mirrors/pytorch-image-models
1
0
Fork 0
mirror of https://github.com/huggingface/pytorch-image-models.git synced 2025-06-03 15:01:08 +08:00
Code Issues Projects Releases Wiki Activity

Almost ready to merge, vovnet typo, version bump, readme addition

Browse Source
This commit is contained in:
Ross Wightman 2020-06-11 15:41:58 -07:00
parent 151679c2f1
commit 39f27c1add
3 changed files with 15 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
README.md
View File

@ -2,6 +2,19 @@
## What's New
### June 11, 2020
Bunch of changes:
* DenseNet models updated with memory efficient addition from torchvision (fixed a bug), blur pooling and deep stem additions
* VoVNet V1 and V2 models added, 39 V2 variant (ese_vovnet_39b) trained to 79.3 top-1
* Activation factory added along with new activations:
* select act at model creation time for more flexibility in using activations compatible with scripting or tracing (ONNX export)
* hard_mish (experimental) added with memory-efficient grad, along with ME hard_swish
* context mgr for setting exportable/scriptable/no_jit states
* Norm + Activation combo layers added with initial trial support in DenseNet and VoVNet along with impl of EvoNorm and InplaceAbn wrapper that fit the interface
* Torchscript works for all but two of the model types as long as using Pytorch 1.5+, tests added for this
* Some import cleanup and classifier reset changes, all models will have classifier reset to nn.Identity on reset_classifer(0) call
* Prep for 0.1.28 pip release
### May 12, 2020
* Add ResNeSt models (code adapted from https://github.com/zhanghang1989/ResNeSt, paper https://arxiv.org/abs/2004.08955))

2
timm/models/vovnet.py
View File

@ -157,7 +157,7 @@ default_cfgs = dict(
ese_vovnet99b=_cfg(url=''),
eca_vovnet39b=_cfg(url=''),
ese_vovnet39b_evos=_cfg(url=''),
eee_vovnet99b_iabn=_cfg(url=''),
ese_vovnet99b_iabn=_cfg(url=''),
)

2
timm/version.py
View File

@ -1 +1 @@
__version__ = '0.1.26'
__version__ = '0.1.28'