Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
CAOANJIA 98306adbd7 | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
README_CN.md | 1 year ago | |
mnasnet.png | 1 year ago | |
mnasnet0.75_ascend.yaml | 1 year ago | |
mnasnet0.75_gpu.yaml | 1 year ago | |
mnasnet1.0_ascend.yaml | 1 year ago | |
mnasnet1.0_gpu.yaml | 1 year ago | |
mnasnet1.4_ascend.yaml | 1 year ago | |
mnasnet1.4_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, we 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, we propose a novel factorized hierarchical search space that encourages layer diversity throughout the network.
Model | Context | Top-1 (%) | Top-5 (%) | Params (M) | Train T. | Infer T. | Download | Config | Log |
---|---|---|---|---|---|---|---|---|---|
MnasNet-B1-0_75 | D910x8-G | 71.81 | 90.53 | 3.20 | 96s/epoch | model | cfg | log | |
MnasNet-B1-1_0 | D910x8-G | 74.28 | 91.70 | 4.42 | 96s/epoch | model | cfg | log | |
MnasNet-B1-1_4 | D910x8-G | 76.01 | 92.83 | 7.16 | 121s/epoch | model | cfg | log |
Please refer to the installation instruction in MindCV.
Please download the ImageNet-1K dataset for model training and validation.
Hyper-parameters. The hyper-parameter configurations for producing the reported results are stored in the yaml files in mindcv/configs/mnasnet
folder. For example, to train with one of these configurations, you can run:
export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
mpirun -n 8 python train.py -c configs/mnasnet/mnasnet0.75_gpu.yaml --data_dir /path/to/imagenet
Note that the number of GPUs/Ascends and batch size will influence the training results. To reproduce the training result at most, it is recommended to use the same number of GPUs/Ascends with the same batch size.
Detailed adjustable parameters and their default value can be seen in config.py.
To validate the trained model, you can use validate.py
. Here is an example for mnasnet0_75 to verify the accuracy of pretrained weights.
python validate.py
-c configs/mnasnet/mnasnet0.75_ascend.yaml
--data_dir=/path/to/imagenet
--ckpt_path=/path/to/ckpt
To validate the model, you can use validate.py
. Here is an example for mnasnet0_75 to verify the accuracy of your training.
python validate.py
-c configs/mnasnet/mnasnet0.75_ascend.yaml
--data_dir=/path/to/imagenet
--ckpt_path=/path/to/ckpt
Please refer to the deployment tutorial in MindCV.
No Description
Jupyter Notebook 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》