robosat
robosat copied to clipboard
mapbox
Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water, clouds
Hi, if i have 512x512 segmented masks using my own convnet model and I want to convert it to geojson file, how to do that ?? rs feature is flashing...
Hi , I have prepared tanzania dataset by downloading grid files and tiff files using routines given by rsp commands. and now tiled dataset is available under correct directory structure...
rs download https://tiles.openaerialmap.org/5ac626e091b5310010e0d480/0/5ac626e091b5310010e0d481/{z}/{x}/{y}.png building.tiles
- [ ] Bump packages for both cpu as well as gpu docker images. - [ ] Re-calculate dependencies and lock dependency tree via pip-compile. - [ ] Test end...
Hi All! I've been experimenting with this framework the past few weeks with great success -- thanks to all who have worked on this tool. I've run into an issue...
For #51. WIP, and needs testing. See https://wiki.openstreetmap.org/wiki/Slippy_map_tilenames#Resolution_and_Scale
With the introduction of the batching feature extraction (#148), the inputs to `rs_cover`, `rs_download`, and `rs_rasterize` are likely going to be multiple GEOJSON files. It would be nice if these...
On most of the datasets I'm putting together, there is not always a 1-1 matching of masks to tiles. At the very least there should be clarification that the trainer...
First try at a topology-aware loss function - https://arxiv.org/abs/1712.02190 - https://arxiv.org/abs/1603.08155 The idea is to optimize for topology like connectivity directly instead of just for pixel-wise loss. Here is an...
For https://github.com/mapbox/robosat/issues/157. Adds scSE modules :boom: :rocket: https://arxiv.org/abs/1709.01507 > Squeeze-and-Excitation Networks https://arxiv.org/abs/1803.02579 > Concurrent Spatial and Channel 'Squeeze & Excitation' in Fully Convolutional Networks  _from https://arxiv.org/abs/1803.02579_ Tasks - [x]...