Siqi

Can you post the command you use to run demo.py, and the result of "ls" command under data folder? Thanks!

Sorry for now the only language we support is English. However I believe you could train with any other language(s) with the code base. However, you need to train from...

Hi dimeldo, Thanks for your comments. Regarding your question 1. Though we try to make variable name as intuitive as possible, it may still look vague, so we will definitely...

Yes. No, we provided the pre-trained model so you don't have to train it again by yourself. Please refer to our README about how to download those pre-trained models. But...

Due to nature of large dataset, we use prepro.py to preprocess raw data (formatted like train_raw.tsv) and output data into multiple chunks... For detailed format please refer to line 56...

Our model was trained on multiple GPU without issues, it might be a display issue related to progress bar, or different version of apex... So can you try with a...

Hi vsahil, can you check your dataloader's output's shape? The problem might come from dataloader as well. For example, if you have 5 data and set batch_size as 4, your...

Yep, you can simply change the config setting, please see [https://github.com/intersun/LightningDOT/blob/5f2880f69ba87b8701ab89348d70ebb11432578c/dvl/models/bi_encoder.py#L423](url) for more details. Thanks!

From the loss curve it looks like it ran successfully in first 6 epochs, and suddenly the loss blows up, which seems very similar to your previous issue. Can you...

Thanks @shivangibithel for your interests. Actually to successfully run the demo, you need to use the **extracted** image features as input, which is not available for now. Please check [https://github.com/ChenRocks/UNITER](url)...