razvanc92
razvanc92
I've been trying to run the MATR example, and from the first iteration I'm receving validation error "nan", as a consequence the model stops learning after 10 iterations. Is there...
Hello, firstly I would like to thank you for sharing the code. I was looking at the Spatial Attention component (line 56 in model.py) and I've noticed some differences from...
Hello, I was curios when do you plan to release the datasets, I'm interested in using them as well. Thank you in advance.
Hello, firstly I would like to thank you for the implementation. I've been trying to use your implementation and I've noticed a big difference, during training when evaluating (fx every...
I ran your implementation with a slightly different configuration (different dataset) and when using num_nodes: 87, enc_input_dim:1 your implementation has 223169 parameters while the original implementation with the same configuration...
Hello and thank you for releasing the code, I was curios if you have an estimated time for when the pytorch version will be released.
Small thing on line 75 in utils.py you should add the encoding type otherwise it will not work for python 3+. objects.append(pkl.load(f, encoding='latin1')) Thanks for sharing the implementation. Cheers.
Hello, I've been looking at the testing procedure (test_model.py) and there are some things which are not clear to me. I can see that you fine-tune the model on the...
Hello,thank you for the implementation. I've tried to run the code and I'm receiving this error: ValueError: slice index 0 of dimension 1 out of bounds. for 'predcnn/strided_slice_10' (op: 'StridedSlice')...