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.
A PyTorch implementation of "CoAtNet: Marrying Convolution and Attention for All Data Sizes"
| Date | Stars |
|---|---|
| 2026-07-24 | 396 |
| 2026-07-25 | 396 |
| 2026-07-28 | 396 |
| 2026-07-30 | 396 |
| 2026-08-06 | 396 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# CoAtNet
## Overview
This is a PyTorch implementation of CoAtNet specified in ["CoAtNet: Marrying Convolution and Attention for All Data Sizes"](https://arxiv.org/abs/2106.04803), arXiv 2021.
👉 Check out [MobileViT](https://github.com/chinhsuanwu/mobilevit-pytorch) if you are interested in other **Convolution + Transformer** models.
## Usage
```python
import torch
from coatnet import coatnet_0
img = torch.randn(1, 3, 224, 224)
net = coatnet_0()
out = net(img)
```
Try out other block combinations mentioned in the paper:
```python
from coatnet import CoAtNet
num_blocks = [2, 2, 3, 5, 2] # L
channels = [64, 96, 192, 384, 768] # D
block_types=['C', 'T', 'T', 'T'] # 'C' for MBConv, 'T' for Transformer
net = CoAtNet((224, 224), 3, num_blocks, channels, block_types=block_types)
out = net(img)
```
## Citation
```bibtex
@article{dai2021coatnet,
title={CoAtNet: Marrying Convolution and Attention for All Data Sizes},
author={Dai, Zihang and Liu, Hanxiao and Le, Quoc V and Tan, Mingxing},
journal={arXiv preprint arXiv:2106.04803},
year={2021}
}
```
## Credits
Code adapted from [MobileNetV2](https://github.com/tonylins/pytorch-mobilenet-v2) and [ViT](https://github.com/lucidrains/vit-pytorch).
Excerpt of 1,358 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:153f593653330cc0, topic:transformer