-
Notifications
You must be signed in to change notification settings - Fork 0
/
05_Autoregressive.py
833 lines (609 loc) · 864 KB
/
05_Autoregressive.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
# -*- coding: utf-8 -*-
"""05_autoregressive_sol.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/16PhYp_98no0euYd7K6KKIAEY3UcgAssd
# Translation with a Sequence to Sequence Network and Attention
**Disclaimer.**
This colab is based on
1. [Pytorch NLP Tutorial](https://pytorch.org/tutorials/intermediate/seq2seq_translation_tutorial.html)
In this project we will be teaching a neural network to translate from
French to English.
[KEY: > input, = target, < output]
> il est en train de peindre un tableau .
= he is painting a picture .
< he is painting a picture .
> pourquoi ne pas essayer ce vin delicieux ?
= why not try that delicious wine ?
< why not try that delicious wine ?
> elle n est pas poete mais romanciere .
= she is not a poet but a novelist .
< she not not a poet but a novelist .
> vous etes trop maigre .
= you re too skinny .
< you re all alone .
... to varying degrees of success.
This is made possible by the simple but powerful idea of the [sequence
to sequence network](https://arxiv.org/abs/1409.3215)_, in which two
recurrent neural networks work together to transform one sequence to
another. An encoder network condenses an input sequence into a vector,
and a decoder network unfolds that vector into a new sequence.
To improve upon this model we'll use an [attention
mechanism](https://arxiv.org/abs/1409.0473)_, which lets the decoder
learn to focus over a specific range of the input sequence.
**Requirements**
"""
from __future__ import unicode_literals, print_function, division
from io import open
import unicodedata
import string
import re
import random
import doctest
import numpy as np
import torch
import torch.nn as nn
from torch import optim
import torch.nn.functional as F
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
seed = 2022
random.seed(seed)
np.random.seed(seed)
torch.manual_seed(seed)
torch.cuda.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
"""## Loading data files
The data for this project is a tab
separated list of translation pairs:
I am cold. J'ai froid.
"""
import os
import urllib.request
from urllib.error import HTTPError
file_path = "./data.zip"
file_url = "https://download.pytorch.org/tutorial/data.zip"
print("Downloading ...")
try:
urllib.request.urlretrieve(file_url, file_path)
except HTTPError as e:
print("Something went wrong :<", e)
!unzip data.zip
print("Data prepared!")
"""Similar to the character encoding used in the character-level RNN
tutorials, we will be representing each word in a language as a one-hot
vector, or giant vector of zeros except for a single one (at the index
of the word). Compared to the dozens of characters that might exist in a
language, there are many many more words, so the encoding vector is much
larger. We will however cheat a bit and trim the data to only use a few
thousand words per language.
We'll need a unique index per word to use as the inputs and targets of
the networks later. To keep track of all this we will use a helper class
called ``Lang`` which has word → index (``word2index``) and index → word
(``index2word``) dictionaries, as well as a count of each word
``word2count`` which will be used to replace rare words later.
**Q1. Complete the implementation of the `Lang` class**
"""
SOS_token = 0
EOS_token = 1
class Lang:
"""
>>> lang_test = Lang("eng")
>>> lang_test.addSentence("Hi my name is Alex")
>>> lang_test.addSentence("This is a GIST AI Graduate School course")
>>> lang_test.addSentence("What is the weather like")
>>> lang_test.addSentence("Where do you want to go")
>>> lang_test.addSentence("There are great students at GIST AI Graduate School")
>>> print(lang_test.n_words)
29
>>> print(lang_test.word2index["GIST"])
9
>>> print(lang_test.word2count["GIST"])
2
>>> print(lang_test.index2word[5])
is
>>> print(lang_test.index2word[10])
AI
>>> print(lang_test.index2word[15])
the
"""
def __init__(self, name):
self.name = name
self.word2index = {}
self.word2count = {}
self.index2word = {0: "SOS", 1: "EOS"}
self.n_words = 2 # Count SOS and EOS
def addSentence(self, sentence):
for word in sentence.split(' '):
self.addWord(word)
def addWord(self, word):
if word not in self.word2index:
self.word2index[word] = self.n_words
self.word2count[word] = 1
self.index2word[self.n_words] = word
self.n_words += 1
else:
self.word2count[word] += 1
"""Run below to check your implementation :)"""
doctest.run_docstring_examples(Lang, globals(), False, __name__)
"""The files are all in Unicode, to simplify we will turn Unicode
characters to ASCII, make everything lowercase, and trim most
punctuation.
