PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

Updated 2025-04-22 23:50:11 +08:00

The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.

Updated 2025-04-07 18:56:01 +08:00

OpenMMLab Image Classification Toolbox and Benchmark

Updated 2024-11-01 14:27:36 +08:00

Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Updated 2024-08-12 16:52:02 +08:00

Official PyTorch implementation of SegFormer

Updated 2023-06-14 06:01:29 +08:00

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

Updated 2023-04-27 16:22:16 +08:00

Inverse Compositional Spatial Transformer Networks 🎭 (CVPR 2017 oral)

Updated 2019-04-11 03:30:20 +08:00

PyTorch implementation of Spatial Transformer Network (STN) with Thin Plate Spline (TPS)

Updated 2018-03-26 15:08:02 +08:00