Model card for efficientnet_el_pruned.in1k
A EfficientNet-EdgeTPU image classification model. Knapsack pruned from existing weights.
Model Details
- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 10.6
- GMACs: 8.0
- Activations (M): 30.7
- Image size: 300 x 300
- Papers:
- Accelerator-aware Neural Network Design using AutoML: https://arxiv.org/abs/2003.02838
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946
- Knapsack Pruning with Inner Distillation: https://arxiv.org/abs/2002.08258
- Dataset: ImageNet-1k
Model Usage
Image Classification
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('efficientnet_el_pruned.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
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(
'efficientnet_el_pruned.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, 32, 150, 150])
# torch.Size([1, 40, 75, 75])
# torch.Size([1, 56, 38, 38])
# torch.Size([1, 176, 19, 19])
# torch.Size([1, 232, 10, 10])
print(o.shape)
Image Embeddings
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(
'efficientnet_el_pruned.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, 1536, 10, 10) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
Model Comparison
Explore the dataset and runtime metrics of this model in timm model results.
Citation
@article{gupta2020accelerator,
title={Accelerator-aware neural network design using automl},
author={Gupta, Suyog and Akin, Berkin},
journal={arXiv preprint arXiv:2003.02838},
year={2020}
}
@inproceedings{tan2019efficientnet,
title={Efficientnet: Rethinking model scaling for convolutional neural networks},
author={Tan, Mingxing and Le, Quoc},
booktitle={International conference on machine learning},
pages={6105--6114},
year={2019},
organization={PMLR}
}
@article{aflalo2020knapsack,
title={Knapsack pruning with inner distillation},
author={Aflalo, Yonathan and Noy, Asaf and Lin, Ming and Friedman, Itamar and Zelnik, Lihi},
journal={arXiv preprint arXiv:2002.08258},
year={2020}
}
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
- Downloads last month
- 435
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.