Ji Zhang comments

Results 8 comments of


                                            Ji Zhang

error when computing return_dict['losses'][k] = v.unsqueeze(0)

Hi @ShuangLI59, I believe it is a pytorch version issue. Please make sure you are using pytorch0.4.0 or 0.4.1. BTW, I'll update a version with support for pytorch1.0 very soon....

error when computing return_dict['losses'][k] = v.unsqueeze(0)

Hi @czqInNanjing, Good catch! Thank you for the correction. I've updated model_builder_rel.py accordingly.

How to get the visual result of the feature map in the paper?

Hi @waallf, I don't have the visualization script at hand, but it's not hard at all, you just need to obtain the output of the last convolution layer from the...

How exactly do you download word2vec vocabulary?

Hi @dmitriy-serdyuk, Here is an alternative link that works for me: https://drive.google.com/file/d/0B7XkCwpI5KDYNlNUTTlSS21pQmM/edit

Runtime error during evaluation

Hi everyone, Sorry for the late reply. I've updated the link which contains a compatible VGG16 that gives a results on par with the paper. You can also download it...

Runtime error during evaluation

Hi @cao-nv, Yes I confirm that these are the valid reproduced results. A little suggestion of mine: if you want to compare with our method, these results are definitely OK;...

Runtime error during evaluation

@cao-nv It should be OK if you do export CUDA_VISIBLE_DEVICES= where g1,g2 are the indices of the GPUs you want to use, and you can set any number of these...

Index out of range for pretrained model

Hi @Prudhvinik1, I think this is probably an issue of the environment that you are using. I have seen this before when someone else in a company tries to run...