A collection of pre-trained, state-of-the-art models in the ONNX format

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Datasets, Transforms and Models specific to Computer Vision

A PyTorch implementation of simple Mask R-CNN

Mask R-CNN for object detection and instance segmentation on Keras==2.7.0 and TensorFlow==2.7.0

Use Mask R-CNN/Keras/TensorFlow and OSM to find features in satellite images for fun.

Instance segmentation deep learning model built using PyTorch and fastai to classify rooftops and calculate their solar PV potential.

SAM with text prompt

code for the paper "Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis"

Training dataset for supervised learning

Python code for partitioning rectilinear polygon in O(n) time complexity

Evaluating DINOv2 for Radiology

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

A library for efficient similarity search and clustering of dense vectors.

This repository contains demos I made with the Transformers library by HuggingFace.

OpenMMLab Rotated Object Detection Toolbox and Benchmark

Low rank adaptation for Vision Transformer

VMamba: Visual State Space Models，code is based on mamba

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

PyTorch code and models for the DINOv2 self-supervised learning method.

Software for working with satellite & aerial imagery ML datasets

Virtual whiteboard for sketching hand-drawn like diagrams

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

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

OpenMMLab Computer Vision Foundation

Turkish BERT/DistilBERT, ELECTRA and ConvBERT models