/torchsat

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

Primary LanguagePythonMIT LicenseMIT

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.

Install

  • pypi: pip3 install torchsat
  • source: python3 setup.py install
  • docker: docker pull sshuair/torchsat:gpu-latest

How to use

  • Introduction -
  • Classification tutorial -
  • Data augmentation - data-augmentation.ipynb
  • Data loader
  • models
  • train script

Features

Data augmentation

We suppose all the input images, masks and bbox should be NumPy ndarray. The data shape should be [height, width] or [height, width, channels].

pixel level

Pixel-level transforms only change the input image and will leave any additional targets such as masks, bounding boxes unchanged. It support all channel images. Some transforms only support specific input channles.

Transform Image masks BBoxes
ToTensor ✓ ✓ ✓
Normalize ✓ ✓ ✓
ToGray ✓ ✓ ✓
GaussianBlur ✓ ✓ ✓
RandomNoise ✓ ✓ ✓
RandomBrightness ✓ ✓ ✓
RandomContrast ✓ ✓ ✓

spatial-level

Spatial-level transforms will simultaneously change both an input image as well as additional targets such as masks, bounding boxes. It support all channel images.

Transform Image masks BBoxes
Resize ✓ ✓ ✓
Pad ✓ ✓ ✓
RandomHorizontalFlip ✓ ✓ ✓
RandomVerticalFlip ✓ ✓ ✓
RandomFlip ✓ ✓ ✓
CenterCrop ✓ ✓ ✓
RandomCrop ✓ ✓ ✓
RandomResizedCrop ✓ ✓ ✓
ElasticTransform ✓ ✓
RandomRotation ✓ ✓ ✓
RandomShift ✓ ✓ ✓

Models

Classification

All models support multi-channels as input (e.g. 8 channels).

  • VGG: vgg11, vgg11_bn, vgg13, vgg13_bn, vgg16, vgg16_bn,vgg19_bn, vgg19
  • ResNet: resnet18, resnet34, restnet50, resnet101, resnet152
  • DenseNet: densenet121, densenet169, densenet201, densenet161
  • Inception: inception_v3
  • MobileNet: mobilenet_v2

Sementic Segmentation

  • UNet: unet, unet34, unet101, unet152 (with resnet as backbone.)

Dataloader

Classification

Showcase

If you extend this repository or build projects that use it, we'd love to hear from you.

Reference

Note

  • If you are looking for the torchvision-enhance, please checkout the enhance branch. But it was deprecated.