https://github.com/cedrickchee/octaveconv-pytorch

PyTorch implementation of Octave Convolution for ResNet

https://github.com/cedrickchee/octaveconv-pytorch

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: arxiv.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (6.9%) to scientific vocabulary

Keywords

deep-learning octaveconv octconv octconv-resnet pytorch-implementation resnet
Last synced: 5 months ago · JSON representation

Repository

PyTorch implementation of Octave Convolution for ResNet

Basic Info
  • Host: GitHub
  • Owner: cedrickchee
  • License: mit
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 3.03 MB
Statistics
  • Stars: 0
  • Watchers: 3
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Fork of lxtGH/OctaveConv_pytorch
Topics
deep-learning octaveconv octconv octconv-resnet pytorch-implementation resnet
Created almost 7 years ago · Last pushed almost 7 years ago

https://github.com/cedrickchee/octaveconv-pytorch/blob/master/

# Octave Convolution (OctConv)

## Pytorch implementation of Octave Convolution with other similar operation

This is **third-party/un-official** implementation of the following papers which are presented in [Recent_Convolution.pdf](https://github.com/cedrickchee/octaveconv-pytorch/blob/master/Recent_Convolution.pdf):

1. Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
[paper](https://arxiv.org/abs/1904.05049).
![](fig/OctConv_detailed_design.png)
2. Adaptively Connected Neural Networks.(CVPR 2019)
[paper](https://arxiv.org/abs/1904.03579).
![](fig/adaptive_conv.png)
3. Res2net:A New Multi-scale Backbone Architecture
[paper](https://arxiv.org/abs/1904.01169).
![](fig/res2net.png)

## Plan

- [x] Add Res2Net block with SE-layer
- [x] Add Adaptive-Convolution: both pixel-aware and dataset-aware (done)
- [ ] Add HetConv (optional): (_if I have time :slightly_smiling_face:_)
- [ ] Train on CIFAR
- [ ] Train on ImageNet (_Who can help me train this repo on ImageNet?_)

## Requirements

- Python 3
  - Tested with Python 3.6
- PyTorch
  - Tested with version 1.0.1

## Usage

Check model files under the `nn` directory.

```python
from nn.OCtaveResnet import resnet50
from nn.res2net import se_resnet50
from nn.AdaptiveConvResnet import PixelAwareResnet50, DataSetAwareResnet50

model = resnet50().cuda()
model = se_resnet50().cuda()
model = PixelAwareResnet50().cuda()
model = DataSetAwareResnet50().cuda()
```

## Credits:

Referenced these implementations:

1. OctaveConv: MXNet implementation [here](https://github.com/terrychenism/OctaveConv)
2. AdaptiveCov: Offical tensorflow implementation [here](https://github.com/wanggrun/Adaptively-Connected-Neural-Networks)  

## Other Implementations

- PyTorch
  - https://github.com/gan3sh500/octaveconv-pytorch
  - https://github.com/vivym/OctaveConv.pytorch
- TensorFlow / Keras
  - https://github.com/CyberZHG/keras-octave-conv
  - https://github.com/l5shi/Octave-Conv-Keras

## License

MIT License

Owner

  • Name: Cedric Chee
  • Login: cedrickchee
  • Kind: user
  • Location: PID 1
  • Company: InvictusByte

Lead Software Engineer | LLMs | full stack Go/JS dev, backend | product dev @ startups | 🧑‍🎓 CompSci | alumni: fast.ai, Antler.co

GitHub Events

Total
Last Year