keras EfficientNet介绍，在ImageNet任务上涨点明显 | keras efficientnet introduction
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
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
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) |
| ResNet101 |
23.580 |
7.214 |
6.092 |
44.7M |
42.7M |
[[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-101-deploy.prototxt) |
| ResNet152 |
23.396 |
6.882 |
5.908 |
60.4M |
58.4M |
[[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-152-deploy.prototxt) |
| ResNet50V2 |
24.040 |
6.966 |
5.896 |
25.6M |
23.6M |
[[paper]](https://arxiv.org/abs/1603.05027) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/resnet_v2.py) [[torch]](https://github.com/facebook/fb.resnet.torch/blob/master/models/preresnet.lua) |
| ResNet101V2 |
22.766 |
6.184 |
5.158 |
44.7M |
42.6M |
[[paper]](https://arxiv.org/abs/1603.05027) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/resnet_v2.py) [[torch]](https://github.com/facebook/fb.resnet.torch/blob/master/models/preresnet.lua) |
| ResNet152V2 |
21.968 |
5.838 |
4.900 |
60.4M |
58.3M |
[[paper]](https://arxiv.org/abs/1603.05027) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/resnet_v2.py) [[torch]](https://github.com/facebook/fb.resnet.torch/blob/master/models/preresnet.lua) |
| ResNeXt50 |
22.260 |
6.190 |
5.410 |
25.1M |
23.0M |
[[paper]](https://arxiv.org/abs/1611.05431) [[torch]](https://github.com/facebookresearch/ResNeXt/blob/master/models/resnext.lua) |
| ResNeXt101 |
21.270 |
5.706 |
4.842 |
44.3M |
42.3M |
[[paper]](https://arxiv.org/abs/1611.05431) [[torch]](https://github.com/facebookresearch/ResNeXt/blob/master/models/resnext.lua) |
| InceptionV3 |
22.102 |
6.280 |
5.038 |
23.9M |
21.8M |
[[paper]](https://arxiv.org/abs/1512.00567) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/inception_v3.py) |
| InceptionResNetV2 | 19.744 |
4.748 |
3.962 |
55.9M |
54.3M |
[[paper]](https://arxiv.org/abs/1602.07261) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/inception_resnet_v2.py) |
| Xception |
20.994 |
5.548 |
4.738 |
22.9M |
20.9M |
[[paper]](https://arxiv.org/abs/1610.02357) |
| MobileNet(alpha=0.25) |
48.418 |
24.208 |
21.196 |
0.5M |
0.2M |
[[paper]](https://arxiv.org/abs/1704.04861) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet_v1.py) |
| MobileNet(alpha=0.50) |
35.708 |
14.376 |
12.180 |
1.3M |
0.8M |
[[paper]](https://arxiv.org/abs/1704.04861) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet_v1.py) |
| MobileNet(alpha=0.75) |
31.588 |
11.758 |
9.878 |
2.6M |
1.8M |
[[paper]](https://arxiv.org/abs/1704.04861) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet_v1.py) |
| MobileNet(alpha=1.0) |
29.576 |
10.496 |
8.774 |
4.3M |
3.2M |
[[paper]](https://arxiv.org/abs/1704.04861) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet_v1.py) |
| MobileNetV2(alpha=0.35) |
39.914 |
17.568 |
15.422 |
1.7M |
0.4M |
[[paper]](https://arxiv.org/abs/1801.04381) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet_v2.py) |
| MobileNetV2(alpha=0.50) |
34.806 |
13.938 |
11.976 |
2.0M |
0.7M |
[[paper]](https://arxiv.org/abs/1801.04381) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet_v2.py) |
| MobileNetV2(alpha=0.75) |
30.468 |
10.824 |
9.188 |
2.7M |
1.4M |
