Howardqlz

icon indicating an email [email protected]

icon company Fudan university

Results 5 comments of Howardqlz

RuntimeError: Expected object of backend CUDA but got backend CPU for argument #3 'index'

I met the same problem. I fix it like this: `p = self.word_emb([kwargs['p'].cuda(self.args.gpu)])`

About the training step

I just want to use your model as a pretrained model to finetune on my own dataset. Wish your reply if you have time to explain the training step about...

the performance in squad2.0

how about dcn+ performs on SQuAD2.0?Can f1 or em reaches 50%?And it's seem that the model runs an epoch needs 3hours，i don't know it's correct or not(the f1 and em...

ffi import error

i have met the same problem. This repo depend on [this repo](https://github.com/jwyang/faster-rcnn.pytorch), it seems like we should set an environment like torch 0.4.0, cuda 8.0. I use cuda 9.0 still...

Only pdf and label is available to train and test，is this method still work?

I wonder the render layers need us to generate or can generate by your code