Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/dblN/stochastic_depth_keras
Keras implementation for "Deep Networks with Stochastic Depth" http://arxiv.org/abs/1603.09382
https://github.com/dblN/stochastic_depth_keras
Last synced: about 1 month ago
JSON representation
Keras implementation for "Deep Networks with Stochastic Depth" http://arxiv.org/abs/1603.09382
- Host: GitHub
- URL: https://github.com/dblN/stochastic_depth_keras
- Owner: dblN
- License: mit
- Created: 2016-04-06T15:11:09.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2020-07-21T06:49:00.000Z (over 4 years ago)
- Last Synced: 2024-08-01T22:49:53.125Z (4 months ago)
- Language: Python
- Homepage:
- Size: 16.6 KB
- Stars: 139
- Watchers: 14
- Forks: 28
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-image-classification - unofficial-keras : https://github.com/dblN/stochastic_depth_keras
- awesome-image-classification - unofficial-keras : https://github.com/dblN/stochastic_depth_keras
README
[Deprecated]
No longer maintained
(to catch up with the latest keras/theano/tensorflow but you'll get the idea of how to implement stochastic depth)
# Deep Networks with Stochastic Depth
Keras implementation for "Deep Networks with Stochastic Depth" http://arxiv.org/abs/1603.09382
Original code(in lua/torch) is at https://github.com/yueatsprograms/Stochastic_Depth.
## Usage
1. Install [Theano](https://github.com/Theano/Theano) following its instruction.
2. Install [Keras](https://github.com/fchollet/keras) (I use new API at `keras-1` branch)
```
$ cd keras
$ git checkout keras-1
$ python setup.py install
```
3. Just run `python train.py`
## Known Issues
- Error related to maximum recursion depth
- When the network is deep, there happens error saying it reaches to maximum recursion depth.
- You can resolve this issue by using `sys.setrecursionlimit(max_recursion_depth)`. You should increase `max_recursion_depth` until you get no error (Increasing this value might cause segmentation fault if you don't have enough memory).
## Results
CIFAR10
- Number of layers == 50
- (other configs are same as `train.py`)
