- Vancouver, BC
- rwightman.com
- @wightmanr
Highlights
- Pro
- 97 discussions answered
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)
563 contributions in the last year
Activity overview
Contribution activity
May 2022
Created 36 commits in 2 repositories
Created a pull request in mlfoundations/open_clip that received 2 comments
Opened 3 other pull requests in 2 repositories
rwightman/pytorch-image-models
2
merged
mlfoundations/open_clip
1
merged
Created an issue in NVIDIA/DeepLearningExamples that received 3 comments
[GPUNet/PyTorch] Model padding is incorrect, layer naming goes against norms.
Describe the bug The handling of padding in the model appears incorrect due to misunderstanding of the source code (my pytorch-image-models) Effici…
Answered 7 discussions in 1 repository
rwightman/pytorch-image-models
- About truncated normal distribution based weight initialization
- Flowers-102 train split include validation split ?
- Transfer Learning
- why pretrained models' query result different between methods of list_models() and model_entrypoints
- Why is the performance of `resnet50` higher than `tv_resnet50` so much?
- Why do some of the EfficientNet models have mean, std = 0.5 in their configs?
- Weight decay cosine schedule