Claudio

@brunoalr good point. I'm working on a mac+lldb port that defines a clear and concise interface for the "symbol" object provided to the giwtype and want to keep it as...

Hi @zhujiagang, thank you so much for your swift replies! I'm currently working on reproducing the training with the `hmdb_scripts_split_1/train_rgb_tpp_delete_dropout_split_1.sh` script on a Titan X. I had a few issues...

Hello @zhujiagang, thanks again for your clear answer! I probably needed to set `new_width` and `new_height` because I extracted myself the frames of the dataset using ffmpeg. When I proceeded...

I see! The `eval_scores_rgb_flow.py` complained about some missing `.npz` files, so I guess I should have changed the `save_scores` variable in the `eval_tpp_net_hmdb.py` script, right? So the whole process should...

Thank you @zhujiagang! I was able to reproduce the results of the paper with ~73% accuracy with the fusion model. Now I'm trying to use the Kinects pre trained model...

Nice, thank you! I can confirm that the issue has been solved. Great job! I have one suggestion related to the clone issue. It appears that you can only clone...

Not sure you've had the same issue as me, but this seems to have fixed it for me: e4eebae522e2e6fc9448de12a8a15e924ed684e9