HTseng

Hi, thank you for reporting a problem running on Windows. Long time ago I seemed to notice there's a difference running Pytorch codes on Windows & Linux. Since now I...

yeah, I noticed the problem until you mentioned this now, thank you for that. I may find some time to adjust the splitting and rerun the experiments, but in terms...

yes I had it sometime before, allow me to take a few days to find it

Please check out the files in the folder **ResNetCRNN_varylength** and run _UCF101_ResNetCRNN_varlen.py_. This necessarily takes longer time to load and run. Let me know if there's any bug spotted, thanks!

Happy new year! Thanks for the error message. May I ask what versions are your packages running? eg. numpy, pandas, scikit-learn, pytorch?

Hi, the 1.02% accuracy is in training or testing? have you adjusted the default parameters? it's possible to have this accuracy if the learning rate is not proper. Also in...

As far as I know it, this is probably because the samples you put may be too few. Just increase the sample size and this error should go away. This...

Hi, I posted my pretrained CRNN model [here](https://drive.google.com/open?id=1uXQFvqmOWzJLsAaXUOjoPhje790Ub19S) with about 41% accuracy on testing data at epoch 36. Please note that you need to reload this pretrained weights with only...

Good to know that the parameter works! thanks for the update. Sure, I actually have the code of variable length, just need to organize better and test it. Will let...

yes, in order to have fixed size tensors as inputs for CNNs.