pytorch-image-models/timm/data
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
..
__init__.py Big re-org, working towards making pip/module as 'timm' 2019-06-19 17:20:51 -07:00
config.py A number of tweaks to arguments, epoch handling, config 2019-06-28 13:49:20 -07:00
constants.py Big re-org, working towards making pip/module as 'timm' 2019-06-19 17:20:51 -07:00
dataset.py Big re-org, working towards making pip/module as 'timm' 2019-06-19 17:20:51 -07:00
distributed_sampler.py Big re-org, working towards making pip/module as 'timm' 2019-06-19 17:20:51 -07:00
loader.py A number of tweaks to arguments, epoch handling, config 2019-06-28 13:49:20 -07:00
mixup.py Big re-org, working towards making pip/module as 'timm' 2019-06-19 17:20:51 -07:00
random_erasing.py Big re-org, working towards making pip/module as 'timm' 2019-06-19 17:20:51 -07:00
tf_preprocessing.py Big re-org, working towards making pip/module as 'timm' 2019-06-19 17:20:51 -07:00
transforms.py A number of tweaks to arguments, epoch handling, config 2019-06-28 13:49:20 -07:00