Closed kezakool closed 3 years ago
Hi,
Thank you for all your work this is great! no bug here, but i was asking myself why you choose tf_slim instead of tf for convolutions layers?
thx
@kezakool this is just a personal preference, I think tf.contrib.slim is easier to use than other tensorflow API btw, I transfer to pytorch now because tensorflow APIs are too complicated.
Hi,
Thank you for all your work this is great! no bug here, but i was asking myself why you choose tf_slim instead of tf for convolutions layers?
thx