pytorch-image-models/timm
Ross Wightman e4de077021 Add first 'Normalizer Free' models. nf_regnet_b1 79.3 @ 288x288 test, and nf_resnet50 80.3 @ 256x256 test (80.68 @ 288x288). 2021-02-11 13:20:11 -08:00
..
data Add new weights for ecaresnet26t/50t/269d models. Remove distinction between 't' and 'tn' (tiered models), tn is now t. Add test time img size spec to default cfg. 2021-02-06 16:30:02 -08:00
loss asymmetric_loss 2020-10-16 17:12:28 +03:00
models Add first 'Normalizer Free' models. nf_regnet_b1 79.3 @ 288x288 test, and nf_resnet50 80.3 @ 256x256 test (80.68 @ 288x288). 2021-02-11 13:20:11 -08:00
optim Configure create_optimizer with args.opt_args 2020-12-08 00:03:09 -06:00
scheduler Merge branch 'logger' into features. Change 'logger' to '_logger'. 2020-07-27 18:00:46 -07:00
utils Fix #387 so that checkpoint saver works with max history of 1. Add checkpoint-hist arg to train.py. 2021-01-31 20:14:51 -08:00
__init__.py Monster commit, activation refactor, VoVNet, norm_act improvements, more 2020-06-01 17:16:52 -07:00
version.py Update README.md and docs. Version bumped to 0.4.3 2021-02-10 14:46:07 -08:00