moznpan

Results 3 comments of moznpan

macOS support

I would volunteer to help out if I knew where to begin. If anyone finds a good resource please @ me!

Way to evaluate a "score" for models

@Sentdex we might be able to get away with a `Dense(1, activation='tanh')` output and multiply this, with some speed/acceleration scalars, directly to the x-position of your object on screen. -1...

Make the validation sets completely separate/not same sitting as the training data

hey @Sentdex . I didn't have much luck escaping over-fitting either, but I figured I'd still share my results. I took a slightly different approach and used the average across...