#161161st of 168 in ML frameworks and libraries
raster-vision
Python library for training vision models on satellite and aerial imagery
- Stars
- 2.2k
- License
- Apache-2.0
- Last commit
- Jun 2026
- Last release
- Aug 2024
- Language
- Python
2,206 on 21 Apr 20262,247 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Raster Vision is a Python library and low-code framework for chip classification, object detection and semantic segmentation on satellite, aerial and drone imagery, using PyTorch backends. It runs a configurable pipeline: analyze data, create chips, train, predict, evaluate and bundle the model. Experiments can run locally or on AWS Batch and AWS SageMaker.
Who it is for: Geospatial and remote-sensing teams training vision models on imagery
Strengths
- Reads and writes geo-referenced data, so predictions come out in geospatial formats
- Repeatable pipeline from chip creation through evaluation and model bundling
- Built-in AWS Batch and SageMaker support for cloud runs
- Installable with pip or prebuilt Docker images on quay.io
Weaknesses
- Limited to three tasks: chip classification, object detection, semantic segmentation
- Built-in cloud execution covers AWS only
- Last release is 2024-08-30, well behind recent commits
- PyTorch is the only backend mentioned
What it needs
- Docker
- Needs PyTorch, AWS Batch (optional), AWS SageMaker (optional)
- Models: PyTorch
Quick answers
Is raster-vision open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Can you run raster-vision with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in ML frameworks and libraries
See all 168| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |