Version 0.9.5 prep for release. README update

Author: rwightman

README.md

@@ -35,6 +35,12 @@ And a big thanks to all GitHub sponsors who helped with some of my costs before
 * The Hugging Face Hub (https://huggingface.co/timm) is now the primary source for `timm` weights. Model cards include link to papers, original source, license. 
 * Previous 0.6.x can be cloned from [0.6.x](https://github.com/rwightman/pytorch-image-models/tree/0.6.x) branch or installed via pip with version.
 
+### Aug 3, 2023
+* Add GluonCV weights for HRNet w18_small and w18_small_v2. Converted by [SeeFun](https://github.com/seefun)
+* Fix `selecsls*` model naming regression
+* Patch and position embedding for ViT/EVA works for bfloat16/float16 weights on load (or activations for on-the-fly resize)
+* v0.9.5 release prep
+
 ### July 27, 2023
 * Added timm trained `seresnextaa201d_32x8d.sw_in12k_ft_in1k_384` weights (and `.sw_in12k` pretrain) with 87.3% top-1 on ImageNet-1k, best ImageNet ResNet family model I'm aware of.
 * RepViT model and weights (https://arxiv.org/abs/2307.09283) added by [wangao](https://github.com/jameslahm)

timm/version.py

@@ -1 +1 @@
-__version__ = '0.9.4dev0'
+__version__ = '0.9.5'