pytorch-image-models

Commit Graph

Author	SHA1	Message	Date
Ross Wightman	0562b91c38	Add per model crop pct, interpolation defaults, tie it all together * create one resolve fn to pull together model defaults + cmd line args * update attribution comments in some models * test update train/validation/inference scripts	6 years ago
Ross Wightman	9c3859fb9c	Uniform pretrained model handling. * All models have 'default_cfgs' dict * load/resume/pretrained helpers factored out * pretrained load operates on state_dict based on default_cfg * test all models in validate * schedule, optim factor factored out * test time pool wrapper applied based on default_cfg	6 years ago
Ross Wightman	0bc50e84f8	Lots of refactoring and cleanup. * Move 'test time pool' to Module that can be used by any model, remove from DPN * Remove ResNext model file and combine with ResNet * Remove fbresnet200 as it was an old conversion and pretrained performance not worth param count * Cleanup adaptive avgmax pooling and add back conctat variant * Factor out checkpoint load fn	6 years ago

Author

SHA1

Message

Date

Ross Wightman

0562b91c38

Add per model crop pct, interpolation defaults, tie it all together

* create one resolve fn to pull together model defaults + cmd line args
* update attribution comments in some models
* test update train/validation/inference scripts

Ross Wightman

9c3859fb9c

Uniform pretrained model handling.

* All models have 'default_cfgs' dict
* load/resume/pretrained helpers factored out
* pretrained load operates on state_dict based on default_cfg
* test all models in validate
* schedule, optim factor factored out
* test time pool wrapper applied based on default_cfg

Ross Wightman

0bc50e84f8

Lots of refactoring and cleanup.

* Move 'test time pool' to Module that can be used by any model, remove from DPN
* Remove ResNext model file and combine with ResNet
* Remove fbresnet200 as it was an old conversion and pretrained performance not worth param count
* Cleanup adaptive avgmax pooling and add back conctat variant
* Factor out checkpoint load fn

3 Commits (e8e8bce3354af28953d5f1e2dd6dffa8e115a167)