gcamfer / gym-classification Goto Github PK

Hello,
first thanks for sharing your code.
I run your code with MNIST dataset without any problem but when I use it for my dataset after 13 epochs ,I get an error on
# Update states for next step
self.true_labels = np.take(self.y,self.current_indices,axis=0).ravel()
and the erroe is:
IndexError: index 2373 is out of bounds for axis 0 with size 2373
do you know why this happend?

Hello,
Thank you for your code. While I was running your MNIST example an error appeared.

I added statements in your code to prevent the error since the truth value of an array with more than one element is ambiguous.

But as a result, the model could not converge like that you showed in your github page.

I wonder if you had the same problem or is there something that I've missed.