Convert source code from channels_first to channels_last

[daitrandev]

Hi Sasank Chilamkurthy

I have a problem with your source code when trying to convert your model from channels_first to channels_last. I have deleted this line: "K.set_image_data_format('channels_first')" and changed the input_shape from Cov2D() to: input_shape=(IMG_SIZE, IMG_SIZE, 3) instead of input_shape=(3, IMG_SIZE, IMG_SIZE). Then I got an issue: "expected conv2d_1_input to have shape (None, 48, 48, 3) but got array with shape (13320, 3, 48, 48)". How can I fix that? Thanks.

[chsasank]

You also have to move the channel axis in actual inputs. Remove np.rollaxis in preprocess_img

[daitrandev]

I fixed that. Thanks 👍