Hi everyone,
does anyone know a solution for this Error? I am trying to switch my PyTorch network to an Federated Learning network but i always get this Error.
I’m using Google Colab an train on GPU. When I print the size of embeds I get 0, but I don’t understand why the data is not used there.
RuntimeError Traceback (most recent call last)
<ipython-input-42-fd4a5223524b> in <module>()
----> 1 model, history = train_model(net, dataloaders_dict, criterion, optimizer, num_epochs=10)
2 #model = train_model(net, dataloaders_dict, criterion, optimizer, num_epochs=10)
6 frames
<ipython-input-41-a386f044d41f> in train_model(model, dataloaders, criterion, optimizer, num_epochs, batch_size)
68 # detaching it from its history on the last instance.
69
---> 70 outputs = model(inputs)
71
72 loss = criterion(outputs, labels)
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
530 result = self._slow_forward(*input, **kwargs)
531 else:
--> 532 result = self.forward(*input, **kwargs)
533 for hook in self._forward_hooks.values():
534 hook_result = hook(self, input, result)
<ipython-input-36-64e9a7d68b11> in forward(self, sentence)
11 def forward(self, sentence):
12 embeds = self.word_embeddings(sentence)
---> 13 lstm_out, (h,t) = self.lstm(embeds)
14 lstm_out = self.dropout(lstm_out)
15 tag_space = self.output(lstm_out[:,-1,:])
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
530 result = self._slow_forward(*input, **kwargs)
531 else:
--> 532 result = self.forward(*input, **kwargs)
533 for hook in self._forward_hooks.values():
534 hook_result = hook(self, input, result)
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py in forward(self, input, hx)
554 hx = self.permute_hidden(hx, sorted_indices)
555
--> 556 self.check_forward_args(input, hx, batch_sizes)
557 if batch_sizes is None:
558 result = _VF.lstm(input, hx, self._flat_weights, self.bias, self.num_layers,
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py in check_forward_args(self, input, hidden, batch_sizes)
506 def check_forward_args(self, input, hidden, batch_sizes):
507 # type: (Tensor, Tuple[Tensor, Tensor], Optional[Tensor]) -> None
--> 508 self.check_input(input, batch_sizes)
509 expected_hidden_size = self.get_expected_hidden_size(input, batch_sizes)
510
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py in check_input(self, input, batch_sizes)
157 raise RuntimeError(
158 'input.size(-1) must be equal to input_size. Expected {}, got {}'.format(
--> 159 self.input_size, input.size(-1)))
160
161 def get_expected_hidden_size(self, input, batch_sizes):
RuntimeError: input.size(-1) must be equal to input_size. Expected 200, got 0
class LSTM(nn.Module):
def __init__(self, embedding_dim, hidden_layers,vocab_size,num_layers,pretrained_weights):
super(LSTM, self).__init__()
self.word_embeddings = nn.Embedding(vocab_size, embedding_dim,_weight=pretrained_weights, padding_idx=0)
self.lstm = nn.LSTM(embedding_dim, hidden_size=hidden_layers,num_layers=num_layers, batch_first=True)
self.output = nn.Linear(hidden_layers, vocab_size, bias=False)
self.dropout = nn.Dropout(0.1)
def forward(self, sentence):
embeds = self.word_embeddings(sentence)
lstm_out, (h,t) = self.lstm(embeds)
lstm_out = self.dropout(lstm_out)
tag_space = self.output(lstm_out[:,-1,:])
return tag_space
The Error throws in this line: lstm_out, (h,t) = self.lstm(embeds)
for epoch in range(num_epochs):
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
train_loss = 0
acc_score = 0
valid_loss = 0
acc_valid_score = 0
#Variables to store the losses temporary
train_loss_result = 0
acc_score_result = 0
valid_loss_result = 0
acc_valid_score_result = 0
valid_loss_not_decreased = 0
if valid_loss_not_decreased == 5:
break
# Each epoch has a training and validation phase
for phase in ['train', 'val']:
if phase == 'train':
model.train() # Set model to training mode
else:
model.eval() # Set model to evaluate mode
for inputs,labels in dataloaders[phase]:
# Location of current batch
worker = inputs.location # <---- Where will send the model to
#model.to(device)
model = model.send(worker) # <---- for Federated Learning
inputs, labels = inputs.to(device), labels.to(device)
print("--------> INPUT: ",inputs)
print("--------> LABEL: ",labels)
# zero the parameter gradients
optimizer.zero_grad()
# forward
# track history if only in train
with torch.set_grad_enabled(phase == 'train'):
# Get model outputs and calculate loss
# backward + optimize only if in training phase
if phase == 'train':
# we need to clear out the hidden state of the LSTM,
# detaching it from its history on the last instance.
outputs = model(inputs)
loss = criterion(outputs, labels)
acc = binary_accuracy(outputs,labels)
acc_score = acc_score + acc
train_loss = train_loss + loss.item()
loss.backward()
optimizer.step()
