Proper Way To Define Inputshape On The First Layer On Keras

I have an array of 35000 images of 256x256 grayscale images print(len(data)) >>>35000 print(data[0].shape) >>>(256, 256) My first layer is model.add(Conv2D(64, (

Solution 1:

Convolutional layers input shape: (images, height, width, channels)

So:

• input_shape=(256,256,1)
• batch_shape=(batch_size,256,256,1)
• batch_input_shape=(batch_size,256,256,1)