A demonstration of how to use PyTorch to implement Support Vector Machine with one-vs.-all hinge loss. Weighted penalty of each class and square hinge loss are also available.
Requirements
PyTorch==0.2.0 with GPU support
Python==3.5
Approach
The key idea is to optimize a linear classifier with one-vs-all Hinge loss proposed by Dr. Weston and Dr. Watkins.
For more details, please refer the loss function in the code.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].
