https://github.com/affromero/fcn
PyTorch Implementation of Fully Convolutional Networks, for VGG and ResNet backbones.
https://github.com/affromero/fcn
fcn fully-convolutional-networks pytorch pytorch-implementation pytorch-tutorial
Last synced: 5 months ago
JSON representation
PyTorch Implementation of Fully Convolutional Networks, for VGG and ResNet backbones.
- Host: GitHub
- URL: https://github.com/affromero/fcn
- Owner: affromero
- License: mit
- Created: 2019-06-04T02:37:48.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2022-11-22T03:52:11.000Z (over 2 years ago)
- Last Synced: 2023-03-02T21:32:59.304Z (about 2 years ago)
- Topics: fcn, fully-convolutional-networks, pytorch, pytorch-implementation, pytorch-tutorial
- Language: Jupyter Notebook
- Homepage:
- Size: 891 KB
- Stars: 16
- Watchers: 0
- Forks: 14
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# FCN
PyTorch implementation of [Fully Convolutional Networks](https://github.com/shelhamer/fcn.berkeleyvision.org), for VGG and RESNET backbones.
## Requirements
- [pytorch](https://github.com/pytorch/pytorch) >= 1.1.0
- [torchvision](https://github.com/pytorch/vision) >= 0.3.0
- [fcn](https://github.com/wkentaro/fcn)
- [Jupyter Notebook](https://jupyter.org/)
`pip install -r requirements.txt`
## Data
`sh download_dataset.sh` will download the PascalVOC dataset inside **data** folder.
## Training
`python main.py --gpu_id=0 --backbone=vgg --fcn=32s --root_dataset=./data/Pascal_VOC --mode=train`
- **backbone**: vgg or resnet [*vgg default*].
- **fcn**: 32s, 16s, 8s for vgg, and 101, 50 for resnet [*32s default*].
- **mode**: train, val, demo [*train default*].
- **gpu_id**: [*-1 default* (cpu)].
- **resume**: For *val* and *demo*, if no resume path is given, code will use original FCN pre-trained weights.
### Acknowledgement
This repo is built upon [wkentaro](https://github.com/wkentaro/pytorch-fcn)'s code and some snippets can be just a mirror.