Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water, clouds
This release brings incredible new features and improvements from the community accumulated over the last months. We recommend to upgrade.
The pre-built docker images are the recommended way of using robosat:
Changes
rs train
: state of the art losses and metrics. Lovasz loss as default,
many many more small features and fixes in training and related tools.
Thanks https://github.com/ocourtin
rs extract
: fully automatated road training dataset creation
Thanks https://github.com/DragonEmperorG
rs extract
: batch feature extraction for datasets too big for memory
Thanks http://github.com/daniel-j-h
rs rasterize
: batch rasterization for datasets too big for memory
Thanks http://github.com/daniel-j-h
Infrastructure: improved docker images, pre-trained weights in images, upgrades to CUDA 10.1, cudnn 7, and pytorch 1.1. Thanks http://github.com/daniel-j-h
Changes
rs train
: new --checkpoint
argument to re-start training (fine-tune)
from a trained model checkpoint. Thanks https://github.com/ocourtin
rs train
: memory usage reduction during validation by disabling
expensive gradient computation. Thanks https://github.com/Jesse-jApps
rs train
, rs predict
: speedups using multiple workers and
doing metric calculation on GPU. Thanks https://github.com/ocourtin
rs merge
: polygon orientation fixes to respect the GeoJSON
specification (right-hand rule). Thanks https://github.com/marsbroshok
You can find automatically built Docker images as usual at https://hub.docker.com/r/mapbox/robosat/