn.ReLU(),
            #nn.Dropout(0.5),
            nn.Linear(H, D_out)
        )

        # Freeze the BERT model
        if freeze_bert:
            for param in self.bert.parameters():
                param.requires_grad = False
        
    def forward(self, input_ids, attention_mask):
        """
        Feed input to BERT and the classifier to compute logits.
        @param    input_ids (torch.Tensor): an input tensor with shape (batch_size,
                      max_length)
        @param    attention_mask (torch.Tensor): a tensor that hold attention mask
                      information with shape (batch_size, max_length)
        @return   logits (torch.Tensor): an output tensor with shape (batch_size,
                      num_labels)
        """
        # Feed input to BERT
        outputs = self.bert(input_ids=input_ids,
                            attention_mask=attention_mask)
        
        # Extract the last hidden state of the token `[CLS]` for classification task
        last_hidden_state_cls = outputs[0][:, 0, :]

        # Feed input to classifier to compute logits
        logits = self.classifier(last_hidden_state_cls)

        return logits
from transformers import AdamW, get_linear_schedule_with_warmup
device='cuda'
def initialize_model(train_dataloader,epochs=4):
    """Initialize the Bert Classifier, the optimizer and the learning rate scheduler.
    """
    # Instantiate Bert Classifier
    bert_classifier = ScratchBert(freeze_bert=False)

    # Tell PyTorch to run the model on GPU
    bert_classifier.to(device)

    # Create the optimizer
    optimizer = AdamW(bert_classifier.parameters(),
                      lr=5e-5,    # Default learning rate
                      eps=1e-8    # Default epsilon value
                      )

    # Total number of training steps
    total_steps = len(train_dataloader) * epochs

    # Set up the learning rate scheduler
    scheduler = get_linear_schedule_with_warmup(optimizer,
                                                num_warmup_steps=0, # Default value
                                                num_training_steps=total_steps)
    return bert_classifier, optimizer, scheduler
import random
import time
import torch.nn as nn

# Specify loss function
loss_fn = nn.CrossEntropyLoss()


def train(model,optimizer, scheduler, train_dataloader, val_dataloader=None, epochs=4, evaluation=False):
    """Train the BertClassifier model.
    """
    # Start training loop
    print("Start training...\n")
    for epoch_i in range(epochs):
        # =======================================
        #               Training
        # =======================================
        # Print the header of the result table
        print(f"{'Epoch':^7} | {'Batch':^7} | {'Train Loss':^12} | {'Val Loss':^10} | {'Val Acc':^9} | {'Elapsed':^9}")
        print("-"*70)

        # Measure the elapsed time of each epoch
        t0_epoch, t0_batch = time.time(), time.time()

        # Reset tracking variables at the beginning of each epoch
        total_loss, batch_loss, batch_counts = 0, 0, 0

        # Put the model into the training mode
        model.train()

        # For each batch of training data...
        for step, batch in enumerate(train_dataloader):
            batch_counts +=1
            # Load batch to GPU
            b_input_ids, b_attn_mask, b_labels = tuple(t.to(device) for t in batch)

            # Zero out any previously calculated gradients
            model.zero_grad()

            # Perform a forward pass. This will return logits.
            logits = model(b_input_ids, b_attn_mask)

            # Compute loss and accumulate the loss values
            loss = loss_fn(logits, b_labels)
            batch_loss += loss.item()
            total_loss += loss.item()

            # Perform a backward pass to calculate gradients
            loss.backward()

            # Clip the norm of the gradients to 1.0 to prevent "exploding gradients"
            torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)

            # Update parameters and the learning rate
            optimizer.step()
            scheduler.step()

            # Print the loss values and time elapsed for every 20 batches
            if (step % 20 == 0 and step != 0) or (step == len(train_dataloader) - 1):
                # Calculate time elapsed for 20 batches
                time_elapsed = time.time() - t0_batch

                # Print training results
                print(f"{epoch_i + 1:^7} | {step:^7} | {batch_loss / batch_counts:^12.6f} | {'-':^10} | {'-':^9} | {time_elapsed:^9.2f}")

                # Reset batch tracking variables
                batch_loss, batch_counts = 0, 0
                t0_batch = time.time()

        # Calculate the average loss over the entire training data
        avg_train_loss = total_loss / len(train_dataloader)
        torch.save(model.state_dict(), '{}model.pt'.format("VirDNA"))
        print("-"*70)
        # =======================================
        #               Evaluation
        # =======================================
        if evaluation == True:
            # After the completion of each training epoch, measure the model's performance
            # on our validation set.
            val_loss, val_accuracy = valid_evaluate(model, val_dataloader)

            # Print performance over the entire training data
            time_elapsed = time.time() - t0_epoch
            
            print(f"{epoch_i + 1:^7} | {'-':^7} | {avg_train_loss:^12.6f} | {val_loss:^10.6f} | {val_accuracy:^9.2f} | {time_elapsed:^9.2f}")
            print("-"*70)
        print("\n")
    
    print("Training complete!")