"""
# Turn a Unicode string to plain ASCII, thanks to
# https://stackoverflow.com/a/518232/2809427
def unicodeToAscii(s):
return ''.join(
c for c in unicodedata.normalize('NFD', s)
if unicodedata.category(c) != 'Mn'
)
# Lowercase, trim, and remove non-letter characters
def normalizeString(s):
s = unicodeToAscii(s.lower().strip())
s = re.sub(r"([.!?])", r" \1", s)
s = re.sub(r"[^a-zA-Z.!?]+", r" ", s)
return s
"""To read the data file we will split the file into lines, and then split
lines into pairs. The files are all English → Other Language, so if we
want to translate from Other Language → English I added the ``reverse``
flag to reverse the pairs.
"""
def readLangs(lang1, lang2, reverse=False):
print("Reading lines...")
# Read the file and split into lines
lines = open('data/%s-%s.txt' % (lang1, lang2), encoding='utf-8').\
read().strip().split('\n')
# Split every line into pairs and normalize
pairs = [[normalizeString(s) for s in l.split('\t')] for l in lines]
# Reverse pairs, make Lang instances
if reverse:
pairs = [list(reversed(p)) for p in pairs]
input_lang = Lang(lang2)
output_lang = Lang(lang1)
else:
input_lang = Lang(lang1)
output_lang = Lang(lang2)
return input_lang, output_lang, pairs
"""Since there are a *lot* of example sentences and we want to train
something quickly, we'll trim the data set to only relatively short and
simple sentences. Here the maximum length is 10 words (that includes
ending punctuation) and we're filtering to sentences that translate to
the form "I am" or "He is" etc. (accounting for apostrophes replaced
earlier).
"""
MAX_LENGTH = 10
eng_prefixes = (
"i am ", "i m ",
"he is", "he s ",
"she is", "she s ",
"you are", "you re ",
"we are", "we re ",
"they are", "they re "
)
def filterPair(p):
return len(p[0].split(' ')) < MAX_LENGTH and \
len(p[1].split(' ')) < MAX_LENGTH and \
p[1].startswith(eng_prefixes)
def filterPairs(pairs):
return [pair for pair in pairs if filterPair(pair)]
"""The full process for preparing the data is:
- Read text file and split into lines, split lines into pairs
- Normalize text, filter by length and content
- Make word lists from sentences in pairs
"""
def prepareData(lang1, lang2, reverse=False):
input_lang, output_lang, pairs = readLangs(lang1, lang2, reverse)
print("Read %s sentence pairs" % len(pairs))
pairs = filterPairs(pairs)
print("Trimmed to %s sentence pairs" % len(pairs))
print("Counting words...")
for pair in pairs:
input_lang.addSentence(pair[0])
output_lang.addSentence(pair[1])
print("Counted words:")
print(input_lang.name, input_lang.n_words)
print(output_lang.name, output_lang.n_words)
return input_lang, output_lang, pairs
input_lang, output_lang, pairs = prepareData('eng', 'fra', True)
print(random.choice(pairs))
"""## The Seq2Seq Model
A Recurrent Neural Network, or RNN, is a network that operates on a
sequence and uses its own output as input for subsequent steps.
A [Sequence to Sequence network](https://arxiv.org/abs/1409.3215)_, or
seq2seq network, or [Encoder Decoder
network](https://arxiv.org/pdf/1406.1078v3.pdf)_, is a model
consisting of two RNNs called the encoder and decoder. The encoder reads
an input sequence and outputs a single vector, and the decoder reads
that vector to produce an output sequence.
Unlike sequence prediction with a single RNN, where every input
corresponds to an output, the seq2seq model frees us from sequence
length and order, which makes it ideal for translation between two
languages.
Consider the sentence "Je ne suis pas le chat noir" → "I am not the
black cat". Most of the words in the input sentence have a direct
translation in the output sentence, but are in slightly different
orders, e.g. "chat noir" and "black cat". Because of the "ne/pas"
construction there is also one more word in the input sentence. It would
be difficult to produce a correct translation directly from the sequence
of input words.
