https://github.com/jasonzhu1313/satellite-segmentation
term project for comp540; Image Segmentation to extract the road from high resolution satellite images
https://github.com/jasonzhu1313/satellite-segmentation
Last synced: 2 months ago
JSON representation
term project for comp540; Image Segmentation to extract the road from high resolution satellite images
- Host: GitHub
- URL: https://github.com/jasonzhu1313/satellite-segmentation
- Owner: JasonZhu1313
- License: mit
- Created: 2019-01-25T23:04:38.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-04-19T04:38:21.000Z (over 6 years ago)
- Last Synced: 2025-06-01T10:44:19.708Z (4 months ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 2.31 MB
- Stars: 1
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Satellite-Segmentation
# The functionality of each py file
Config.py - The hyperparameters of the network
customer_init.py - some initialization method
Model.py - abstract model
readfile.py - read a batch of images from file and send it to tensorflow to train (refer to Tensorflow Dataset)
SegnetModel - implementation of segnet model
util.py - util methods
# How to run the code
1. Make several dirs under the data folder:
-- data
-- Logs
-- train
-- val
-- submission
2. download data from kaggle website
3. put the training data under train folder and the test data under val folder
4. You can train your model by writing code in the main function of SegnetModel
```
if __name__ == "__main__":
segmodel = SegnetModel()
segmodel.training()
```
EDA: https://colab.research.google.com/drive/12HpbXiewjQdJaZ3qm1QFEBS3xm_lvYbh#scrollTo=cmWKLEOlQSVo
training: https://github.com/JasonChu1313/Satellite-Segmentation/tree/master/src