Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/tmulc18/highwaynetworks
TensorFlow implementation of Highway Networks
https://github.com/tmulc18/highwaynetworks
Last synced: about 2 months ago
JSON representation
TensorFlow implementation of Highway Networks
- Host: GitHub
- URL: https://github.com/tmulc18/highwaynetworks
- Owner: tmulc18
- License: mit
- Created: 2017-08-15T03:08:51.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2017-08-16T05:14:28.000Z (over 7 years ago)
- Last Synced: 2024-10-29T21:10:10.576Z (3 months ago)
- Language: Jupyter Notebook
- Size: 849 KB
- Stars: 2
- Watchers: 4
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Highway Networks
TensorFlow implementation of [Highway Networks](https://arxiv.org/abs/1505.00387). These networks shown to allow training with deeper architectures than traditional networks.
## Data
All evaluations were done using MNIST which can be downloaded from [here](https://pjreddie.com/projects/mnist-in-csv/)The data should be structured like
```
--HighwayNetworks
--Data
--MNIST
--mnist_train.csv
--mnist_test.csv
```## Repository Information
* `Highway Networks Demo.ipynb` notebook that shows how the networks is constructed.
* `Plain vs Highway.ipynb` flexible notebook that compares plain networks with highway networks
* `utils.py` data processing functions
* `modules.py` helper functions for building networks
* `models.py` builds networks