With a seq2seq model the encoder creates a single vector which, in the
ideal case, encodes the "meaning" of the input sequence into a single
vector — a single point in some N dimensional space of sentences.
### The Encoder
The encoder of a seq2seq network is a RNN that outputs some value for
every word from the input sentence. For every input word the encoder
outputs a vector and a hidden state, and uses the hidden state for the
next input word.
**Q2. Complete the implementation of the `EncoderRNN` class**
"""
class EncoderRNN(nn.Module):
"""
>>> encoder_test = EncoderRNN(1000, 256).to(device)
>>> input_test = torch.randint(999, (1,)).to(device)
>>> hidden_test = encoder_test.initHidden()
>>> output_test, hidden_test = encoder_test(input_test, hidden_test)
>>> print(output_test.shape)
torch.Size([1, 1, 256])
>>> print(hidden_test.shape)
torch.Size([1, 1, 256])
"""
def __init__(self, input_size, hidden_size):
super(EncoderRNN, self).__init__()
self.hidden_size = hidden_size
self.embedding = nn.Embedding(input_size, hidden_size)
self.gru = nn.GRU(hidden_size, hidden_size)
def forward(self, input, hidden):
embedded = self.embedding(input).view(1, 1, -1)
output = embedded
output, hidden = self.gru(output, hidden)
return output, hidden
def initHidden(self):
return torch.zeros(1, 1, self.hidden_size, device=device)
"""Run the test code below :)"""
doctest.run_docstring_examples(EncoderRNN, globals(), False, __name__)
"""### The Decoder
The decoder is another RNN that takes the encoder output vector(s) and
outputs a sequence of words to create the translation.
#### Simple Decoder
In the simplest seq2seq decoder we use only last output of the encoder.
This last output is sometimes called the *context vector* as it encodes
context from the entire sequence. This context vector is used as the
initial hidden state of the decoder.
At every step of decoding, the decoder is given an input token and
hidden state. The initial input token is the start-of-string ``<SOS>``
token, and the first hidden state is the context vector (the encoder's
last hidden state).
"""
class DecoderRNN(nn.Module):
def __init__(self, hidden_size, output_size):
super(DecoderRNN, self).__init__()
self.hidden_size = hidden_size
self.embedding = nn.Embedding(output_size, hidden_size)
self.gru = nn.GRU(hidden_size, hidden_size)
self.out = nn.Linear(hidden_size, output_size)
self.softmax = nn.LogSoftmax(dim=1)
def forward(self, input, hidden):
output = self.embedding(input).view(1, 1, -1)
output = F.relu(output)
output, hidden = self.gru(output, hidden)
output = self.softmax(self.out(output[0]))
return output, hidden
def initHidden(self):
return torch.zeros(1, 1, self.hidden_size, device=device)
"""I encourage you to train and observe the results of this model, but to
save space we'll be going straight for the gold and introducing the
Attention Mechanism.
#### Attention Decoder
If only the context vector is passed between the encoder and decoder,
that single vector carries the burden of encoding the entire sentence.
Attention allows the decoder network to "focus" on a different part of
the encoder's outputs for every step of the decoder's own outputs. First
we calculate a set of *attention weights*. These will be multiplied by
the encoder output vectors to create a weighted combination. The result
(called ``attn_applied`` in the code) should contain information about
that specific part of the input sequence, and thus help the decoder
choose the right output words.
Calculating the attention weights is done with another feed-forward
layer ``attn``, using the decoder's input and hidden state as inputs.
Because there are sentences of all sizes in the training data, to
actually create and train this layer we have to choose a maximum
sentence length (input length, for encoder outputs) that it can apply
to. Sentences of the maximum length will use all the attention weights,
while shorter sentences will only use the first few.
