- Vancouver, BC
- rwightman.com
- @wightmanr
Highlights
- Pro
Block or Report
Block or report rwightman
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
pytorch-image-models Public
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
-
efficientdet-pytorch Public
A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
-
gen-efficientnet-pytorch Public
Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS
-
pytorch-dpn-pretrained Public
Dual Path Networks (DPN) supporting pretrained weights converted from original MXNet implementation
-
posenet-python Public
A Python port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)
-
posenet-pytorch Public
A PyTorch port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)
864 contributions in the last year
Activity overview
Contribution activity
January 2023
Created 15 commits in 1 repository
Created 1 repository
- rwightman/CLIP_benchmark Jupyter Notebook
Created a pull request in LAION-AI/CLIP_benchmark that received 3 comments
Support evaluating multiple checkpoints for same model
use --pretrained_glob to eval multiple checkpoints for same model via glob pattern don't dump single result output files if --output is set to '' o…
Opened 4 other pull requests in 1 repository
Answered 2 discussions in 2 repositories
mlfoundations/open_clip
-
Why is there a difference in the text encoder between CLIP and open-CLIP?
This contribution was made on Jan 9
rwightman/pytorch-image-models
-
Regnet training hparams
This contribution was made on Jan 5





