Closed sunsided closed 7 years ago
In the utils.deconv2d() function, the parameter k_w was ignored and the kernel height was used in its place:
utils.deconv2d()
k_w
W = tf.get_variable( name='W', shape=[k_h, k_h, n_output_ch, n_input_ch or x.get_shape()[-1]], initializer=tf.contrib.layers.xavier_initializer_conv2d())
This has been changed to:
W = tf.get_variable( name='W', shape=[k_h, k_w, n_output_ch, n_input_ch or x.get_shape()[-1]], initializer=tf.contrib.layers.xavier_initializer_conv2d())
Oops good catch! TY!
Very welcome. :slightly_smiling_face:
In the
utils.deconv2d()
function, the parameterk_w
was ignored and the kernel height was used in its place:This has been changed to: