jokieleung / cl-vqa

the implementation of EMNLP 2020 "Learning to Contrast the Counterfactual Samples for Robust Visual Question Answering"

Hi 👋, I'm Zujie Liang

Welcome! You are the visitor!

• 😄 Hi there, this is Zujie Liang (or "Jokie Leung" in Cantonese). I am a master student at Sun Yat-Sen University (SYSU).
• 🔭 My research interest includes Natural Language Processing, Machine Learning, and Computer Vision.
• 👯 I am open to collaboration on research, feel free to contact me via E-mail!
• ⚡ Please check my homepage for my CV and latest update!

cl-vqa's Issues

pretrained model to reproduce the results

Thanks for sharing your work with us.

I will be grateful if you share the pretrained model with us so I can reproduce the results and I can edit the code.

Thanks again.

只是python3 有难度，按照python2.7 xp卡+torch1.1.0+torchvision0.3.0可以运行

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [512, 2048]], which is output 0 of ReluBackward0, is at version 1; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True)

File path confusing

Dear author, will you please tell us waht is the file path, in class VQAFeatureDataset, such as 'data/train_cpv2_hintscore.json' stands for? And where can i get this file, please?
Thasnks very much for your generous explanations.