qujialing c3003882de | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
README_CN.md | 1 year ago |
The goal of designing MobileNetV3 is to develop the best mobile computer vision architecture to optimize accuracy and
latency on mobile devices.
The highlights of this model are:
Complementary search technology;
a new efficient nonlinear version for mobile environments;
A new efficient network design idea;
New efficient segmentation decoder.
Extensive experiments demonstrate the efficacy and value of MobileNetV3 on a wide range of use cases and mobile phones
Pynative | Pynative | Graph | Graph | ||||||
---|---|---|---|---|---|---|---|---|---|
Model | Top-1 (%) | Top-5 (%) | train (s/epoch) | Infer (ms) | train(s/epoch) | Infer (ms) | Download | Config | |
GPU | MobileNet_v3_large | 74.56 | 91.79 | model | config | ||||
Ascend | MobileNet_v3_large | 74.61 | 91.82 | ||||||
GPU | MobileNet_v3_small | 67.46 | 87.07 | model | config | ||||
Ascend | MobileNet_v3_small | 67.49 | 87.13 |
The yaml config files that yield competitive results on ImageNet for different models are listed in
the configs
folder. To trigger training using preset yaml config.
comming soon
Here is the example for finetuning a pretrained MobileNetV3 on CIFAR10 dataset using Adam optimizer.
python train.py --model=mobilenet_v3_large_100 --pretrained --opt=adam --lr=0.001 ataset=cifar10 --num_classes=10 --dataset_download
Detailed adjustable parameters and their default value can be seen in config.py
To validate the model, you can use validate.py
. Here is an example to verify the accuracy of pretrained weights.
python validate.py --model=mobilenet_v3_large_100 --dataset=imagenet --val_split=val --pretrained
To validate the model, you can use validate.py
. Here is an example to verify the accuracy of your training.
python validate.py --model=mobilenet_v3_large_100 --dataset=imagenet --val_split=val --ckpt_path='./ckpt/mobilenet_v3_large_100-best.ckpt'
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》