The method get_model() in train_steering_model.py provides the
input image to the Lambda layer as a shape (ch, row, col). This is in
the Theano image dimension format, instead of Tensorflow's, which is
(row, col, ch).
An alternative to this is to modify the keras.json file in the Keras
installation path (usually located in ~/.keras/keras.json), in the
image_dim_ordering row.
The method
get_model()intrain_steering_model.pyprovides the input image to theLambdalayer as a shape (ch, row, col). This is in the Theano image dimension format, instead of Tensorflow's, which is (row, col, ch).An alternative to this is to modify the
keras.jsonfile in the Keras installation path (usually located in~/.keras/keras.json), in theimage_dim_orderingrow.