Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
This repository contains the source code of our work on designing efficient CNNs for computer vision
| Date | Stars |
|---|---|
| 2026-07-31 | 413 |
| 2026-08-04 | 413 |
| 2026-08-06 | 413 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Efficient networks for Computer Vision
This repo contains source code of our work on designing efficient networks for different computer vision tasks: <span style="color:blue"> (1) Image classification, (2) Object detection, and (3) Semantic segmentation.</span>
<table>
<tr>
<td colspan=2 align="center"><b>Real-time semantic segmentation using ESPNetv2 on iPhone7. See <a href="https://github.com/sacmehta/ESPNetv2-COREML" target="_blank">here</a> for iOS application source code using COREML.<b></td>
</tr>
<tr>
<td>
<img src="images/espnetv2_iphone7_video_1.gif" alt="Seg demo on iPhone7"></img>
</td>
<td>
<img src="images/espnetv2_iphone7_video_2.gif" alt="Seg demo on iPhone7"></img>
</td>
</tr>
</table>
<table>
<tr>
<td colspan=2 align="center"><b>Real-time object detection using ESPNetv2<b></td>
</tr>
<tr>
<td colspan=2 align="center">
<img src="images/espnetv2_detection_2.gif" alt="Demo 1"></img>
</td>
</tr>
<tr>
<td>
<img src="images/espnetv2_detection_1.gif" alt="Demo 2"></img>
</td>
<td>
<img src="images/espnetv2_detection_3.gif" alt="Demo 3"></img>
</td>
</tr>
</table>
**Table of contents**
1. [Key highlihgts](#key-highlights)
2. [Supported networks](#supported-networks)
3. [Relevant papers](#relevant-papers)
4. [Blogs](#blogs)
5. [Performance comparison](#performance-comparison)
6. [Training receipe](#training-receipe)
7. [Instructions for segmentation and detection demos](#instructions-for-segmentation-and-detection-demos)
8. [Citation](#citation)
9. [License](#license)
10. [Acknowledgements](#acknowledgements)
11. [Contributions](#want-to-help-out)
12. [Notes](#notes)
## Key highlights
* Object classification on the ImageNet and MS-COCO (multi-label)
* Semantic Segmentation on the PASCAL VOC and the CityScapes
* Object Detection on the PASCAL VOC and the MS-COCO
* Supports PyTorch 1.0
* Integrated with Tensorboard for easy visualization of training logs.
* Scripts for downloading different datasets.
* Semantic segmentation application using ESPNetv2 on iPhone can be found [here](https://github.com/sacmehta/ESPNetv2-COREML).
## Supported networks
This repo supports following networks:
* ESPNetv2 (Classification, Segmentation, Detection)
* DiCENet (Classification, Segmentation, Detection)
* ShuffleNetv2 (Classification)
## Relevant papers
* [ESPNet (ECCV'18)](https://arxiv.org/abs/1803.06815)
* [ESPNetv2 (CVPR'19)](https://arxiv.org/abs/1811.11431)
* [DiCENet (arxiv)](https://arxiv.org/pdf/1906.03516.pdf)
## Blogs
* [Faster Training for Efficient Networks](https://medium.com/p/faster-training-of-efficient-cnns-657953aa080?source=email-dc17ff22fa63--writer.postDistributed&sk=f60110289b6157de4c9e0c00c77f51e9)
* [Semantic segmentation using ESPNetv2](https://medium.com/@sachinmehta.ngb/espnetv2-for-semantic-segmentation-9e80f155d522?source=friends_link&sk=91bca9326b088a972c170d1f7f5063e8)
## Performance comparison
### ImageNet
Below figure compares the performance of DiCENet with other efficient networks on the ImageNet dataset. DiCENet outperforms all existing efficient networks, including MobileNetv2 and ShuffleNetv2. More details [here](model/classification/model_zoo/README.md)
### Object detection
Below table compares the performance of our architecture with other detection networks on the MS-COCO dataset. Our network is fast and accurate. More details [here](model/detection/model_zoo/README.md)
<table>
<tr>
<td></td>
<td colspan=3 align="center"> <b>MSCOCO</b></td>
</tr>
<tr>
<td></td>
<td align="center"> <b>Image Size</b> </td>
<td align="center"> <b>FLOPs</b> </td>
<td align="center"> <b>mIOU</b> </td>
<td align="center"> <b>FPS</b>Excerpt of 9,268 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ef7d9fbc47e7892e, topic:object-detection, desc:computer vision
matched fp:ef7d9fbc47e7892e, topic:pytorch