pytorch-image-models/optim/__init__.py

from optim.adabound import AdaBound
from optim.nadam import Nadam
from optim.rmsprop_tf import RMSpropTF
from optim.optim_factory import create_optimizer
Add some Nvidia performance enhancements (prefetch loader, fast collate), and refactor some of training and model fact/transforms 2019-03-10 14:23:16 -07:00			`from optim.adabound import AdaBound`
Uniform pretrained model handling. * All models have 'default_cfgs' dict * load/resume/pretrained helpers factored out * pretrained load operates on state_dict based on default_cfg * test all models in validate * schedule, optim factor factored out * test time pool wrapper applied based on default_cfg 2019-04-11 21:32:16 -07:00			`from optim.nadam import Nadam`
Morph mnasnet impl into a generic mobilenet that covers Mnasnet, MobileNetV1/V2, ChamNet, FBNet, and related * add an alternate RMSprop opt that applies eps like TF * add bn params for passing through alternates and changing defaults to TF style 2019-04-21 15:54:28 -07:00			`from optim.rmsprop_tf import RMSpropTF`
Uniform pretrained model handling. * All models have 'default_cfgs' dict * load/resume/pretrained helpers factored out * pretrained load operates on state_dict based on default_cfg * test all models in validate * schedule, optim factor factored out * test time pool wrapper applied based on default_cfg 2019-04-11 21:32:16 -07:00			`from optim.optim_factory import create_optimizer`