Panagiotis Stalidis

@gaara100 Could you be using tensorflow backend with "image_dim_ordering": "th" ?

In method [preprocess_image](https://github.com/danielvarga/keras-deep-dream/blob/master/deep_dream.py#L87) the ordering is transposed for theano (depth, rows, columns), but the MaxPooling layer expects (because of your keras.json) an ordering for tensorflow (rows, columns, depth). Change the...

The problem you are facing now is because conv5_1 is part of a different graph (model) than the one you selected. btw with these settings `{ "image_dim_ordering": "th", "epsilon": 1e-07,...