dnth / supercharge-your-pytorch-image-models-blogpostLinks
Supercharge Your PyTorch Image Models: Bag of Tricks to 8x Faster Inference with ONNX Runtime & Optimizations
☆23Updated last year
Alternatives and similar repositories for supercharge-your-pytorch-image-models-blogpost
Users that are interested in supercharge-your-pytorch-image-models-blogpost are comparing it to the libraries listed below
Sorting:
- Memory-Efficient CUDA kernels for training ConvNets with PyTorch.☆42Updated 7 months ago
- Timm model explorer☆42Updated last year
- A simple wrapper library for binding timm models as detectron2 backbones☆44Updated 2 years ago
- IceData: Datasets Hub for the *IceVision* Framework☆49Updated 3 years ago
- ☆59Updated last year
- ☆29Updated 2 months ago
- ☆208Updated last year
- PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning☆195Updated last year
- Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.☆159Updated last year
- Estimate dataset difficulty and detect label mistakes using reconstruction error ratios!☆26Updated 8 months ago
- TF2 implementation of knowledge distillation using the "function matching" hypothesis from https://arxiv.org/abs/2106.05237.☆88Updated 4 years ago
- understanding model mistakes with human annotations☆106Updated 2 years ago
- Easily get basic insights about your ML dataset☆40Updated last year
- ☆134Updated last year
- [ICCV25] Official Implementation of LeGrad☆80Updated 11 months ago
- ☆77Updated this week
- Code for experiments for "ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy"☆101Updated last year
- Lightning HPO & Training Studio App☆18Updated 2 years ago
- Continuation of an abandoned project fast-coco-eval☆123Updated 2 weeks ago
- Simplify Your Visual Data Ops. Find and visualize issues with your computer vision datasets such as duplicates, anomalies, data leakage, …☆69Updated 5 months ago
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.