fast-reid/fastreid/solver/optim/__init__.py

# encoding: utf-8
"""
@author:  xingyu liao
@contact: sherlockliao01@gmail.com
"""

from .lamb import Lamb
from .swa import SWA
from .radam import RAdam
from torch.optim import *
update fastreid V1.0 2021-01-18 11:36:38 +08:00			`# encoding: utf-8`
			`"""`
			`@author: xingyu liao`
			`@contact: sherlockliao01@gmail.com`
			`"""`

update version0.2 code 2020-03-25 10:58:26 +08:00			`from .lamb import Lamb`
feat: add swa algorithm Add swa and related config options, if it is enabled, model will do swa after regular training 2020-05-06 10:17:44 +08:00			`from .swa import SWA`
update fastreid v1.2 readme and changelog 2021-04-06 20:09:13 +08:00			`from .radam import RAdam`
v0.3 update Summary: 1. change DPP training in apex way; 2. make warmup scheduler by iter and lr scheduler by epoch; 3. replace random erasing with torchvision implementation; 4. naming modification in config file 2020-12-07 14:19:20 +08:00			`from torch.optim import *`