viyjy
viyjy
Hi, thanks for your interest in our paper. The reason is that the text encoder is the first six layers of BERT, while the fusion encoder is the last six...
Hi, thanks for your interest in our work. What kind of inference do you mean? Image-text retrieval tasks? In terms of putting the model on HuggingFace, I need to check...
I see. What't the difficulties of applying our current inference code on general VQA? [VQA.py](https://github.com/uta-smile/TCL/blob/main/VQA.py) cannot be used in your tasks?
The model will generate the answers using an answer decoder, isn't it? The only difference is that we constrain the answer decoder to only generate from the 3,192 candidate answers.
Thanks, I will try it out. BTW, can I first install `img2dataset` by "`pip install img2dataset`", then run `download.py` on Notebook? Or do I need to download `img2dataset.pex` then run...
Hi, I have upgraded the spark to the latest version, but it still doesn't work. I am using EMR notebook, it might be different from your tutorial? Thanks.
Thanks for your interest in our work. As shown in this [Line](https://github.com/uta-smile/TCL/blob/d6071b11f454030d68eabb345151dec07649f038/models/model_pretrain.py#L296), there is `~indices_replaced` to make sure only 10% are replaced by random word. You can reorder this line...
> You use the hyper parameters for DeepLab ResNet101 to train VGG16. I suggest you to first test the model I upload to make sure everything is correct. Yunsheng, would...
Got it. How about the SSL model? Thanks.