10 Commits

Author SHA1 Message Date
Ross Wightman
f225ae8e59 Update README with model results and attribution. Make scheduler factory bit more robust to arg differences, add noise to plateau lr and fix min/max. 2020-06-12 13:33:12 -07:00
Ross Wightman
6441e9cc1b Fix memory_efficient mode for DenseNets. Add AntiAliasing (Blur) support for DenseNets and create one test model. Add lr cycle/mul params to train args. 2020-05-22 16:16:45 -07:00
Ross Wightman
c16f25ced2 Add MobileNetV3 Large weights, results, update README and sotabench for merge 2020-02-29 20:37:20 -08:00
Ross Wightman
27b3680d49 Revamp LR noise, move logic to scheduler base. Fixup PlateauLRScheduler and add it as an option. 2020-02-22 16:23:15 -08:00
Ross Wightman
514b0938c4 Experimenting with per-epoch learning rate noise w/ step scheduler 2020-02-21 11:51:05 -08:00
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
2019-08-28 00:14:10 -07:00
Ross Wightman
e7c8a37334 Make min-lr and cooldown-epochs cmdline args, change dash in color_jitter arg for consistency 2019-07-26 09:35:31 -07:00
Ross Wightman
c6b32cbe73 A number of tweaks to arguments, epoch handling, config
* reorganize train args
* allow resolve_data_config to be used with dict args, not just arparse
* stop incrementing epoch before save, more consistent naming vs csv, etc
* update resume and start epoch handling to match above
* stop auto-incrementing epoch in scheduler
2019-06-28 13:49:20 -07:00
Ross Wightman
6fc886acaf Remove all prints, change most to logging calls, tweak alignment of batch logs, improve setup.py 2019-06-20 17:29:25 -07:00
Ross Wightman
aa4354f466 Big re-org, working towards making pip/module as 'timm' 2019-06-19 17:20:51 -07:00