https://github.com/aelnouby/relational-networks
Pytorch implementation of " A simple neural network module for relational reasoning" paper aka Relational networks for visual reasoning.
https://github.com/aelnouby/relational-networks
clevr pytorch relational-networks visual-reasoning
Last synced: about 2 months ago
JSON representation
Pytorch implementation of " A simple neural network module for relational reasoning" paper aka Relational networks for visual reasoning.
- Host: GitHub
- URL: https://github.com/aelnouby/relational-networks
- Owner: aelnouby
- License: gpl-3.0
- Created: 2018-04-01T18:54:40.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2018-04-26T14:30:19.000Z (about 7 years ago)
- Last Synced: 2025-03-28T22:51:13.277Z (2 months ago)
- Topics: clevr, pytorch, relational-networks, visual-reasoning
- Language: Python
- Size: 31.3 KB
- Stars: 9
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Relational-Networks
Pytorch implementation of " A simple neural network module for relational reasoning" paper aka Relational networks for visual reasoning. https://arxiv.org/abs/1706.01427
## Important Note
This implementation includes only the visual pipeline for CLEVR dataset. Best validation accuracy acheived with this implementation is **72%** compared to **96.8%** reported in the paper. This result was acheived by applying a learning rate schedule that doubles the learning rate every 20 epochs (motivated by warmup in https://arxiv.org/abs/1706.02677). The paper itself does not discuss any schedules used, running with schedules gets **65%** at best.
Pull requests and suggestions are welcome to reproduce the results from the paper.
## Training and Valiation Accuracies with warmup
## Requirements
- [Pytorch](http://pytorch.org/)
- [Visdom](https://github.com/facebookresearch/visdom)
- [H5py](https://www.h5py.org/)
- [opencv-python](https://anaconda.org/conda-forge/opencv)
## Usage
### Train
`python3 runtime`
**Arguments**
- `lr` : Learning rate. default: `2.5e-4`
- `batch_size`: default : `64`
- `warmup`: A flag to turn on doubling the learning rate every 20 epochs. default: `False`
- `save_path`: path to checkpoints. Checkpoints are saved for every new best validation accuracy.
- `vis_screen`: Visdom env name. default: `RelNet`
## Other Implementations (Visual pipeline)
- https://github.com/rosinality/relation-networks-pytorch
- https://github.com/mesnico/RelationNetworks-CLEVR