**Q3. Complete the implementation of the `AttnDecoderRNN` class**
"""
class AttnDecoderRNN(nn.Module):
"""
>>> max_len_test = 100
>>> attn_decoder_test = AttnDecoderRNN(256, 1000, dropout_p=0.1, max_length=max_len_test).to(device)
>>> hidden_test = attn_decoder_test.initHidden()
>>> input_test = torch.tensor([[SOS_token]], device=device)
>>> context_test = torch.randn(max_len_test, 256, device=device)
>>> out_test, hidden_test, att_test = attn_decoder_test(input_test, hidden_test, context_test)
>>> print(out_test.shape)
torch.Size([1, 1000])
>>> print(att_test.shape)
torch.Size([1, 100])
"""
def __init__(self, hidden_size, output_size, dropout_p=0.1, max_length=MAX_LENGTH):
super(AttnDecoderRNN, self).__init__()
self.hidden_size = hidden_size
self.output_size = output_size
self.dropout_p = dropout_p
self.max_length = max_length
self.embedding = nn.Embedding(self.output_size, self.hidden_size)
self.attn = nn.Linear(self.hidden_size * 2, self.max_length)
self.attn_combine = nn.Linear(self.hidden_size * 2, self.hidden_size)
self.dropout = nn.Dropout(self.dropout_p)
self.gru = nn.GRU(self.hidden_size, self.hidden_size)
self.out = nn.Linear(self.hidden_size, self.output_size)
def forward(self, input, hidden, encoder_outputs):
embedded = self.embedding(input).view(1, 1, -1)
embedded = self.dropout(embedded)
attn_weights = F.softmax(
self.attn(torch.cat((embedded[0], hidden[0]), 1)), dim=1)
attn_applied = torch.bmm(attn_weights.unsqueeze(0),
encoder_outputs.unsqueeze(0))
output = torch.cat((embedded[0], attn_applied[0]), 1)
output = self.attn_combine(output).unsqueeze(0)
output = F.relu(output)
output, hidden = self.gru(output, hidden)
output = F.log_softmax(self.out(output[0]), dim=1)
return output, hidden, attn_weights
def initHidden(self):
return torch.zeros(1, 1, self.hidden_size, device=device)
"""Run the test code below to check your implementation :)"""
doctest.run_docstring_examples(AttnDecoderRNN, globals(), False, __name__)
"""<div class="alert alert-info"><h4>Note</h4><p>There are other forms of attention that work around the length
limitation by using a relative position approach. Read about "local
attention" in [Effective Approaches to Attention-based Neural Machine
Translation](https://arxiv.org/abs/1508.04025)_.</p></div>
## Training
### Preparing Training Data
To train, for each pair we will need an input tensor (indexes of the
words in the input sentence) and target tensor (indexes of the words in
the target sentence). While creating these vectors we will append the
EOS token to both sequences.
"""
def indexesFromSentence(lang, sentence):
return [lang.word2index[word] for word in sentence.split(' ')]
def tensorFromSentence(lang, sentence):
indexes = indexesFromSentence(lang, sentence)
indexes.append(EOS_token)
return torch.tensor(indexes, dtype=torch.long, device=device).view(-1, 1)
def tensorsFromPair(pair):
input_tensor = tensorFromSentence(input_lang, pair[0])
target_tensor = tensorFromSentence(output_lang, pair[1])
return (input_tensor, target_tensor)
"""### Training the Model
To train we run the input sentence through the encoder, and keep track
of every output and the latest hidden state. Then the decoder is given
the ``<SOS>`` token as its first input, and the last hidden state of the
encoder as its first hidden state.
"Teacher forcing" is the concept of using the real target outputs as
each next input, instead of using the decoder's guess as the next input.
Using teacher forcing causes it to converge faster but [when the trained
network is exploited, it may exhibit
instability](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.378.4095&rep=rep1&type=pdf)_.
You can observe outputs of teacher-forced networks that read with
coherent grammar but wander far from the correct translation -
intuitively it has learned to represent the output grammar and can "pick
up" the meaning once the teacher tells it the first few words, but it
has not properly learned how to create the sentence from the translation
in the first place.
Because of the freedom PyTorch's autograd gives us, we can randomly
choose to use teacher forcing or not with a simple if statement. Turn
``teacher_forcing_ratio`` up to use more of it.
