Open Allen-wg opened 6 years ago
this project 's backend is theano if you are based tensorflow, you must change [batch, channel,w, h] to [batch,w, h, channel] in your python code.
theano backend default, but if you use tensorflow backend,just set_image_dim_ordering
from keras import backend as K
K.set_image_dim_ordering('th')
I meet some errors like this: ValueError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,128,64]. what's the reason behind it ,how to solve it? Thank you!