metr0jw / DeepRL-TF2-DQN-implementation-for-TensorFlow-2

Deep Q-Network based Reinforcement Learning implementation for TensorFlow 2

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

conv2d layer dimension compatibility problem

metr0jw opened this issue · comments

train.py line 55

net.build(input_shape)    # input_shape=[84, 84, 1]
ValueError: Input 0 of layer conv2d is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [84, 84, 1]