AI Enthusiast

@Yshihui 支持的算子有列表可查看吗？

@shocoladka will this bug be fixed in the new release? When? good news

@shocoladka thanks

I can convert one-layer LSTM and multilayer LSTMs to tensorflow (onnx 1.7.0, onnx-tf 1.7.0 ). However, the results between onnx and onnx-tf are not equal when using multi-layer LSTM, while...

@chist have you figured out a solution?

> You can try to process the dataset as a sequence of `.png` frames (use `--format .png` when running [load_videos.py](https://github.com/AliaksandrSiarohin/video-preprocessing/blob/master/load_videos.py)), so that you only need to read two png images...

> OK, thanks a lot. Got it

Thanks, I got it...

Thanks for your nice work. +1 request.

> Sorry for the mistake, `train.py` file has been released and the training configs in yaml have been fixed. Good job~ Thanks.