Genius Patrick e5f8711dfe | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
mnasnet_0.75_ascend.yaml | 1 year ago | |
mnasnet_0.75_gpu.yaml | 1 year ago | |
mnasnet_1.0_ascend.yaml | 1 year ago | |
mnasnet_1.0_gpu.yaml | 1 year ago | |
mnasnet_1.4_ascend.yaml | 1 year ago | |
mnasnet_1.4_gpu.yaml | 1 year ago |
MnasNet: Platform-Aware Neural Architecture Search for Mobile
Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate. Although significant efforts have been dedicated to design and improve mobile CNNs on all dimensions, it is very difficult to manually balance these trade-offs when there are so many architectural possibilities to consider. In this paper, the authors propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. Unlike previous work, where latency is considered via another, often inaccurate proxy (e.g., FLOPS), our approach directly measures real-world inference latency by executing the model on mobile phones. To further strike the right balance between flexibility and search space size, the authors propose a novel factorized hierarchical search space that encourages layer diversity throughout the network.[1]
Figure 1. Architecture of MnasNet [1]
Our reproduced model performance on ImageNet-1K is reported as follows.
Model | Context | Top-1 (%) | Top-5 (%) | Params (M) | Recipe | Download |
---|---|---|---|---|---|---|
MnasNet-B1-0_75 | D910x8-G | 71.81 | 90.53 | 3.20 | yaml | weights |
MnasNet-B1-1_0 | D910x8-G | 74.28 | 91.70 | 4.42 | yaml | weights |
MnasNet-B1-1_4 | D910x8-G | 76.01 | 92.83 | 7.16 | yaml | weights |
Please refer to the installation instruction in MindCV.
Please download the ImageNet-1K dataset for model training and validation.
It is easy to reproduce the reported results with the pre-defined training recipe. For distributed training on multiple Ascend 910 devices, please run
# distributed training on multiple GPU/Ascend devices
mpirun -n 8 python train.py --config configs/mnasnet/mnasnet_0.75_ascend.yaml --data_dir /path/to/imagenet
If the script is executed by the root user, the
--allow-run-as-root
parameter must be added tompirun
.
Similarly, you can train the model on multiple GPU devices with the above mpirun
command.
For detailed illustration of all hyper-parameters, please refer to config.py.
Note: As the global batch size (batch_size x num_devices) is an important hyper-parameter, it is recommended to keep the global batch size unchanged for reproduction or adjust the learning rate linearly to a new global batch size.
If you want to train or finetune the model on a smaller dataset without distributed training, please run:
# standalone training on a CPU/GPU/Ascend device
python train.py --config configs/mnasnet/mnasnet_0.75_ascend.yaml --data_dir /path/to/dataset --distribute False
To validate the accuracy of the trained model, you can use validate.py
and parse the checkpoint path with --ckpt_path
.
python validate.py -c configs/mnasnet/mnasnet_0.75_ascend.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt
Please refer to the deployment tutorial in MindCV.
[1] Tan M, Chen B, Pang R, et al. Mnasnet: Platform-aware neural architecture search for mobile[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 2820-2828.
No Description
Python Markdown Text other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》