mikkoim / dinotoolLinks
Command-line tool for extracting DINO, CLIP, and SigLIP2 features for images and videos
☆22Updated last week
Alternatives and similar repositories for dinotool
Users that are interested in dinotool are comparing it to the libraries listed below
Sorting:
- Convert datasets from Hugging Face to FiftyOne for Visualization☆11Updated last year
- Pixel Parsing. A reproduction of OCR-free end-to-end document understanding models with open data☆21Updated 10 months ago
- Use Grounding DINO, Segment Anything, and CLIP to label objects in images.☆31Updated last year
- Notebooks to demonstrate TimmWrapper☆16Updated 5 months ago
- ☆58Updated last year
- ☆73Updated 2 months ago
- Easily get basic insights about your ML dataset☆38Updated last year
- Let's bake an image.☆14Updated last month
- Memory-Efficient CUDA kernels for training ConvNets with PyTorch.☆41Updated 3 months ago
- Timm model explorer☆40Updated last year
- Compare Savant and PyTorch performance☆13Updated last year
- Repository containing the Kornia related tutorials☆47Updated 7 months ago
- Evaluate the performance of computer vision models and prompts for zero-shot models (Grounding DINO, CLIP, BLIP, DINOv2, ImageBind, model…☆36Updated last year
- Lightweight, open-source, high-performance Yolo implementation☆33Updated 3 weeks ago
- Simplify Your Visual Data Ops. Find and visualize issues with your computer vision datasets such as duplicates, anomalies, data leakage, …☆70Updated last month
- A tool for converting computer vision label formats.☆62Updated 2 months ago
- ☆13Updated 2 years ago
- A lightweight, completely free experiment tracking Python library built on top of 🤗 Datasets and Spaces.☆45Updated this week
- FiftyOne Plugin for finding common image quality issues☆32Updated 8 months ago
- A tiny package supporting distributed computation of COCO metrics for PyTorch models.☆12Updated 2 years ago
- Solving Computer Vision with AI agents☆33Updated last month
- EdgeSAM model for use with Autodistill.☆27Updated last year
- auto_labeler - An all-in-one library to automatically label vision data☆15Updated 5 months ago
- ☆14Updated 10 months ago
- Official code repository for paper: "ExPLoRA: Parameter-Efficient Extended Pre-training to Adapt Vision Transformers under Domain Shifts"☆31Updated 8 months ago
- Cache PyTorch module outputs on-the-fly☆44Updated 2 months ago
- Code and pretrained models for the paper: "MatMamba: A Matryoshka State Space Model"☆59Updated 7 months ago
- Adds timm pretrained backbone to pytorch's FasterRcnn model☆12Updated last year
- Simple and easy stable diffusion inference with LightningModule on GPU, CPU and MPS (Possibly all devices supported by Lightning).☆17Updated last year
- GroundedSAM Base Model plugin for Autodistill☆51Updated last year