Archisha Chandel

icon location I try not to think. It interferes with being nuts.

Results 3 comments of Archisha Chandel

run the program

`fire_net.py` has 3 functions in it so basically set the test image/video path there and then call the function not the python file

Don't instantiate a TextureStore each time we pick something in the scene

![image](https://user-images.githubusercontent.com/47753303/75351503-46a5ce00-58ce-11ea-8517-dd73a6a9ff3a.png) So, this should not be printed everytime an object is picked or selected?

During training checkpoints are being saved, also the last version of the trained model, which might not be the best model. So there should be an option to save the best model as well.

@haimat I might have not understood the issue accurately so I was just curious to know, how `save_best_only` feature of `tensorflow.keras.callbacks.ModelCheckpoint` not solve the problem?