GitHub - qubvel/efficientnet: Implementation on EfficientNet model. Keras.
source link: https://github.com/qubvel/efficientnet
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
README.md
EfficientNet-Keras
This repository contains Keras reimplementation of EfficientNet, the new convolutional neural network architecture from EfficientNet (TensorFlow implementation).
Table of content
About EfficientNet Models
If you're new to EfficientNets, here is an explanation straight from the official TensorFlow implementation:
EfficientNets are a family of image classification models, which achieve state-of-the-art accuracy, yet being an order-of-magnitude smaller and faster than previous models. EfficientNets are based on AutoML and Compound Scaling. In particular, AutoML Mobile framework have been used to develop a mobile-size baseline network, named as EfficientNet-B0; Then, the compound scaling method is used to scale up this baseline to obtain EfficientNet-B1 to B7.
EfficientNets achieve state-of-the-art accuracy on ImageNet with an order of magnitude better efficiency:
-
In high-accuracy regime, EfficientNet-B7 achieves state-of-the-art 84.4% top-1 / 97.1% top-5 accuracy on ImageNet with 66M parameters and 37B FLOPS, being 8.4x smaller and 6.1x faster on CPU inference than previous best Gpipe.
-
In middle-accuracy regime, EfficientNet-B1 is 7.6x smaller and 5.7x faster on CPU inference than ResNet-152, with similar ImageNet accuracy.
-
Compared with the widely used ResNet-50, EfficientNet-B4 improves the top-1 accuracy from 76.3% of ResNet-50 to 82.6% (+6.3%), under similar FLOPS constraint.
Examples
Two lines to create model:
from efficientnet import EfficientNetB0 model = EfficientNetB0(weights='imagenet')
Inference example inference_example.ipynb
Models
Available architectures and pretrained weights (converted from original repo):
Architecture @top1* @top5* Weights EfficientNetB0 0.7668 0.9312 + EfficientNetB1 0.7863 0.9418 + EfficientNetB2 0.7968 0.9475 + EfficientNetB3 0.8083 0.9531 + EfficientNetB4 - - - EfficientNetB5 - - - EfficientNetB6 - - - EfficientNetB7 - - -"*" - topK accuracy score for converted models (imagenet val set)
Weights for B4-B7 are not released yet (issue).
Installation
Requirements:
- keras >= 2.2.0 (tensorflow)
- scikit-image
Source:
$ pip install git+https://github.com/qubvel/efficientnet
PyPI:
$ pip install efficientnet
Recommend
-
51
EfficientNet: Improving Accuracy and Efficiency through AutoML and Model Scaling ...
-
47
Abstract: 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 s...
-
71
卷积神经网络（CNN）通常以固定成本开发，然后再按比例放大，从而在获得更多资源时可以达到更高的准确率。例如，
-
487
README.md EfficientNet PyTorch This repository contains an op-for-op PyTorch reimplementation of EfficientNe...
-
52
readme.md EfficientNet A PyTorch implementation of EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks.
-
10
Take control of named entity recognition with your own Keras model! 11/13/20 by
-
41
How to Convert Your Keras Model to ONNX Intuition I love Keras for its simplicity. With about 10 minutes, I can build a deep learning model with its sequential or functional API with elegant code. However, Keras always load...
-
8
TensorflowJS EfficientNet This repository contains a tensorflowJs implementation of EfficientNet, an object detection model trained on ImageNet and can detect
-
8
LSTM implementation in Keras A little about me
-
8
This article was published as a part of the Data Science Blogathon. Background on Flower Classification Model
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK