S. Ging

Also check the locale of your system, on Linux `echo $LANG` should output `en_US.UTF-8`.

Confirmed. Another workaround is putting the css string at the end. Error: ~~~ const ErrorDiv = styled.div` ${(props: {}) => css` color: red; `} color: blue; `; ~~~ No Error:...

I also have some questions about TVQA finetuning as I am trying to reproduce your results. 1. Do you use the ground-truth timestamps of the question to select frames from...

The pretrained models only understand english, for chinese you will have to train everything from scratch: Train retrieval, extract features, train captioning.

Yes, that is correct

Hi, I suggest you try regular installation with conda: `python=3.8.5` and `pytorch=1.7.1` with installation as described on the pytorch homepage, then `pip install -r requirements.txt`. You don't need `torchaudio` Best

If you have solved it, please consider posting your fix for others.

Does it still happen? If yes please post a complete bug report: Which command do you input, the complete error message, output of system command "nvidia-smi", which system / python...

I will check this problem, it should be possible to train on multiple GPUs. Other than that, unless you increase the model size or batch size, a single 12GB GPU...

Hi, so first of all TransformerXL is not officially supported by this repo and not tested well. That being said, reasons for NaN can be: - Float16 training doesn't work...