[[paper]](https://arxiv.org/abs/1801.04381) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet_v2.py) |
| MobileNetV2(alpha=1.0) |
28.664 |
9.858 |
8.322 |
3.5M |
2.3M |
[[paper]](https://arxiv.org/abs/1801.04381) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet_v2.py) |
| MobileNetV2(alpha=1.3) |
25.320 |
7.878 |
6.728 |
5.4M |
3.8M |
[[paper]](https://arxiv.org/abs/1801.04381) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet_v2.py) |
| MobileNetV2(alpha=1.4) |
24.770 |
7.578 |
6.518 |
6.2M |
4.4M |
[[paper]](https://arxiv.org/abs/1801.04381) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet_v2.py) |
| DenseNet121 |
25.028 |
7.742 |
6.522 |
8.1M |
7.0M |
[[paper]](https://arxiv.org/abs/1608.06993) [[torch]](https://github.com/liuzhuang13/DenseNet/blob/master/models/densenet.lua) |
| DenseNet169 |
23.824 |
6.824 |
5.860 |
14.3M |
12.6M |
[[paper]](https://arxiv.org/abs/1608.06993) [[torch]](https://github.com/liuzhuang13/DenseNet/blob/master/models/densenet.lua) |
| DenseNet201 |
22.680 |
6.380 |
5.466 |
20.2M |
18.3M |
[[paper]](https://arxiv.org/abs/1608.06993) [[torch]](https://github.com/liuzhuang13/DenseNet/blob/master/models/densenet.lua) |
| NASNetLarge |
17.502 |
3.996 |
3.412 |
93.5M |
84.9M |
[[paper]](https://arxiv.org/abs/1707.07012) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/nasnet/nasnet.py) |
| NASNetMobile |
25.634 |
8.146 |
6.758 |
7.7M |
4.3M |
[[paper]](https://arxiv.org/abs/1707.07012) [[tf-models]](https://github.com/tensorflow/models/blob/master/research/slim/nets/nasnet/nasnet.py) |
| EfficientNet-B0 |
22.810 |
6.508 |
5.858 |
5.3M |
4.0M |
[[paper]](https://arxiv.org/abs/1905.11946) [[tf-tpu]](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet) |
| EfficientNet-B1 |
20.866 |
5.552 |
5.050 |
7.9M |
6.6M |
[[paper]](https://arxiv.org/abs/1905.11946) [[tf-tpu]](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet) |
| EfficientNet-B2 |
19.820 |
5.054 |
4.538 |
9.2M |
7.8M |
[[paper]](https://arxiv.org/abs/1905.11946) [[tf-tpu]](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet) |
| EfficientNet-B3 |
18.422 |
4.324 |
3.902 |
12.3M |
10.8M |
[[paper]](https://arxiv.org/abs/1905.11946) [[tf-tpu]](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet) |
| EfficientNet-B4 |
17.040 |
3.740 |
3.344 |
19.5M |
17.7M |
[[paper]](https://arxiv.org/abs/1905.11946) [[tf-tpu]](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet) |
| EfficientNet-B5 |
16.298 |
3.290 |
3.114 |
30.6M |
28.5M |
[[paper]](https://arxiv.org/abs/1905.11946) [[tf-tpu]](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet) |
| EfficientNet-B6 |
15.918 |
3.102 |
2.916 |
43.3M |
41.0M |
[[paper]](https://arxiv.org/abs/1905.11946) [[tf-tpu]](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet) |
| EfficientNet-B7 |
15.570 |
3.160 |
2.906 |
66.7M |
64.1M |
[[paper]](https://arxiv.org/abs/1905.11946) [[tf-tpu]](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet) |
Reference
- tf efficientnet
- efficientnet keras pre-trained weights
- Implementation of EfficientNet model. Keras and TensorFlow Keras.
History
- 20190912: created.
Copyright
- Post author: kezunlin
- Post link: https://kezunlin.me/post/88fbc049/
- Copyright Notice: All articles in this blog are licensed under CC BY-NC-SA 3.0 unless stating additionally.