https://github.com/itdxer/deeplab
Deeplab v3 for Semantic Segmentation in NeuPy and Tensorflow
https://github.com/itdxer/deeplab
deep-learning deeplab deeplabv3 neupy semantic-segmentation tensorflow
Last synced: 2 months ago
JSON representation
Deeplab v3 for Semantic Segmentation in NeuPy and Tensorflow
- Host: GitHub
- URL: https://github.com/itdxer/deeplab
- Owner: itdxer
- Created: 2018-12-12T10:46:05.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2018-12-12T15:49:54.000Z (over 6 years ago)
- Last Synced: 2023-08-03T03:55:14.397Z (almost 2 years ago)
- Topics: deep-learning, deeplab, deeplabv3, neupy, semantic-segmentation, tensorflow
- Language: Python
- Homepage:
- Size: 19.5 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Deeplab for semantic segmentation
### Data
1. Download VOC 2012 data from the official website: [http://host.robots.ox.ac.uk/pascal/VOC/voc2012/](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/)
2. Unpack data into the `dataset` folder and make sure that directory `dataset/VOCdevkit/VOC2012` exists.
### Training
Traing the model and save partial progress into the `storage` folder.
```
python -i src/train.py --storage-folder storage --image-size 321 --batch-size 20
```
### Validation
Use one of the stored deeplab models in order to assess network's performance on the validation dataset.
```
python -i src/validate.py --deeplab-weights storage/dump.hdf5
```
### Running tests
```
$ pip install pytest
$ pytest
```