Hello, I found a performance issue in the definition of get_condconv_initializer, libs/networks/efficientnet/condconv/condconv_layers.py, tf.reshape(kernel, [-1]) will be calculated repeatedly during program execution, resulting in reduced efficiency. I think both it and kernel should be created before the loop in condconv_initializer.
Looking forward to your reply. Btw, I am very glad to create a PR to fix it if you are too busy.
Hello, I found a performance issue in the definition of
get_condconv_initializer
, libs/networks/efficientnet/condconv/condconv_layers.py,tf.reshape(kernel, [-1])
will be calculated repeatedly during program execution, resulting in reduced efficiency. I think both it andkernel
should be created before the loop incondconv_initializer
.Looking forward to your reply. Btw, I am very glad to create a PR to fix it if you are too busy.