Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/wkentaro/pytorch-fcn
PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)
https://github.com/wkentaro/pytorch-fcn
computer-vision convolutional-networks deep-learning fcn fcn8s pytorch semantic-segmentation
Last synced: 15 days ago
JSON representation
PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)
- Host: GitHub
- URL: https://github.com/wkentaro/pytorch-fcn
- Owner: wkentaro
- License: mit
- Archived: true
- Created: 2017-02-16T18:55:08.000Z (almost 8 years ago)
- Default Branch: main
- Last Pushed: 2023-02-05T15:40:40.000Z (almost 2 years ago)
- Last Synced: 2025-01-17T04:41:19.350Z (16 days ago)
- Topics: computer-vision, convolutional-networks, deep-learning, fcn, fcn8s, pytorch, semantic-segmentation
- Language: Python
- Homepage:
- Size: 32 MB
- Stars: 1,756
- Watchers: 28
- Forks: 482
- Open Issues: 21
-
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE
Awesome Lists containing this project
- awesome-pytorch - pytorch-fcn
- awesome-pytorch - pytorch-fcn
README
# pytorch-fcn
[](https://pypi.python.org/pypi/torchfcn)
[](https://pypi.org/project/torchfcn)
[](https://github.com/wkentaro/pytorch-fcn/actions)
PyTorch implementation of [Fully Convolutional Networks](https://github.com/shelhamer/fcn.berkeleyvision.org).
## Requirements
- [pytorch](https://github.com/pytorch/pytorch) >= 0.2.0
- [torchvision](https://github.com/pytorch/vision) >= 0.1.8
- [fcn](https://github.com/wkentaro/fcn) >= 6.1.5
- [Pillow](https://github.com/python-pillow/Pillow)
- [scipy](https://github.com/scipy/scipy)
- [tqdm](https://github.com/tqdm/tqdm)
## Installation
```bash
git clone https://github.com/wkentaro/pytorch-fcn.git
cd pytorch-fcn
pip install .
# or
pip install torchfcn
```
## Training
See [VOC example](examples/voc).
## Accuracy
At `10fdec9`.
| Model | Implementation | epoch | iteration | Mean IU | Pretrained Model |
|:-----:|:--------------:|:-------:|:-----------:|:-------:|:----------------:|
|FCN32s | [Original](https://github.com/shelhamer/fcn.berkeleyvision.org/tree/main/voc-fcn32s) | - | - | **63.63** | [Download](https://github.com/wkentaro/pytorch-fcn/blob/45c6b2d3f553cbe6369822d17a7a51dfe9328662/torchfcn/models/fcn32s.py#L34) |
|FCN32s | Ours |11 | 96000 | 62.84 | |
|FCN16s | [Original](https://github.com/shelhamer/fcn.berkeleyvision.org/tree/main/voc-fcn16s) | - | - | **65.01** | [Download](https://github.com/wkentaro/pytorch-fcn/blob/45c6b2d3f553cbe6369822d17a7a51dfe9328662/torchfcn/models/fcn16s.py#L17) |
|FCN16s | Ours |11 | 96000 | 64.91 | |
|FCN8s | [Original](https://github.com/shelhamer/fcn.berkeleyvision.org/tree/main/voc-fcn8s) | - | - | **65.51** | [Download](https://github.com/wkentaro/pytorch-fcn/blob/45c6b2d3f553cbe6369822d17a7a51dfe9328662/torchfcn/models/fcn8s.py#L17) |
|FCN8s | Ours | 7 | 60000 | 65.49 | |
|FCN8sAtOnce | [Original](https://github.com/shelhamer/fcn.berkeleyvision.org/tree/main/voc-fcn8s-atonce) | - | - | **65.40** | |
|FCN8sAtOnce | Ours |11 | 96000 | 64.74 | |
Visualization of validation result of FCN8s.
## Cite This Project
If you use this project in your research or wish to refer to the baseline results published in the README, please use the following BibTeX entry.
```bash
@misc{pytorch-fcn2017,
author = {Ketaro Wada},
title = {{pytorch-fcn: PyTorch Implementation of Fully Convolutional Networks}},
howpublished = {\url{https://github.com/wkentaro/pytorch-fcn}},
year = {2017}
}
```