ID	mobilenet_v3_large
LR	0.064
Epochs	600
LR Gamma	0.973
Momentum	0.9
Batch Size	128
LR Step Size	2
Random Erase	0.2
Weight Decay	0.00001

ID	mobilenet_v3_small
LR	0.064
Epochs	600
LR Gamma	0.973
Momentum	0.9
Batch Size	128
LR Step Size	2
Random Erase	0.2
Weight Decay	0.00001

MobileNet V3

pytorch / vision

Last updated on Feb 12, 2021

Parameters 5 Million

FLOPs 225 Million

File Size 21.11 MB

Training Data ImageNet

Training Resources 8x NVIDIA V100 GPUs

Training Time

Training Techniques	Weight Decay, RMSProp, AutoAugment
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	mobilenet_v3_large
LR	0.064
Epochs	600
LR Gamma	0.973
Momentum	0.9
Batch Size	128
LR Step Size	2
Random Erase	0.2
Weight Decay	0.00001
SHOW MORE
SHOW LESS

Parameters 3 Million

FLOPs 59 Million

File Size 9.83 MB

Training Data ImageNet

Training Resources 8x NVIDIA V100 GPUs

Training Time

Training Techniques	Weight Decay, RMSProp, AutoAugment
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	mobilenet_v3_small
LR	0.064
Epochs	600
LR Gamma	0.973
Momentum	0.9
Batch Size	128
LR Step Size	2
Random Erase	0.2
Weight Decay	0.00001
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 torchvision.models as models
mobilenet_v3_small = models.mobilenet_v3_small(pretrained=True)

Replace the model name with the variant you want to use, e.g. mobilenet_v3_small. You can find the IDs in the model summaries at the top of this page.

To evaluate the model, use the image classification recipes from the library.

python train.py --test-only --model='<model_name>'

How do I train this model?

You can follow the torchvision recipe on GitHub 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	MobileNet V3 Large	Top 1 Accuracy	74.042%	# 243
		Top 5 Accuracy	91.340%	# 243
ImageNet	MobileNet V3 Small	Top 1 Accuracy	67.668%	# 289
		Top 5 Accuracy	87.402%	# 289