I am building a DecoderRNN using PyTorch (This is an image-caption decoder):
class DecoderRNN(nn.Module):
def __init__(self, embed_size, hidden_size, vocab_size):
super(DecoderRNN, self).__init__()
self.hidden_size = hidden_size
self.gru = nn.GRU(embed_size, hidden_size, hidden_size)
self.softmax = nn.LogSoftmax(dim=1)
def forward(self, features, captions):
print (features.shape)
print (captions.shape)
output, hidden = self.gru(features, captions)
output = self.softmax(self.out(output[0]))
return output, hidden
The data have the following shapes:
torch.Size([10, 200]) <- features.shape (10 for batch size)
torch.Size([10, 12]) <- captions.shape (10 for batch size)
Then I got the following errors. Any ideas what I missed here? Thanks!
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-2-76e05ba08b1d> in <module>()
44 # Pass the inputs through the CNN-RNN model.
45 features = encoder(images)
---> 46 outputs = decoder(features, captions)
47
48 # Calculate the batch loss.
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
323 for hook in self._forward_pre_hooks.values():
324 hook(self, input)
--> 325 result = self.forward(*input, **kwargs)
326 for hook in self._forward_hooks.values():
327 hook_result = hook(self, input, result)
/home/workspace/model.py in forward(self, features, captions)
37 print (captions.shape)
38 # features = features.unsqueeze(1)
---> 39 output, hidden = self.gru(features, captions)
40 output = self.softmax(self.out(output[0]))
41 return output, hidden
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
323 for hook in self._forward_pre_hooks.values():
324 hook(self, input)
--> 325 result = self.forward(*input, **kwargs)
326 for hook in self._forward_hooks.values():
327 hook_result = hook(self, input, result)
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/rnn.py in forward(self, input, hx)
167 flat_weight=flat_weight
168 )
--> 169 output, hidden = func(input, self.all_weights, hx)
170 if is_packed:
171 output = PackedSequence(output, batch_sizes)
/opt/conda/lib/python3.6/site-packages/torch/nn/_functions/rnn.py in forward(input, *fargs, **fkwargs)
383 return hack_onnx_rnn((input,) + fargs, output, args, kwargs)
384 else:
--> 385 return func(input, *fargs, **fkwargs)
386
387 return forward
/opt/conda/lib/python3.6/site-packages/torch/autograd/function.py in _do_forward(self, *input)
326 self._nested_input = input
327 flat_input = tuple(_iter_variables(input))
--> 328 flat_output = super(NestedIOFunction, self)._do_forward(*flat_input)
329 nested_output = self._nested_output
330 nested_variables = _unflatten(flat_output, self._nested_output)
/opt/conda/lib/python3.6/site-packages/torch/autograd/function.py in forward(self, *args)
348 def forward(self, *args):
349 nested_tensors = _map_variable_tensor(self._nested_input)
--> 350 result = self.forward_extended(*nested_tensors)
351 del self._nested_input
352 self._nested_output = result
/opt/conda/lib/python3.6/site-packages/torch/nn/_functions/rnn.py in forward_extended(self, input, weight, hx)
292 hy = tuple(h.new() for h in hx)
293
--> 294 cudnn.rnn.forward(self, input, hx, weight, output, hy)
295
296 self.save_for_backward(input, hx, weight, output)
/opt/conda/lib/python3.6/site-packages/torch/backends/cudnn/rnn.py in forward(fn, input, hx, weight, output, hy)
206 if (not is_input_packed and input.dim() != 3) or (is_input_packed and input.dim() != 2):
207 raise RuntimeError(
--> 208 'input must have 3 dimensions, got {}'.format(input.dim()))
209 if fn.input_size != input.size(-1):
210 raise RuntimeError('input.size(-1) must be equal to input_size. Expected {}, got {}'.format(
RuntimeError: input must have 3 dimensions, got 2
Your GRU input needs to be 3-dimensional:
input of shape (seq_len, batch, input_size): tensor containing the features of the input sequence.
Further you need to provide the hidden state (last encoder hidden state in this case) as second parameter:
self.gru(input, h_0)
Where input
is your actual input and h_0
the hidden state which needs to be 3-dimensional as well:
h_0 of shape (num_layers * num_directions, batch, hidden_size): tensor containing the initial hidden state for each element in the batch. Defaults to zero if not provided.