https://github.com/jaketae/res-mlp
PyTorch implementation of ResMLP: Feedforward networks for image classification with data-efficient training
https://github.com/jaketae/res-mlp
computer-vision image-classification mlp pytorch
Last synced: 23 days ago
JSON representation
PyTorch implementation of ResMLP: Feedforward networks for image classification with data-efficient training
- Host: GitHub
- URL: https://github.com/jaketae/res-mlp
- Owner: jaketae
- License: mit
- Created: 2021-05-10T16:57:41.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2021-05-11T02:45:18.000Z (about 5 years ago)
- Last Synced: 2025-01-29T00:43:57.882Z (over 1 year ago)
- Topics: computer-vision, image-classification, mlp, pytorch
- Language: Python
- Homepage:
- Size: 297 KB
- Stars: 3
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ResMLP
PyTorch implementation of [ResMLP: Feedforward networks for image classification with data-efficient training](https://arxiv.org/abs/2105.03404).
## Quickstart
Clone this repository.
```
git clone https://github.com/jaketae/res-mlp.git
```
Navigate to the cloned directory. You can start using the model via
```python
>>> from res_mlp import ResMLP
>>> model = ResMLP()
```
By default, the model comes with the following parameters:
```python
ResMLP(
image_size=256,
patch_size=16,
in_channels=3,
num_features=128,
expansion_factor=2,
num_layers=6,
num_classes=10,
)
```
## Resources
- [Original Paper](https://arxiv.org/abs/2105.03404)
- [Going deeper with Image Transformers](https://arxiv.org/abs/2103.17239)