Panagiotis Braimakis

> First of all, thanks for sharing, and I have some questions: > > 1. In test.py, I make threshold=0.00055,some normal events and some abnormal events were obtained, but the...

I actually just noticed you used the mains below: def main() in /fbank_net/model_training/cross_entropy_pre_training/cross_entropy_train.py for pretraining and likewise in fbank_net/model_training/triplet_loss_fine_tuing/triplet_loss_train.py Should i assume there were no Jupiter notebooks ? thanks, pb

I had the same issues and reinstalled all my drivers and now FPS is 25-30/s. I think NVIDIA needs to embed on their drivers the CUDA and cuDNN packages. Too...

its too slow. with a GTX 1080 i get 12fps at best.

So that i understand.... if the split is done in such a way that the TESTING set has horse riding and the TRAINING set does not have, this does not...

there is a simple fix. just comment the Error exceptions.

This should work better. #!/bin/bash > train.list > test.list COUNT=-1 for folder in $1/* do echo $folder COUNT=$[$COUNT + 1] for imagesFolder in "$folder"/* do if ( (( ( RANDOM...

Pm me Pb > On 31 Mar 2019, at 10:29, Yan-echo wrote: > > Do you run it on Linux or Windows? > How can I run it? > I...

I think the problem with precision occurs to everyone with this specific release. It steams from the way the train and test datasets are created. If one looks carefully the...

1. Check that your dataset is correctly prepared before you train. (Means that you re training apples and testing apples, not oranges for instance). Thats the most important step actually....