Saurabh Kumar

You need to get rid of the `_` after id and the last `_` . Assuming parent directory is named fashion as mentioned earlier, in ubuntu I did this: *...

If anyone needs it I have a working example of the model here : https://colab.research.google.com/drive/15uGzI5adMsZ7mIfVsr3Ruda25JswraPU?usp=sharing

Setting `debug = True` does not solve the problem entirely, it shows the error in ns3 simulation script but stays there forever. To handle runtime errors in the simulation script...

The problem is with libzmq version. Ubuntu 18.04 has older version which causes the error, version 20.04 has more recent version that works. A simple solution is to add 20.04...

What datasets and loss functions did you use? There is also [UCFRep dataset](https://github.com/Xiaodomgdomg/Deep-Temporal-Repetition-Counting).

Given limited data, the model is bound to overfit. Use other datasets, the `SyntheticDataset` class implements the technique mentioned in the paper. There are some videos from kinetics dataset in...

Yes, although when y1 < 1e-1 gradient won't flow at all, because y2>0 is not differentiable and 1e-1 is constant. You want the loss to be a differentiable function of...

The [PCSegRGB-Sep-Disc](https://github.com/ofnote/TryOnGAN/tree/PCSegRGB-Sep-Disc) branch has some changes that handle seg maps. The exact reason is a combination of all the reasons you mentioned. :) The description was not clear so I...

The `Model.py` file was old, I have updated it. Some of the trained checkpoints are [here](https://drive.google.com/drive/folders/1uYJQTMR6gRXzFVbCfMREv940iLfk27oK?usp=sharing). The notebook that I am using locally is [here](https://drive.google.com/file/d/1sB6SNneHHe6gMgD748uf8cWtfBM7M_qt/view?usp=sharing). Note that for long videos...

>I test your model, the effect is not as good as the paper 's model The checkpoints that I linked were not trained exhaustively. There is room for improvement by...