Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/sshuair/dl-docker-geospatial
Deep learning docker files and docker images for geospatial anaysis.
https://github.com/sshuair/dl-docker-geospatial
deep-learning docker geo machine-learning satellite
Last synced: 16 days ago
JSON representation
Deep learning docker files and docker images for geospatial anaysis.
- Host: GitHub
- URL: https://github.com/sshuair/dl-docker-geospatial
- Owner: sshuair
- Created: 2017-08-07T14:28:04.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-02-18T10:28:33.000Z (over 5 years ago)
- Last Synced: 2024-08-01T00:41:50.321Z (3 months ago)
- Topics: deep-learning, docker, geo, machine-learning, satellite
- Language: Dockerfile
- Homepage:
- Size: 332 KB
- Stars: 35
- Watchers: 6
- Forks: 10
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Deep Learning Docker for Geospatial
Deep learning docker files and docker images for geospatial anaysis. It contains the most popular deep learning frameworks(PyTorch and Tensorflow) with CPU and GPU support (CUDA and cuDNN included). And some other commonly used packages in machine learning and geospatial anaysis.Docker Hub: [deepgeo](https://hub.docker.com/r/sshuair/deepgeo/)
## support docker image tags
- all-cpu-torch1.0.1-tf0.12.0
- all-cuda10-cudnn7-runtime-torch1.0.1-tf0.12.0
- all-cuda10-cudnn7-devel-torch1.0.1-tf0.12.0
- pytorch-1.0.1-cuda10-runtime
- pytorch-1.0.1-cuda10-devel
- tensorflow-0.12.0-cuda10-runtime
- tensorflow-0.12.0-cuda10-devel## packages contain
### deep learning framework
- tensorflow
- keras
- pytorch### machine learning farmework
- scikit-learn
- scikit-image
- xgboost### geospatial packages
- GDAL
- fiona
- shapely
- rasterio
- tifffile
- geopandas### other related packages
- numpy
- scipy
- OpenCV
- Pillow
- jupyter
- matplotlib
- pandas## usage
### build image`docker build -t REPOSITORY:TAG -f Dockerfile .`
### pull image
- cpu version: `docker pull sshuair/deepgeo:[TAG]`
- gpu version: `docker pull sshuair/deepgao:[TAG]`### start container
1. cpu: `docker run -it --name [CONTAINER-NAME] -p 8888:8888 -p 6006:6006 -v /sharedfolder:/workdir sshuair/deepgeo:[TAG] bash`
2. gpu: `nvidia-docker run -it --name [CONTAINER-NAME] -p 8888:8888 -p 6006:6006 -v /sharedfolder:/workdir sshuair/deepgeo:[TAG] bash`### jupyter notebook
If you want run jupyter notebook in a docker container you should use the follow command in a running docker container:
`jupyter notebook --allow-root`