hexiang-hu/answer_embedding

Code Release for `Learning Answer Embeddings for Visual Question Answering`. (CVPR 2018)

answer_embedding's Issues

hi, it seems that there are no WUPS method realized in codes which is mentioned in paper?

something wrong with "answer_vectors = default_collate(_answer_vectors)" in ansemb/dataset/data_utils.py

train E000: 0% 0/3467 [00:02<?, ?it/s]
Traceback (most recent call last):
File "train_vqa_embedding.py", line 266, in
main(args)
File "train_vqa_embedding.py", line 239, in main
train(context_net, answer_net, train_loader, optimizer, tracker, args, prefix='train', epoch=i)
File "train_vqa_embedding.py", line 108, in train
for v, q, avocab, a, labels, idx, q_len in tq:
File "/home/anaconda3/lib/python3.6/site-packages/tqdm/std.py", line 1130, in iter
for obj in iterable:
File "/home/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 345, in next
data = self._next_data()
File "/home/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data
return self._process_data(data)
File "/home/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data
data.reraise()
File "/home/anaconda3/lib/python3.6/site-packages/torch/_utils.py", line 394, in reraise
raise self.exc_type(msg)
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/anaconda3/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/home/anaconda3/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 47, in fetch
return self.collate_fn(data)
File "/home/answer_embedding-master/ansemb/dataset/data_utils.py", line 95, in collate_fn
answer_vectors = default_collate(_answer_vectors)
File "/home/anaconda3/lib/python3.6/site-packages/torch/utils/data/_utils/collate.py", line 55, in default_collate
return torch.stack(batch, 0, out=out)
TypeError: stack(): argument 'tensors' (position 1) must be tuple of Tensors, not Tensor

How to generate "vqa-resnet-14x14.h5"?

The training process requires file "vqa-resnet-14x14.h5", how it is generated?

How to generate the answer JSON file for test?

The VQA challenge requires uploading answer JSON file to their server for testing. However, I did not find related functions in your code, except the functions in dump_vqa_eval_json.py. Maybe I missed them ?