pytorch-image-models/timm/optim/__init__.py

from .nadam import Nadam
from .rmsprop_tf import RMSpropTF
from .adamw import AdamW
from .radam import RAdam
from .novograd import NovoGrad
from .nvnovograd import NvNovoGrad
from .lookahead import Lookahead
from .optim_factory import create_optimizer
Change some absolute imports to relative 2019-06-20 07:08:58 +08:00			`from .nadam import Nadam`
			`from .rmsprop_tf import RMSpropTF`
Add RAdam, NovoGrad, Lookahead, and AdamW optimizers, a few ResNet tweaks and scheduler factory tweak. * Add some of the trendy new optimizers. Decent results but not clearly better than the standards. * Can create a None scheduler for constant LR * ResNet defaults to zero_init of last BN in residual * add resnet50d config 2019-08-28 15:14:10 +08:00			`from .adamw import AdamW`
			`from .radam import RAdam`
			`from .novograd import NovoGrad`
Add Nvidia's NovogGrad impl from Jasper (cleaner/faster than current) and Apex Fused optimizers 2019-08-30 06:21:38 +08:00			`from .nvnovograd import NvNovoGrad`
Add RAdam, NovoGrad, Lookahead, and AdamW optimizers, a few ResNet tweaks and scheduler factory tweak. * Add some of the trendy new optimizers. Decent results but not clearly better than the standards. * Can create a None scheduler for constant LR * ResNet defaults to zero_init of last BN in residual * add resnet50d config 2019-08-28 15:14:10 +08:00			`from .lookahead import Lookahead`
Change some absolute imports to relative 2019-06-20 07:08:58 +08:00			`from .optim_factory import create_optimizer`