ID	mobilenetv3_large_100
LR	0.1
Dropout	0.8
Crop Pct	0.875
Momentum	0.9
Batch Size	4096
Image Size	224
Weight Decay	0.00001
Interpolation	bicubic

ID	mobilenetv3_rw
LR	0.1
Dropout	0.8
Crop Pct	0.875
Momentum	0.9
Batch Size	4096
Image Size	224
Weight Decay	0.00001
Interpolation	bicubic

MobileNet V3

rwightman / pytorch-image-models

Last updated on Feb 14, 2021

Parameters 5 Million

FLOPs 287 Million

File Size 21.05 MB

Training Data ImageNet

Training Resources 4x4 TPU Pod

Training Time

Training Techniques	RMSProp, Weight Decay
Architecture	1x1 Convolution, Batch Normalization, Convolution, Dense Connections, Depthwise Separable Convolution, Dropout, Global Average Pooling, Hard Swish, Inverted Residual Block, Residual Connection, ReLU, Softmax, Squeeze-and-Excitation Block
ID	mobilenetv3_large_100
LR	0.1
Dropout	0.8
Crop Pct	0.875
Momentum	0.9
Batch Size	4096
Image Size	224
Weight Decay	0.00001
Interpolation	bicubic
SHOW MORE
SHOW LESS

Parameters 5 Million

FLOPs 287 Million

File Size 21.04 MB

Training Data ImageNet

Training Resources 4x4 TPU Pod

Training Time

Training Techniques	RMSProp, Weight Decay
Architecture	1x1 Convolution, Batch Normalization, Convolution, Dense Connections, Depthwise Separable Convolution, Dropout, Global Average Pooling, Hard Swish, Inverted Residual Block, Residual Connection, ReLU, Softmax, Squeeze-and-Excitation Block
ID	mobilenetv3_rw
LR	0.1
Dropout	0.8
Crop Pct	0.875
Momentum	0.9
Batch Size	4096
Image Size	224
Weight Decay	0.00001
Interpolation	bicubic
SHOW MORE
SHOW LESS

README.md

Summary

MobileNetV3 is a convolutional neural network that is designed for mobile phone CPUs. The network design includes the use of a hard swish activation and squeeze-and-excitation modules in the MBConv blocks.

How do I load this model?

To load a pretrained model:

import timm
m = timm.create_model('mobilenetv3_large_100', pretrained=True)
m.eval()

Replace the model name with the variant you want to use, e.g. mobilenetv3_large_100. 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

@article{DBLP:journals/corr/abs-1905-02244,
  author    = {Andrew Howard and
               Mark Sandler and
               Grace Chu and
               Liang{-}Chieh Chen and
               Bo Chen and
               Mingxing Tan and
               Weijun Wang and
               Yukun Zhu and
               Ruoming Pang and
               Vijay Vasudevan and
               Quoc V. Le and
               Hartwig Adam},
  title     = {Searching for MobileNetV3},
  journal   = {CoRR},
  volume    = {abs/1905.02244},
  year      = {2019},
  url       = {http://arxiv.org/abs/1905.02244},
  archivePrefix = {arXiv},
  eprint    = {1905.02244},
  timestamp = {Tue, 12 Jan 2021 15:30:06 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1905-02244.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Results

Image Classification on ImageNet

Image Classification

BENCHMARK	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
ImageNet	mobilenetv3_large_100	Top 1 Accuracy	75.77%	# 217
		Top 5 Accuracy	92.54%	# 217
ImageNet	mobilenetv3_rw	Top 1 Accuracy	75.62%	# 219
		Top 5 Accuracy	92.71%	# 219