SigNet-PyTorch

A PyTorch implementation of Convolutional Siamese Network for Writer Independent Oflline Signature Verification

Table of Contents:

• SigNet-PyTorch
  • Data
  • Model
  • Experiment configs
  • Requirements
  • Usage
  • Results
  • References
  • License

Data:

Model:

Experiment configs:

- Input size: 105 x 105 x 3
- Batch size: 8
- Learning rate: 1e-4
- Optimizer: Adam

Usage:

• Clone the repository here
• python main.py
• Runs on a GPU, you need to enable cuda in the config file.

Requirements:

Check requirements.txt.

References:

• SigNet Official Implementation: https://bit.ly/2RKUe6S

License:

This project is licensed under Apache-2.0 License - see the LICENSE file for details.