Closed JoyHuYY1412 closed 5 years ago
Sorry but I am a little bit confused by the learning rate. https://github.com/uber-research/UPSNet/blob/96b7b5172b7b76446f637f4922b7a2054e46703b/upsnet/upsnet_end2end_train.py#L119
https://github.com/uber-research/UPSNet/blob/96b7b5172b7b76446f637f4922b7a2054e46703b/upsnet/upsnet_end2end_train.py#L200
What is the relation of these two learning rates? And how can I get the real leaning rate? Since if I print the optimizer.param_groups[0]["lr"], I always get 1.
optimizer.param_groups[0]["lr"]
Sorry but I am a little bit confused by the learning rate. https://github.com/uber-research/UPSNet/blob/96b7b5172b7b76446f637f4922b7a2054e46703b/upsnet/upsnet_end2end_train.py#L119
https://github.com/uber-research/UPSNet/blob/96b7b5172b7b76446f637f4922b7a2054e46703b/upsnet/upsnet_end2end_train.py#L200
What is the relation of these two learning rates? And how can I get the real leaning rate? Since if I print the
optimizer.param_groups[0]["lr"]
, I always get 1.