Welcome to TorchSat’s documentation!

TorchSat is an open-source deep learning framework for satellite imagery analysis based on PyTorch.

This project is still work in progress. If you want to know more about it, please refer to the Roadmap .

Hightlight

• Support multi-channels(> 3 channels, e.g. 8 channels) images and TIFF file as input.
• Convenient data augmentation method for classification, sementic segmentation and object detection.
• Lots of models for satellite vision tasks, such as ResNet, DenseNet, UNet, PSPNet, SSD, FasterRCNN …
• Lots of common satellite datasets loader.
• Training script for common satellite vision tasks.

Contents:

• Installation
  • Deepndencies
  • Install
• Core Conceptions
• Image Classification
  • Prepare trainning data
  • Training model
  • Inference new image
• Semantic Segmentation
  • Prepare training data
  • Training model
  • Inference new image
• Object Detection
• Change Detection
  • Prepare the training data
  • train a model
  • We provide the following models:
• Data Augumentation
  • Image classification
  • Object detection
  • Semantic segmentation
• Useful Tools
  • processing tools
  • train scripts
• API Reference
  • torchsat package

Indices and tables

• Index
• Module Index
• Search Page