# EfficientNet Pruned

#### rwightman / pytorch-image-models

Last updated on Feb 14, 2021

efficientnet_b1_pruned

Parameters 6 Million
FLOPs 490 Million
File Size 24.41 MB
Training Data ImageNet
Training Resources
Training Time

Architecture 1x1 Convolution, Average Pooling, Convolution, Dense Connections, Dropout, Inverted Residual Block, Batch Normalization, Squeeze-and-Excitation Block, Swish efficientnet_b1_pruned 0.882 240 bicubic SHOW MORE SHOW LESS
efficientnet_b2_pruned

Parameters 8 Million
FLOPs 878 Million
File Size 32.00 MB
Training Data ImageNet
Training Resources
Training Time

Architecture 1x1 Convolution, Average Pooling, Convolution, Dense Connections, Dropout, Inverted Residual Block, Batch Normalization, Squeeze-and-Excitation Block, Swish efficientnet_b2_pruned 0.89 260 bicubic SHOW MORE SHOW LESS
efficientnet_b3_pruned

Parameters 10 Million
FLOPs 1 Billion
File Size 37.93 MB
Training Data ImageNet
Training Resources
Training Time

Architecture 1x1 Convolution, Average Pooling, Convolution, Dense Connections, Dropout, Inverted Residual Block, Batch Normalization, Squeeze-and-Excitation Block, Swish efficientnet_b3_pruned 0.904 300 bicubic SHOW MORE SHOW LESS

# Summary

EfficientNet is a convolutional neural network architecture and scaling method that uniformly scales all dimensions of depth/width/resolution using a compound coefficient. Unlike conventional practice that arbitrary scales these factors, the EfficientNet scaling method uniformly scales network width, depth, and resolution with a set of fixed scaling coefficients. For example, if we want to use $2^N$ times more computational resources, then we can simply increase the network depth by $\alpha ^ N$, width by $\beta ^ N$, and image size by $\gamma ^ N$, where $\alpha, \beta, \gamma$ are constant coefficients determined by a small grid search on the original small model. EfficientNet uses a compound coefficient $\phi$ to uniformly scales network width, depth, and resolution in a principled way.

The compound scaling method is justified by the intuition that if the input image is bigger, then the network needs more layers to increase the receptive field and more channels to capture more fine-grained patterns on the bigger image.

The base EfficientNet-B0 network is based on the inverted bottleneck residual blocks of MobileNetV2, in addition to squeeze-and-excitation blocks.

This collection consists of pruned EfficientNet models.

## How do I load this model?

import timm
m = timm.create_model('efficientnet_b1_pruned', pretrained=True)
m.eval()


Replace the model name with the variant you want to use, e.g. efficientnet_b1_pruned. You can find the IDs in the model summaries at the top of this page.

## How do I train this model?

You can follow the timm recipe scripts for training a new model afresh.

## Citation

@misc{tan2020efficientnet,
title={EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks},
author={Mingxing Tan and Quoc V. Le},
year={2020},
eprint={1905.11946},
archivePrefix={arXiv},
primaryClass={cs.LG}
}

@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/rwightman/pytorch-image-models}}
}


# Results

#### Image Classification on ImageNet

##### Image Classification
BENCHMARK MODEL METRIC NAME METRIC VALUE GLOBAL RANK
ImageNet efficientnet_b3_pruned Top 1 Accuracy 80.86% # 74
Top 5 Accuracy 95.24% # 74
ImageNet efficientnet_b2_pruned Top 1 Accuracy 79.91% # 101
Top 5 Accuracy 94.86% # 101
ImageNet efficientnet_b1_pruned Top 1 Accuracy 78.25% # 160
Top 5 Accuracy 93.84% # 160