**Q4. Complete the implementation of the `train` function**
"""
teacher_forcing_ratio = 0.5
def train(input_tensor, target_tensor, encoder, decoder, encoder_optimizer, decoder_optimizer, criterion, max_length=MAX_LENGTH):
encoder_hidden = encoder.initHidden()
encoder_optimizer.zero_grad()
decoder_optimizer.zero_grad()
input_length = input_tensor.size(0)
target_length = target_tensor.size(0)
encoder_outputs = torch.zeros(max_length, encoder.hidden_size, device=device)
loss = 0
for ei in range(input_length):
encoder_output, encoder_hidden = encoder(
input_tensor[ei], encoder_hidden)
encoder_outputs[ei] = encoder_output[0, 0]
decoder_input = torch.tensor([[SOS_token]], device=device)
decoder_hidden = encoder_hidden
use_teacher_forcing = True if random.random() < teacher_forcing_ratio else False
if use_teacher_forcing:
# Teacher forcing: Feed the target as the next input
for di in range(target_length):
decoder_output, decoder_hidden, decoder_attention = decoder(
decoder_input, decoder_hidden, encoder_outputs)
loss += criterion(decoder_output, target_tensor[di])
decoder_input = target_tensor[di] # Teacher forcing
else:
# Without teacher forcing: use its own predictions as the next input
for di in range(target_length):
decoder_output, decoder_hidden, decoder_attention = decoder(
decoder_input, decoder_hidden, encoder_outputs)
topv, topi = decoder_output.topk(1)
decoder_input = topi.squeeze().detach() # detach from history as input
loss += criterion(decoder_output, target_tensor[di])
if decoder_input.item() == EOS_token:
break
loss.backward()
encoder_optimizer.step()
decoder_optimizer.step()
return loss.item() / target_length
"""This is a helper function to print time elapsed and estimated time
remaining given the current time and progress %.
"""
import time
import math
def asMinutes(s):
m = math.floor(s / 60)
s -= m * 60
return '%dm %ds' % (m, s)
def timeSince(since, percent):
now = time.time()
s = now - since
es = s / (percent)
rs = es - s
return '%s (- %s)' % (asMinutes(s), asMinutes(rs))
"""The whole training process looks like this:
- Start a timer
- Initialize optimizers and criterion
- Create set of training pairs
- Start empty losses array for plotting
Then we call ``train`` many times and occasionally print the progress (%
of examples, time so far, estimated time) and average loss.
"""
def trainIters(encoder, decoder, n_iters, print_every=1000, plot_every=100, learning_rate=0.01):
start = time.time()
plot_losses = []
print_loss_total = 0 # Reset every print_every
plot_loss_total = 0 # Reset every plot_every
encoder_optimizer = optim.SGD(encoder.parameters(), lr=learning_rate)
decoder_optimizer = optim.SGD(decoder.parameters(), lr=learning_rate)
training_pairs = [tensorsFromPair(random.choice(pairs))
for i in range(n_iters)]
criterion = nn.NLLLoss()
for iter in range(1, n_iters + 1):
training_pair = training_pairs[iter - 1]
input_tensor = training_pair[0]
target_tensor = training_pair[1]
loss = train(input_tensor, target_tensor, encoder,
decoder, encoder_optimizer, decoder_optimizer, criterion)
print_loss_total += loss
plot_loss_total += loss
if iter % print_every == 0:
print_loss_avg = print_loss_total / print_every
print_loss_total = 0
print('%s (%d %d%%) %.4f' % (timeSince(start, iter / n_iters),
iter, iter / n_iters * 100, print_loss_avg))
if iter % plot_every == 0:
plot_loss_avg = plot_loss_total / plot_every
plot_losses.append(plot_loss_avg)
plot_loss_total = 0
showPlot(plot_losses)
"""### Plotting results
Plotting is done with matplotlib, using the array of loss values
``plot_losses`` saved while training.
**Q5. Complete the implementation of the `showPlot` function**
"""
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
def showPlot(points):
plt.figure()
fig, ax = plt.subplots()
# this locator puts ticks at regular intervals
loc = ticker.MultipleLocator(base=0.2)
ax.yaxis.set_major_locator(loc)
plt.plot(points)
"""## Evaluation
Evaluation is mostly the same as training, but there are no targets so
we simply feed the decoder's predictions back to itself for each step.
Every time it predicts a word we add it to the output string, and if it
predicts the EOS token we stop there. We also store the decoder's
attention outputs for display later.
