keras EfficientNet介绍，在ImageNet任务上涨点明显 | keras efficientnet introduction

最新推荐文章于 2024-06-02 07:18:16 发布

kezunlin

最新推荐文章于 2024-06-02 07:18:16 发布

阅读量1.6k

点赞数

分类专栏： kezunlin.me

本文链接：https://blog.csdn.net/weixin_43654079/article/details/103380012

版权

本文介绍了EfficientNet模型，相较于ResNet-50，EfficientNet-B4在相似的FLOPS限制下将精度提高了6.3%，达到82.6%。此外，文章还讨论了预训练的EfficientNet检查点在Keras中的应用以及不同模型在224x224到600x600不同输入尺寸下的性能。

摘要由CSDN通过智能技术生成

本文首发于个人博客https://kezunlin.me/post/88fbc049/，欢迎阅读最新内容！

keras efficientnet introduction

Guide

About EfficientNet Models

params flops

compared with resnet50, EfficientNet-B4 improves the top-1 accuracy from 76.3% of ResNet-50 to 82.6% ( 6.3%), under similar FLOPS constraint.

Using Pretrained EfficientNet Checkpoints

b0-b7 top-1 on imagenet

Keras Models Performance

The top-k errors were obtained using Keras Applications with the TensorFlow backend on the 2012 ILSVRC ImageNet validation set and may slightly differ from the original ones.

The input size used was 224x224 for all models except NASNetLarge (331x331), InceptionV3 (299x299), InceptionResNetV2 (299x299), Xception (299x299),

EfficientNet-B0 (224x224), EfficientNet-B1 (240x240), EfficientNet-B2 (260x260), EfficientNet-B3 (300x300), EfficientNet-B4 (380x380), EfficientNet-B5 (456x456), EfficientNet-B6 (528x528), and EfficientNet-B7 (600x600).

notice

Top-1: single center crop, top-1 error
Top-5: single center crop, top-5 error
10-5: ten crops (1 center 4 corners and those mirrored ones), top-5 error
Size: rounded the number of parameters when include_top=True
Stem: rounded the number of parameters when include_top=False

	Top-1	Top-5	10-5	Size	Stem	References
VGG16	28.732	9.950	8.834	138.4M	14.7M	[[paper]](https://arxiv.org/abs/1409.1556) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/vgg.py)
VGG19	28.744	10.012	8.774	143.7M	20.0M	[[paper]](https://arxiv.org/abs/1409.1556) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/vgg.py)
ResNet50	25.072	7.940	6.828	25.6M	23.6M	[[paper]](https://arxiv.org/abs/1512.03385) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/resnet_v1.py) [[torch]](https://github.com/facebook/fb.resnet.torch/blob/master/models/resnet.lua) [[caffe]](https://github.com/KaimingHe/deep-residual-networks/blob/master/prototxt/ResNet-50-deploy.prototxt)