|
--- |
|
tags: |
|
- image-classification |
|
- timm |
|
library_name: timm |
|
license: mit |
|
datasets: |
|
- imagenet-1k |
|
--- |
|
# Model card for edgenext_base.usi_in1k |
|
|
|
An EdgeNeXt image classification model. Trained on ImageNet-1k by paper authors using distillation (`USI` as per `Solving ImageNet`). |
|
|
|
## Model Details |
|
- **Model Type:** Image classification / feature backbone |
|
- **Model Stats:** |
|
- Params (M): 18.5 |
|
- GMACs: 3.8 |
|
- Activations (M): 15.6 |
|
- Image size: train = 256 x 256, test = 320 x 320 |
|
- **Papers:** |
|
- EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications: https://arxiv.org/abs/2206.10589 |
|
- Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results: https://arxiv.org/abs/2204.03475 |
|
- **Dataset:** ImageNet-1k |
|
- **Original:** https://github.com/mmaaz60/EdgeNeXt |
|
|
|
## Model Usage |
|
### Image Classification |
|
```python |
|
from urllib.request import urlopen |
|
from PIL import Image |
|
import timm |
|
|
|
img = Image.open(urlopen( |
|
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' |
|
)) |
|
|
|
model = timm.create_model('edgenext_base.usi_in1k', pretrained=True) |
|
model = model.eval() |
|
|
|
# get model specific transforms (normalization, resize) |
|
data_config = timm.data.resolve_model_data_config(model) |
|
transforms = timm.data.create_transform(**data_config, is_training=False) |
|
|
|
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 |
|
|
|
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5) |
|
``` |
|
|
|
### Feature Map Extraction |
|
```python |
|
from urllib.request import urlopen |
|
from PIL import Image |
|
import timm |
|
|
|
img = Image.open(urlopen( |
|
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' |
|
)) |
|
|
|
model = timm.create_model( |
|
'edgenext_base.usi_in1k', |
|
pretrained=True, |
|
features_only=True, |
|
) |
|
model = model.eval() |
|
|
|
# get model specific transforms (normalization, resize) |
|
data_config = timm.data.resolve_model_data_config(model) |
|
transforms = timm.data.create_transform(**data_config, is_training=False) |
|
|
|
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 |
|
|
|
for o in output: |
|
# print shape of each feature map in output |
|
# e.g.: |
|
# torch.Size([1, 80, 64, 64]) |
|
# torch.Size([1, 160, 32, 32]) |
|
# torch.Size([1, 288, 16, 16]) |
|
# torch.Size([1, 584, 8, 8]) |
|
|
|
print(o.shape) |
|
``` |
|
|
|
### Image Embeddings |
|
```python |
|
from urllib.request import urlopen |
|
from PIL import Image |
|
import timm |
|
|
|
img = Image.open(urlopen( |
|
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' |
|
)) |
|
|
|
model = timm.create_model( |
|
'edgenext_base.usi_in1k', |
|
pretrained=True, |
|
num_classes=0, # remove classifier nn.Linear |
|
) |
|
model = model.eval() |
|
|
|
# get model specific transforms (normalization, resize) |
|
data_config = timm.data.resolve_model_data_config(model) |
|
transforms = timm.data.create_transform(**data_config, is_training=False) |
|
|
|
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor |
|
|
|
# or equivalently (without needing to set num_classes=0) |
|
|
|
output = model.forward_features(transforms(img).unsqueeze(0)) |
|
# output is unpooled, a (1, 584, 8, 8) shaped tensor |
|
|
|
output = model.forward_head(output, pre_logits=True) |
|
# output is a (1, num_features) shaped tensor |
|
``` |
|
|
|
## Citation |
|
```bibtex |
|
@inproceedings{Maaz2022EdgeNeXt, |
|
title={EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications}, |
|
author={Muhammad Maaz and Abdelrahman Shaker and Hisham Cholakkal and Salman Khan and Syed Waqas Zamir and Rao Muhammad Anwer and Fahad Shahbaz Khan}, |
|
booktitle={International Workshop on Computational Aspects of Deep Learning at 17th European Conference on Computer Vision (CADL2022)}, |
|
year={2022}, |
|
organization={Springer} |
|
} |
|
``` |
|
```bibtex |
|
@misc{https://doi.org/10.48550/arxiv.2204.03475, |
|
doi = {10.48550/ARXIV.2204.03475}, |
|
url = {https://arxiv.org/abs/2204.03475}, |
|
author = {Ridnik, Tal and Lawen, Hussam and Ben-Baruch, Emanuel and Noy, Asaf}, |
|
keywords = {Computer Vision and Pattern Recognition (cs.CV), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences}, |
|
title = {Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results}, |
|
publisher = {arXiv}, |
|
year = {2022}, |
|
} |
|
``` |
|
|
