MILVLG/mcan-vqa

single question test

miao404 opened this issue · 3 comments

miao404 commented

I am trying to do a single question test, so I reduce the test_question.json to one picture and one question, and I encounter this problem:
RuntimeError: Error(s) in loading state_dict for Net: size mismatch for embedding.weight: copying a param with shape torch.Size([20572, 300]) from checkpoint, the shape in current model is torch.Size([18405, 300]).

Do you know how to fix this ? or the test_question.json is just stable which I cannot modify the scale of the pictures and the questions?

Can you give me some suggestions about how to test single question in single picture ?

Thanks a lot.

MIL-VLG commented

This may be due to the vocabulary size for the question. Have you changed the config for the training vocab (or split)?

GaoKangYu commented

This may be due to the vocabulary size for the question. Have you changed the config for the training vocab (or split)?

I met the same problem, how can I test single question in single picture ?

Whitch .py file and how to changed the config for the training vocab (or split) ?

Thanks a lot.

MIL-VLG commented

This repo does not support such single image testing.