Fix issue with pool shape in Neural Network
Currently, CNNWhale only accepts pool shape (2,2). Any other shape results in an error message when attempting to compute the cross entropy:
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=dense_layer2, labels=y),name="cost_function")Would be good to understand why this is happening, and how to fix it!
To upload designs, you'll need to enable LFS and have an admin enable hashed storage. More information