Biao Zhang

`pip3 install lingvo` works for python3.6, but fails on python3.7, in my case.

@avinashsai Thanks for pointing this out. 1. The PyTorch (rmsnorm_torch) and TensorFlow (rmsnorm_tensorflow) code do *NOT* consider the case of CNN. By default, the code can be used for RNN,...

Hey @dongxiao92, we just released the models for dgs3-t (https://data.statmt.org/bzhang/iclr2023_sltunet/). Please check it out, and let me know if you have any further questions.

Hey, the logging information is a little bit confusing here. The `pretrained model` here doesn't mean the pretrained sign embeddings, but pretrained SLT model. so it's normal and not a...

This could be checked by inspecting the source_train_file and the resulted train.h5. Could you please show a few lines in your train file? and also read train.h5 with h5py and...

could you please list some keys from your `train.h5`? e.g. 5142_8 is missing based on the error, then could you please take a look what keys for 5142 are contained...

Hey @Lulo187, Re software, As mentioned [here](https://github.com/bzhangGo/sltunet?tab=readme-ov-file#requirement), we used python 3.8 and tensorflow 1.15 (which was based on nvidia-tensorflow). I'm not sure about other details now, though. Re hardware, The...

For inference, "ref" part is meaningless becuase it's not used at all. The code may need a reference file to load the input properly. In this case, you can feed...

Hey @tzjg7293, you could try install tensorflow supported by nvidia instead. See more details at https://github.com/NVIDIA/tensorflow

Hey @XinS0909, there seems to be an update in another repository; could you please try [this dgs.json](https://github.com/sign-language-processing/datasets/blob/master/sign_language_datasets/datasets/dgs_corpus/dgs.json) instead?