DenisDsh

CORAL loss is defined differently from the original paper

9

I noticed that both the covariance and the Frobenius norm are computed differently in your implementation. You compute the Frobenius norm as below: ` # frobenius norm between source and...

In the[ LSTM documentation]( https://pytorch.org/docs/stable/nn.html#torch.nn.LSTM) is specified that we should feed to the RNN inputs of shape (seq_len, batch, input_size) however it seems to me that we are feeding inputs...

In vqa_processed.py, encode_question fails (index out of range) when the padding desired is 'left' and the question length is larger than the maximum length. A possible fix is to replace...