Keras

Model Card: Sudoku Net

Model Overview

  • A Neural Network that solves Sudoku puzzles

Intended Use

  • Use Cases: SuDoKu is a research project aimed at exploring the capabilities of Neural Networks in SuDoKu Puzzles. It serves as an experimental tool rather than a specific real-world application.

Training Details

  • Optimizer: Adam
  • Learning Rate: 1e-3
  • Batch Size: 64K
  • Training Dataset Sudoku Dataset

Models

Model Filename Accuracy
ffn__64x2.keras 0.92932
ffn__64x4.keras 0.92928
ffn__128x2.keras πŸ‘‘ 0.92968
ffn__128x4.keras 0.92892
cnn__64x2.keras 0.92796
cnn__64x4.keras πŸ‘‘ 0.93030
cnn__128x2.keras 0.92786
cnn__128x4.keras 0.92878

Model Usage

  • Users can interact with the model through this Space.
Downloads last month
91
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Dataset used to train Ritvik19/SudokuNet

Space using Ritvik19/SudokuNet 1

Collection including Ritvik19/SudokuNet