Need help with MoGA?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

220 Stars 34 Forks 15 Commits 7 Opened issues


MoGA: Searching Beyond MobileNetV3

Services available


Need anything else?

Contributors list

MoGA: Searching Beyond MobileNetV3

We propose the first Mobile GPU-Aware (MoGA) neural architecture search in order to be precisely tailored for real-world applications. Further, the ultimate objective to devise a mobile network lies in achieving better performance by maximizing the utilization of bounded resources. While urging higher capability and restraining time consumption, we unconventionally encourage increasing the number of parameters for higher representational power. Undoubtedly, these three forces are not reconcilable and we have to alleviate the tension by weighted evolution techniques. Lastly, we deliver our searched networks at a mobile scale that outperform MobileNetV3 under the similar latency constraints, i.e., MoGA-A achieves 75.9% top-1 accuracy on ImageNet, MoGA-B meets 75.5% which costs only 0.5ms more on mobile GPU than MobileNetV3, which scores 75.2%. MoGA-C best attests GPU-awareness by reaching 75.3% and being slower on CPU but faster on GPU.

MoGA Architectures


  • Python 3.6 +
  • Pytorch 1.0.1 +
  • The pretrained models are accessible after submitting a questionnaire:
  • 国内用户填写问卷 后就可以下载预训练模型。

Benchmarks on ImageNet

ImageNet Dataset

We use the standard ImageNet 2012 dataset, the only difference is that we reorganized the validation set by their classes.


To evaluate,

python3 --model [MoGA_A|MoGA_B|MoGA_C] --device [cuda|cpu] --val-dataset-root [path/to/ILSVRC2012] --pretrained-path [path/to/pretrained_model]


This repository goes with this paper, your citations are welcomed!

    title={MoGA: Searching Beyond MobileNetV3},
    author={Chu, Xiangxiang and Zhang, Bo and Xu, Ruijun},

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.