The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

OpenMMLab Detection Toolbox and Benchmark

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

A resource for learning about Machine learning & Deep Learning

OpenMMLab Computer Vision Foundation

Accelerated deep learning R&D

A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.

Run VSCode (codeserver) on Google Colab or Kaggle Notebooks

A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights

Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS

PyTorch extensions for fast R&D prototyping and Kaggle farming

[CVPR2021, PAMI2023] End-to-End Object Detection with Learnable Proposal

UNet model with VGG11 encoder pre-trained on Kaggle Carvana dataset

Deep learning toolbox based on PyTorch for hyperspectral data classification.

SIIM-ACR Pneumothorax Segmentation first place solution

Waymo: Motion Prediction 2021

[ICIP 2021] Puzzle-CAM: Improved localization via matching partial and full features.

Code for a winning model (3 out of 419) in a Dstl Satellite Imagery Feature Detection challenge

The 2nd place solution to the 2020 edition of the Google Landmark Recognition competition

EfficientNet, MobileNetV3, MobileNetV2, MixNet, etc in JAX w/ Flax Linen and Objax

Model to check if image was rotated by 90, 180, 270 degrees.

🎖️ 4th place solution in the Feedback Prize Competition🎖️

Training code of Cornell Birdcall Identification Challenge 6th place solution

2nd place solution

The repository to show the way I trained https://www.kaggle.com/hidehisaarai1213/birdcall-resnet50-init-weights

Code and pre-trained models for detecting spoofing attacks from images.