**Q6. Complete the implementation of the `evaluate` function**
"""
def evaluate(encoder, decoder, sentence, max_length=MAX_LENGTH):
with torch.no_grad():
input_tensor = tensorFromSentence(input_lang, sentence)
input_length = input_tensor.size()[0]
encoder_hidden = encoder.initHidden()
encoder_outputs = torch.zeros(max_length, encoder.hidden_size, device=device)
for ei in range(input_length):
encoder_output, encoder_hidden = encoder(input_tensor[ei],
encoder_hidden)
encoder_outputs[ei] += encoder_output[0, 0]
decoder_input = torch.tensor([[SOS_token]], device=device) # SOS
decoder_hidden = encoder_hidden
decoded_words = []
decoder_attentions = torch.zeros(max_length, max_length)
for di in range(max_length):
decoder_output, decoder_hidden, decoder_attention = decoder(
decoder_input, decoder_hidden, encoder_outputs)
decoder_attentions[di] = decoder_attention.data
topv, topi = decoder_output.data.topk(1)
if topi.item() == EOS_token:
decoded_words.append('<EOS>')
break
else:
decoded_words.append(output_lang.index2word[topi.item()])
decoder_input = topi.squeeze().detach()
return decoded_words, decoder_attentions[:di + 1]
"""We can evaluate random sentences from the training set and print out the
input, target, and output to make some subjective quality judgements:
"""
def evaluateRandomly(encoder, decoder, n=10):
for i in range(n):
pair = random.choice(pairs)
print('>', pair[0])
print('=', pair[1])
output_words, attentions = evaluate(encoder, decoder, pair[0])
output_sentence = ' '.join(output_words)
print('<', output_sentence)
print('')
"""## Putting it all together
With all these helper functions in place (it looks like extra work, but
it makes it easier to run multiple experiments) we can actually
initialize a network and start training.
Remember that the input sentences were heavily filtered. For this small
dataset we can use relatively small networks of 256 hidden nodes and a
single GRU layer. After about 40 minutes on a MacBook CPU we'll get some
reasonable results.
"""
hidden_size = 256
encoder1 = EncoderRNN(input_lang.n_words, hidden_size).to(device)
attn_decoder1 = AttnDecoderRNN(hidden_size, output_lang.n_words, dropout_p=0.1).to(device)
trainIters(encoder1, attn_decoder1, 75000, print_every=5000)
evaluateRandomly(encoder1, attn_decoder1)
"""### Visualizing Attention
A useful property of the attention mechanism is its highly interpretable
outputs. Because it is used to weight specific encoder outputs of the
input sequence, we can imagine looking where the network is focused most
at each time step.
You could simply run ``plt.matshow(attentions)`` to see attention output
displayed as a matrix, with the columns being input steps and rows being
output steps:
"""
output_words, attentions = evaluate(
encoder1, attn_decoder1, "je suis trop froid .")
plt.matshow(attentions.numpy())
plt.show()
"""For a better viewing experience we will do the extra work of adding axes
and labels:
**Q7. Complete the implementation of the `showAttention` function**
"""
def showAttention(input_sentence, output_words, attentions):
# Set up figure with colorbar
fig = plt.figure()
ax = fig.add_subplot(111)
cax = ax.matshow(attentions.numpy(), cmap='bone')
fig.colorbar(cax)
# Set up axes
ax.set_xticklabels([''] + input_sentence.split(' ') +
['<EOS>'], rotation=90)
ax.set_yticklabels([''] + output_words)
# Show label at every tick
ax.xaxis.set_major_locator(ticker.MultipleLocator(1))
ax.yaxis.set_major_locator(ticker.MultipleLocator(1))
plt.show()
def evaluateAndShowAttention(input_sentence):
output_words, attentions = evaluate(
encoder1, attn_decoder1, input_sentence)
print('input =', input_sentence)
print('output =', ' '.join(output_words))
showAttention(input_sentence, output_words, attentions)
evaluateAndShowAttention("elle a cinq ans de moins que moi .")
evaluateAndShowAttention("elle est trop petit .")
evaluateAndShowAttention("je ne crains pas de mourir .")
evaluateAndShowAttention("c est un jeune directeur plein de talent .")