https://github.com/narumiruna/efficientnet-pytorch
A PyTorch implementation of "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks".
https://github.com/narumiruna/efficientnet-pytorch
cifar10 efficientnet imagenet mnist pytorch
Last synced: 6 months ago
JSON representation
A PyTorch implementation of "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks".
- Host: GitHub
- URL: https://github.com/narumiruna/efficientnet-pytorch
- Owner: narumiruna
- License: mit
- Created: 2019-06-01T10:39:33.000Z (over 6 years ago)
- Default Branch: main
- Last Pushed: 2025-03-07T05:12:05.000Z (7 months ago)
- Last Synced: 2025-03-29T13:05:25.393Z (6 months ago)
- Topics: cifar10, efficientnet, imagenet, mnist, pytorch
- Language: Python
- Homepage:
- Size: 312 KB
- Stars: 113
- Watchers: 2
- Forks: 31
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# EfficientNet
https://arxiv.org/abs/1905.11946
## Prerequisites
- Ubuntu
- Python 3
- torch 1.0.1
- torchvision 0.2.2.post3
- tqdm
- mlconfig
## Usage
## Torch Hub
```python
model = torch.hub.load('narumiruna/efficientnet-pytorch', 'efficientnet_b0', pretrained=True)
```
### Train
```shell
$ python train.py -c /path/to/config
```
### Evaluate
```shell
$ python evaluate.py --arch efficientnet_b0 -r /path/to/dataset
```
## Pretrained models
Source: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
| Model Name | Top-1 Accuracy |
| ------ | ------ |
| efficientnet_b0 | 76.52% |
| efficientnet_b1 | 77.80% |
| efficientnet_b2 | 78.83% |
| efficientnet_b3 | 80.19% |
| efficientnet_b4 | 82.27% |
| efficientnet_b5 | 83.11% |
| efficientnet_b6 | |
| efficientnet_b7 | |
## References
- https://arxiv.org/abs/1905.11946
- https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py