pytorch-image-models

pytorch-image-models copied to clipboard

**Is your feature request related to a problem? Please describe.** I would greatly appreciate it if a flag could be implemented, allowing me to log accuracy in Tensorboard format after...

exx8

Is there any work on supporting [SeaFormer](https://github.com/fudan-zvg/SeaFormer) ?

MohamedAliRashad

Add features_intermediate() support to coatnet, maxvit, swin*. Tweak feature extraction interfaces. Prep new vit weights while testing.

1

rwightman

WIP Hiera implementation.

1

…ion to work.

rwightman

Add NPU backend support for val and inference

8

I am a user of NPU. When I used TIMM recently, I found that it does not support NPU natively. It's pleasure to see that someone has made some contributions...

MengqingCao

[BUG] There is the error in timm/train.py when i use the Webdataset (timm/imagent-w21-wds in huggingface) with class map

9

**Describe the bug** A clear and concise description of what the bug is. i wanted to train the the parts of IN21k-winter class , so i made the class map...

TheDarkKnight-21th

Add Intel's GPU / XPU support to TIMM's validation script

4

# Background This PR is mainly about increasing the diversity of accelerators. Intel has a new GPU released last year and it is promoting to different platforms. This is a...

cfgfung

Fiddling with EfficientNet x/h defs, MobileNet-v4.

1

rwightman

Hi， Could you provide the pretrained model of cs3darknet_focus_s.c2ns_in1k? Thanks This is relly an excellent and inspiring project.

wenhui-ml

[FEATURE] Add image backbones from `MobileCLIP` paper

3

[MobileCLIP](https://github.com/apple/ml-mobileclip/) is a really fast CLIP architecture for mobile inference - about 3x faster than the fastest publicly available CLIP backbone `convnext_base_w` for inference on iOS / macOS devices. They...

rsomani95