5 Commits (a1886346df714b47880cc0f278c792f0a4c36261)

Author	SHA1	Message	Date
Vyacheslav Shults	44ed0f85e8	Refactor imports and indents according to PEP. ... Add proposal for links to pretrained weights. Unify style of reset_classifier function. Replace None by nn.Identity() in torch modules (all empty classifiers and HRNet)	5 years ago
Ross Wightman	e6f24e5578	Add 'momentum' optimizer (SGD w/o nesterov) for stable EfficientDet training defaults	5 years ago
Ross Wightman	64966f61f7	Add Nvidia's NovogGrad impl from Jasper (cleaner/faster than current) and Apex Fused optimizers	6 years ago
Ross Wightman	fac58f609a	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	6 years ago
Ross Wightman	aa4354f466	Big re-org, working towards making pip/module as 'timm'	6 years ago