sshuair / Torchsat
Licence: mit
🔥TorchSat 🌏 is an open-source deep learning framework for satellite imagery analysis based on PyTorch.
Stars: ✭ 261
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Torchsat
Geospatial Machine Learning
A curated list of resources focused on Machine Learning in Geospatial Data Science.
Stars: ✭ 289 (+10.73%)
Mutual labels: classification, semantic-segmentation, remote-sensing, satellite-imagery
deck.gl-raster
deck.gl layers and WebGL modules for client-side satellite imagery analysis
Stars: ✭ 60 (-77.01%)
Mutual labels: satellite, remote-sensing, satellite-imagery
lightweight-temporal-attention-pytorch
A PyTorch implementation of the Light Temporal Attention Encoder (L-TAE) for satellite image time series. classification
Stars: ✭ 43 (-83.52%)
Mutual labels: satellite, remote-sensing, satellite-imagery
Raster Vision
An open source framework for deep learning on satellite and aerial imagery.
Stars: ✭ 1,248 (+378.16%)
Mutual labels: classification, semantic-segmentation, remote-sensing
geoblaze
Blazing Fast JavaScript Raster Processing Engine
Stars: ✭ 80 (-69.35%)
Mutual labels: satellite, remote-sensing, satellite-imagery
shipsnet-detector
Detect container ships in Planet imagery using machine learning
Stars: ✭ 30 (-88.51%)
Mutual labels: remote-sensing, satellite-imagery
spyndex
Awesome Spectral Indices in Python.
Stars: ✭ 56 (-78.54%)
Mutual labels: remote-sensing, satellite-imagery
dea-coastlines
Extracting tidally-constrained annual shorelines and robust rates of coastal change from freely available Earth observation data at continental scale
Stars: ✭ 24 (-90.8%)
Mutual labels: remote-sensing, satellite-imagery
building-footprint-segmentation
Building footprint segmentation from satellite and aerial imagery
Stars: ✭ 26 (-90.04%)
Mutual labels: satellite-imagery, semantic-segmentation
awesome-spectral-indices
A ready-to-use curated list of Spectral Indices for Remote Sensing applications.
Stars: ✭ 357 (+36.78%)
Mutual labels: remote-sensing, satellite-imagery
LoveDA
[NeurIPS2021 Poster] LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
Stars: ✭ 111 (-57.47%)
Mutual labels: remote-sensing, semantic-segmentation
modape
MODIS Assimilation and Processing Engine
Stars: ✭ 19 (-92.72%)
Mutual labels: satellite, remote-sensing
InstantDL
InstantDL: An easy and convenient deep learning pipeline for image segmentation and classification
Stars: ✭ 33 (-87.36%)
Mutual labels: classification, semantic-segmentation
candock
A time series signal analysis and classification framework
Stars: ✭ 56 (-78.54%)
Mutual labels: classification, data-augmentation
Opensource OBIA processing chain
An open-source semi-automated processing chain for urban OBIA classification.
Stars: ✭ 75 (-71.26%)
Mutual labels: remote-sensing, classification
ee extra
A ninja python package that unifies the Google Earth Engine ecosystem.
Stars: ✭ 42 (-83.91%)
Mutual labels: remote-sensing, satellite-imagery
land-cover-to-land-use-classification
Satellite image processing pipeline to classify land-cover and land-use
Stars: ✭ 64 (-75.48%)
Mutual labels: remote-sensing, satellite-imagery
geowombat
GeoWombat: Utilities for geospatial data
Stars: ✭ 34 (-86.97%)
Mutual labels: satellite, remote-sensing
google-maps-at-88-mph
Google Maps keeps old satellite imagery around for a while – this tool collects what's available for a user-specified region in the form of a GIF.
Stars: ✭ 93 (-64.37%)
Mutual labels: satellite, satellite-imagery
himawari-rx
📡 Receive images from weather satellite Himawari-8 via HimawariCast.
Stars: ✭ 21 (-91.95%)
Mutual labels: satellite, satellite-imagery
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 the latest progress, please check the develop branch.
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
- source:
python3 setup.py install
How to use
- Introduction
- Image Classification Tutorial: Docs, Google Colab
- Semantic Segmentation Tutorial: Docs
- Data Augumentation: Docs, Google Colab
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,resnet50,resnet101,resnet152,resnext50_32x4d,resnext101_32x8d,wide_resnet50_2,wide_resnet101_2 - DenseNet:
densenet121,densenet169,densenet201 - Inception:
inception_v3 - MobileNet:
mobilenet_v2 - EfficientNet:
efficientnet_b0,efficientnet_b1,efficientnet_b2,efficientnet_b3,efficientnet_b4,efficientnet_b5,efficientnet_b6,efficientnet_b7 - ResNeSt:
resnest50,resnest101,resnest200,resnest269
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.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].