Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
tjulitianyi 61c0122c91 | 1 year ago | |
---|---|---|
Bonsai | 1 year ago | |
Convolutional Bonsai | 1 year ago | |
.gitattributes | 1 year ago | |
ConvBonsai.ipynb | 1 year ago | |
README.md | 1 year ago | |
main.py | 1 year ago | |
model.py | 1 year ago | |
model_trainer.py | 1 year ago | |
utils.py | 1 year ago |
Its a recent research by Microsoft Research India on non linear decision tree based method for classification purpose. It achieves high accuracy with less size for resource constraint devices. I am reproducing the code with a bit of simplification.
Link to Bonsai Model research done by Microsoft Research India : https://github.com/Microsoft/EdgeML
Modified the current bonsai model to include convolutional layers which further decreases the model size increases CNNs explainability and increamental learning can be done.
Link to Comparison of different other models and report by our group on this model : https://github.com/yadavdeepak95/Pocket-ML
A recent Publication following this method is : https://arxiv.org/pdf/1904.08249.pdf
It's by default set to use cifar 10 dataset.
Run
python ./main.py
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》