Hey guys, I am newbie over here, and I am trying to use some frankensteined pytorch code to create a sentiment analysis using CNN for a final project. I’ve been getting mistakes and fixing them, but I really can’t figure out this one and all the explanations involve really complicated mathematical things. Any help is extremely appreciated.
BATCH_SIZE = 64
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
train_iterator, valid_iterator, test_iterator = data.BucketIterator.splits(
(train_data, valid_data, test_data),
batch_size = BATCH_SIZE,
device = device)
import torch.nn as nn
import torch.nn.functional as F
class CNN(nn.Module):
def __init__(self, vocab_size, embedding_dim, n_filters, filter_sizes, output_dim,
dropout, pad_idx):
super().__init__()
self.embedding = nn.Embedding(vocab_size, embedding_dim, padding_idx = pad_idx)
self.convs = nn.ModuleList([
nn.Conv2d(in_channels = 1,
out_channels = n_filters,
kernel_size = (fs, embedding_dim))
for fs in filter_sizes
])
self.fc = nn.Linear(len(filter_sizes) * n_filters, output_dim)
self.dropout = nn.Dropout(dropout)
def forward(self, text):
#text = [sent len, batch size]
text = text.permute(1, 0)
#text = [batch size, sent len]
embedded = self.embedding(text)
#embedded = [batch size, sent len, emb dim]
embedded = embedded.unsqueeze(1)
#embedded = [batch size, 1, sent len, emb dim]
conved = [F.relu(conv(embedded)).squeeze(3) for conv in self.convs]
#conv_n = [batch size, n_filters, sent len - filter_sizes[n]]
pooled = [F.max_pool1d(conv, conv.shape[2]).squeeze(2) for conv in conved]
#pooled_n = [batch size, n_filters]
cat = self.dropout(torch.cat(pooled, dim = 1))
#cat = [batch size, n_filters * len(filter_sizes)]
return self.fc(cat)
INPUT_DIM = len(TWEET.vocab)
EMBEDDING_DIM = 20
N_FILTERS = 100
FILTER_SIZES = [3,4,5]
OUTPUT_DIM = 1
DROPOUT = 0.5
PAD_IDX = TWEET.vocab.stoi[TWEET.pad_token]
model = CNN(INPUT_DIM, EMBEDDING_DIM, N_FILTERS, FILTER_SIZES, OUTPUT_DIM, DROPOUT, PAD_IDX)
def count_parameters(model):
return sum(p.numel() for p in model.parameters() if p.requires_grad)
print(f'The model has {count_parameters(model):,} trainable parameters')
embeddings = TWEET.vocab.vectors
model.embedding.weight.data.copy_(embeddings)
UNK_IDX = TWEET.vocab.stoi[TWEET.unk_token]
model.embedding.weight.data[UNK_IDX] = torch.zeros(EMBEDDING_DIM)
model.embedding.weight.data[PAD_IDX] = torch.zeros(EMBEDDING_DIM)
import torch.optim as optim
optimizer = optim.Adam(model.parameters())
criterion = nn.BCEWithLogitsLoss()
model = model.to(device)
criterion = criterion.to(device)
def binary_accuracy(preds, y):
rounded_preds = torch.round(torch.sigmoid(preds))
correct = (rounded_preds == y).float()
acc = correct.sum() / len(correct)
return acc
def train(model, iterator, optimizer, criterion):
epoch_loss = 0
epoch_acc = 0
model.train()
for batch in iterator:
optimizer.zero_grad()
predictions = model(batch.tweet).squeeze(1)
loss = criterion(predictions, batch.label)
acc = binary_accuracy(predictions, batch.label)
loss.backward()
optimizer.step()
epoch_loss += loss.item()
epoch_acc += acc.item()
return epoch_loss / len(iterator), epoch_acc / len(iterator)
def evaluate(model, iterator, criterion):
epoch_loss = 0
epoch_acc = 0
model.eval()
with torch.no_grad():
for batch in iterator:
predictions = model(batch.tweet).squeeze(1)
loss = criterion(predictions, batch.label)
acc = binary_accuracy(predictions, batch.label)
epoch_loss += loss.item()
epoch_acc += acc.item()
return epoch_loss / len(iterator), epoch_acc / len(iterator)
import time
def epoch_time(start_time, end_time):
elapsed_time = end_time - start_time
elapsed_mins = int(elapsed_time / 60)
elapsed_secs = int(elapsed_time - (elapsed_mins * 60))
return elapsed_mins, elapsed_secs
N_EPOCHS = 10
FREEZE_FOR = 5
best_valid_loss = float('inf')
#freeze embeddings
model.embedding.weight.requires_grad = unfrozen = False
for epoch in range(N_EPOCHS):
start_time = time.time()
train_loss, train_acc = train(model, train_iterator, optimizer, criterion)
valid_loss, valid_acc = evaluate(model, valid_iterator, criterion)
end_time = time.time()
epoch_mins, epoch_secs = epoch_time(start_time, end_time)
print(f'Epoch: {epoch+1:02} | Epoch Time: {epoch_mins}m {epoch_secs}s | Frozen? {not unfrozen}')
print(f'\tTrain Loss: {train_loss:.3f} | Train Acc: {train_acc*100:.2f}%')
print(f'\t Val. Loss: {valid_loss:.3f} | Val. Acc: {valid_acc*100:.2f}%')
if valid_loss < best_valid_loss:
best_valid_loss = valid_loss
torch.save(model.state_dict(), 'tutC-model.pt')
if (epoch + 1) >= FREEZE_FOR:
#unfreeze embeddings
model.embedding.weight.requires_grad = unfrozen = True
ValueError Traceback (most recent call last)
<ipython-input-30-10509ec63b58> in <module>()
11 start_time = time.time()
12
---> 13 train_loss, train_acc = train(model, train_iterator, optimizer, criterion)
14 valid_loss, valid_acc = evaluate(model, valid_iterator, criterion)
15
3 frames
<ipython-input-27-80e3304debd7> in train(model, iterator, optimizer, criterion)
12 predictions = model(batch.tweet).squeeze(1)
13
---> 14 loss = criterion(predictions, batch.label)
15
16 acc = binary_accuracy(predictions, batch.label)
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
548 result = self._slow_forward(*input, **kwargs)
549 else:
--> 550 result = self.forward(*input, **kwargs)
551 for hook in self._forward_hooks.values():
552 hook_result = hook(self, input, result)
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/loss.py in forward(self, input, target)
615 self.weight,
616 pos_weight=self.pos_weight,
--> 617 reduction=self.reduction)
618
619
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in binary_cross_entropy_with_logits(input, target, weight, size_average, reduce, reduction, pos_weight)
2431
2432 if not (target.size() == input.size()):
-> 2433 raise ValueError("Target size ({}) must be the same as input size ({})".format(target.size(), input.size()))
2434
2435 return torch.binary_cross_entropy_with_logits(input, target, weight, pos_weight, reduction_enum)
ValueError: Target size (torch.Size([60])) must be the same as input size (torch.Size([66]))