Error with Image captioning

[mhsamavatian]

When I Run the evaluation command
python sample.py --image='png/example.png'

I got this error

Traceback (most recent call last):
File "sample.py", line 97, in
main(args)
File "sample.py", line 61, in main
sampled_ids = decoder.sample(feature)
File "/users/PAS1273/osu8235/pytorch/pytorch-tutorial/tutorials/03-advanced/image_captioning/model.py", line 62, in sample
hiddens, states = self.lstm(inputs, states) # (batch_size, 1, hidden_size),
File "/users/PAS1273/osu8235/.local/lib/python2.7/site-packages/torch/nn/modules/module.py", line 224, in call
result = self.forward(*input, **kwargs)
File "/users/PAS1273/osu8235/.local/lib/python2.7/site-packages/torch/nn/modules/rnn.py", line 162, in forward
output, hidden = func(input, self.all_weights, hx)
File "/users/PAS1273/osu8235/.local/lib/python2.7/site-packages/torch/nn/_functions/rnn.py", line 351, in forward
return func(input, *fargs, **fkwargs)
File "/users/PAS1273/osu8235/.local/lib/python2.7/site-packages/torch/autograd/function.py", line 284, in _do_forward
flat_output = super(NestedIOFunction, self)._do_forward(*flat_input)
File "/users/PAS1273/osu8235/.local/lib/python2.7/site-packages/torch/autograd/function.py", line 306, in forward
result = self.forward_extended(*nested_tensors)
File "/users/PAS1273/osu8235/.local/lib/python2.7/site-packages/torch/nn/_functions/rnn.py", line 293, in forward_extended
cudnn.rnn.forward(self, input, hx, weight, output, hy)
File "/users/PAS1273/osu8235/.local/lib/python2.7/site-packages/torch/backends/cudnn/rnn.py", line 208, in forward
'input must have 3 dimensions, got {}'.format(input.dim()))
RuntimeError: input must have 3 dimensions, got 2

[jysenj]

i got this to, have you fixed it?

[mhsamavatian]

Modify sample function in model.py like below
I added 'inputs = inputs.unsqueeze(1)' in last like of for loop and changed sampled_ids = torch.cat(sampled_ids, 1) to sampled_ids = torch.cat(sampled_ids, 0)

---

`def sample(self, features, states=None):

    """Samples captions for given image features (Greedy search)."""
    sampled_ids = []
    inputs = features.unsqueeze(1)
    for i in range(20):                                      # maximum sampling length
        hiddens, states = self.lstm(inputs, states)          # (batch_size, 1, hidden_size), 
        outputs = self.linear(hiddens.squeeze(1))            # (batch_size, vocab_size)
        predicted = outputs.max(1)[1]
        sampled_ids.append(predicted)
        inputs = self.embed(predicted)
        inputs = inputs.unsqueeze(1)
    sampled_ids = torch.cat(sampled_ids, 0)                  # (batch_size, 20)
    return sampled_ids.squeeze()`

[yunjey]

@mhsamavatian Thanks, you are right. I updated the code :-)

[WangWenshan]

However, I have an error when I do that:
runtimeerror input must have 3 dimensions, got 4

[autogyro]

Hi there
I am also meet that problem, and then I add the 'inputs = inputs.unsqueeze(1)',

def sample(self, features, states=None):
    """Samples captions for given image features (Greedy search)."""
    sampled_ids = []
    inputs = features.unsqueeze(1)
    for i in range(20):                                      # maximum sampling length
        hiddens, states = self.lstm(inputs, states)          # (batch_size, 1, hidden_size), 
        outputs = self.linear(hiddens.squeeze(1))            # (batch_size, vocab_size)
        predicted = outputs.max(1)[1]
        sampled_ids.append(predicted)
        inputs = self.embed(predicted)
        inputs = inputs.unsqueeze(1)
    sampled_ids = torch.cat(sampled_ids, 1)                  # (batch_size, 20)
    return sampled_ids.squeeze()

---

but, I got the following:
File "D:\Dev\image_captioning\model.py", line 134, in sample

sampled_ids = torch.cat(sampled_ids, 1) # (batch_size, 20)

RuntimeError: Dimension out of range (expected to be in range of [-1, 0], but got 1)