TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Image Classification	CIFAR-10	EfficientNet	Percentage correct	98.9	# 2
Image Classification	CIFAR-100	EfficientNet	Percentage correct	91.7	# 1
Image Classification	Flowers-102	EfficientNet	Accuracy	98.8%	# 1
Image Classification	ImageNet	EfficientNet-B3	Top 1 Accuracy	81.1%	# 28
Image Classification	ImageNet	EfficientNet-B3	Top 5 Accuracy	95.5%	# 23
Image Classification	ImageNet	EfficientNet-B3	Number of params	12M	# 1
Image Classification	ImageNet	EfficientNet-B2	Top 1 Accuracy	79.8%	# 39
Image Classification	ImageNet	EfficientNet-B2	Top 5 Accuracy	94.9%	# 28
Image Classification	ImageNet	EfficientNet-B2	Number of params	9.2M	# 1
Image Classification	ImageNet	EfficientNet-B1	Top 1 Accuracy	78.8%	# 50
Image Classification	ImageNet	EfficientNet-B1	Top 5 Accuracy	94.4%	# 43
Image Classification	ImageNet	EfficientNet-B1	Number of params	7.8M	# 1
Image Classification	ImageNet	EfficientNet-B6	Top 1 Accuracy	84.0%	# 10
Image Classification	ImageNet	EfficientNet-B6	Top 5 Accuracy	96.9%	# 9
Image Classification	ImageNet	EfficientNet-B6	Number of params	43M	# 1
Image Classification	ImageNet	EfficientNet-B7	Top 1 Accuracy	84.4%	# 7
Image Classification	ImageNet	EfficientNet-B7	Top 5 Accuracy	97.1%	# 7
Image Classification	ImageNet	EfficientNet-B7	Number of params	66M	# 1
Image Classification	ImageNet	EfficientNet-B0	Top 1 Accuracy	76.3%	# 72
Image Classification	ImageNet	EfficientNet-B0	Top 5 Accuracy	93.2%	# 59
Image Classification	ImageNet	EfficientNet-B0	Number of params	5.3M	# 1
Image Classification	ImageNet	EfficientNet-B5	Top 1 Accuracy	83.3%	# 15
Image Classification	ImageNet	EfficientNet-B5	Top 5 Accuracy	96.7%	# 11
Image Classification	ImageNet	EfficientNet-B5	Number of params	30M	# 1
Image Classification	ImageNet	EfficientNet-B4	Top 1 Accuracy	82.6%	# 19
Image Classification	ImageNet	EfficientNet-B4	Top 5 Accuracy	96.3%	# 15
Image Classification	ImageNet	EfficientNet-B4	Number of params	19M	# 1
Image Classification	Stanford Cars	EfficientNet	Accuracy	94.7%	# 1
Fine-Grained Image Classification	Stanford Cars	EfficientNet	Accuracy	94.7%	# 3

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/image-classification-on-cifar-100)](https://paperswithcode.com/sota/image-classification-on-cifar-100?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/image-classification-on-flowers-102)](https://paperswithcode.com/sota/image-classification-on-flowers-102?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/image-classification-on-stanford-cars)](https://paperswithcode.com/sota/image-classification-on-stanford-cars?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/image-classification-on-cifar-10)](https://paperswithcode.com/sota/image-classification-on-cifar-10?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/fine-grained-image-classification-on-stanford)](https://paperswithcode.com/sota/fine-grained-image-classification-on-stanford?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/image-classification-on-imagenet)](https://paperswithcode.com/sota/image-classification-on-imagenet?p=efficientnet-rethinking-model-scaling-for)`

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

ICML 2019 • Mingxing Tan • Quoc V. Le

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing network depth, width, and resolution can lead to better performance... (read more)

PDF Abstract

Code

Add Remove

lukemelas/EfficientNet-PyTorch

↳ Quickstart in

Colab

2,693

tensorflow/tpu

2,573

rwightman/pytorch-image-models

1,876

osmr/imgclsmob

907

qubvel/efficientnet

672

See all 36 implementations

Tasks

Add Remove

FINE-GRAINED IMAGE CLASSIFICATION

IMAGE CLASSIFICATION

NEURAL ARCHITECTURE SEARCH

TRANSFER LEARNING

Evaluation Results from the Paper

Add Remove

SOTA for Image Classification on Stanford Cars (using extra training data)

Get a GitHub badge

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	COMPARE
Image Classification	CIFAR-10	EfficientNet	Percentage correct	98.9	# 2	See all
Image Classification	CIFAR-100	EfficientNet	Percentage correct	91.7	# 1	See all
Image Classification	Flowers-102	EfficientNet	Accuracy	98.8%	# 1	See all
Image Classification	ImageNet	EfficientNet-B3	Top 1 Accuracy	81.1%	# 28	See all
Image Classification	ImageNet	EfficientNet-B3	Top 5 Accuracy	95.5%	# 23	See all
Image Classification	ImageNet	EfficientNet-B3	Number of params	12M	# 1	See all
Image Classification	ImageNet	EfficientNet-B2	Top 1 Accuracy	79.8%	# 39	See all
Image Classification	ImageNet	EfficientNet-B2	Top 5 Accuracy	94.9%	# 28	See all
Image Classification	ImageNet	EfficientNet-B2	Number of params	9.2M	# 1	See all
Image Classification	ImageNet	EfficientNet-B1	Top 1 Accuracy	78.8%	# 50	See all
Image Classification	ImageNet	EfficientNet-B1	Top 5 Accuracy	94.4%	# 43	See all
Image Classification	ImageNet	EfficientNet-B1	Number of params	7.8M	# 1	See all
Image Classification	ImageNet	EfficientNet-B6	Top 1 Accuracy	84.0%	# 10	See all
Image Classification	ImageNet	EfficientNet-B6	Top 5 Accuracy	96.9%	# 9	See all
Image Classification	ImageNet	EfficientNet-B6	Number of params	43M	# 1	See all
Image Classification	ImageNet	EfficientNet-B7	Top 1 Accuracy	84.4%	# 7	See all
Image Classification	ImageNet	EfficientNet-B7	Top 5 Accuracy	97.1%	# 7	See all
Image Classification	ImageNet	EfficientNet-B7	Number of params	66M	# 1	See all
Image Classification	ImageNet	EfficientNet-B0	Top 1 Accuracy	76.3%	# 72	See all
Image Classification	ImageNet	EfficientNet-B0	Top 5 Accuracy	93.2%	# 59	See all
Image Classification	ImageNet	EfficientNet-B0	Number of params	5.3M	# 1	See all
Image Classification	ImageNet	EfficientNet-B5	Top 1 Accuracy	83.3%	# 15	See all
Image Classification	ImageNet	EfficientNet-B5	Top 5 Accuracy	96.7%	# 11	See all
Image Classification	ImageNet	EfficientNet-B5	Number of params	30M	# 1	See all
Image Classification	ImageNet	EfficientNet-B4	Top 1 Accuracy	82.6%	# 19	See all
Image Classification	ImageNet	EfficientNet-B4	Top 5 Accuracy	96.3%	# 15	See all
Image Classification	ImageNet	EfficientNet-B4	Number of params	19M	# 1	See all
Image Classification	Stanford Cars	EfficientNet	Accuracy	94.7%	# 1	See all
Fine-Grained Image Classification	Stanford Cars	EfficientNet	Accuracy	94.7%	# 3	See all

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Code Edit Add Remove

Tasks Edit Add Remove

Evaluation Results from the Paper Edit Add Remove

Code

Add Remove

Tasks

Add Remove

Evaluation Results from the Paper

Add Remove