3 Commits

Author SHA1 Message Date
Ross Wightman
4bb5e9b224 Ported Tensorflow pretrained EfficientNet weights and some model cleanup
* B0-B3 weights ported from TF with close to paper accuracy
* Renamed gen_mobilenet to gen_efficientnet since scaling params go well beyond 'mobile' specific
* Add Tensorflow preprocessing option for closer images to source repo
2019-05-30 17:55:35 -07:00
Ross Wightman
45cde6f0c7 Improve creation of data pipeline with prefetch enabled vs disabled, fixup inception_res_v2 and dpn models 2019-03-11 22:17:42 -07:00
Ross Wightman
2295cf56c2 Add some Nvidia performance enhancements (prefetch loader, fast collate), and refactor some of training and model fact/transforms 2019-03-10 14:23:16 -07:00