https://github.com/shunk031/chainer-xception
Chainer implementation of the paper "Xception: Deep Learning with Depthwise Separable Convolutions" (https://arxiv.org/abs/1610.02357).
https://github.com/shunk031/chainer-xception
chainer chainerv4 deep-learning imagenet xception
Last synced: 8 months ago
JSON representation
Chainer implementation of the paper "Xception: Deep Learning with Depthwise Separable Convolutions" (https://arxiv.org/abs/1610.02357).
- Host: GitHub
- URL: https://github.com/shunk031/chainer-xception
- Owner: shunk031
- Created: 2018-04-20T14:35:10.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2018-05-17T08:24:01.000Z (about 8 years ago)
- Last Synced: 2025-04-30T02:38:22.017Z (about 1 year ago)
- Topics: chainer, chainerv4, deep-learning, imagenet, xception
- Language: Python
- Homepage:
- Size: 7.81 KB
- Stars: 5
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# chainer-Xception
This repository contains a [Chainer](https://chainer.org/) implementation for the paper: [Xception: Deep Learning with Depthwise Separable Convolutions](https://arxiv.org/abs/1610.02357) (CVPR 2017, François Chollet).
## Requirements
- Chainer 4.0.0+
- CuPy 4.0.0+
## Use pretrained model
Download the pre-trained caffemodel from [Baidu Cloud](https://pan.baidu.com/s/1gfiTShd).
If `pretrained_model` is specified as `xception.caffemodel`, it automatically loads and converts the caffemodel from `$CHAINER_DATASET_ROOT/pfnet/chainer/models/`, where `$CHAINER_DATASET_ROOT` os set as `$HOME/.chainer/dataset` unless you specify another value by modifying the environment variable.
``` python-console
Python 3.6.2 (default, Oct 31 2017, 12:23:24)
Type 'copyright', 'credits' or 'license' for more information
IPython 6.4.0 -- An enhanced Interactive Python. Type '?' for help.
In [1]: from xception import Xception
In [2]: model = Xception(pretrained_model='xception.caffemodel')
Now loading caffemodel (usually it may take few minutes)
```
## Reference
- [Chollet, François. "Xception: Deep Learning with Depthwise Separable Convolutions." arXiv preprint arXiv:1610.02357 (2016).](https://arxiv.org/abs/1610.02357)