https://github.com/tynab/animal-chess

Animal Chess
https://github.com/tynab/animal-chess

a-star a-star-algorithm animal-chess bfs bfs-algorithm board-game breadth-first-search breadth-first-search-algorithm chess chess-game cnn deep-learning game keras numpy pandas scikit-learn search-algorithm sklearn tensorflow

Last synced: 27 days ago
JSON representation

Animal Chess

• Host: GitHub
• URL: https://github.com/tynab/animal-chess
• Owner: Tynab
• Created: 2024-02-18T19:36:29.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-05-26T17:25:59.000Z (7 months ago)
• Last Synced: 2024-12-02T08:58:58.447Z (about 1 month ago)
• Topics: a-star, a-star-algorithm, animal-chess, bfs, bfs-algorithm, board-game, breadth-first-search, breadth-first-search-algorithm, chess, chess-game, cnn, deep-learning, game, keras, numpy, pandas, scikit-learn, search-algorithm, sklearn, tensorflow
• Language: Python
• Homepage: https://tynab.github.io/Animal-Chess/
• Size: 15.8 MB
• Stars: 1
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# ANIMAL CHESS

Animal Chess is a two-player strategy game where players use animal pieces with unique abilities to capture opponents or enter their den, requiring tactical placement and special moves, and the game project collects player data to train AI models.

## LINK DEMO



[Click here to play the game](https://tynab.github.io/Animal-Chess)



## IMAGE DEMO







## CODE DEMO

```python

# Build the model architecture

def build_model(input_shape, activation='relu'):

    # Create a sequential model

    model = Sequential([

        # Input layer specifies the shape of the input data

        Input(shape=input_shape),

        # First convolution layer with 128 filters

        Conv2D(128, (3, 3), padding='same'),

        BatchNormalization(),

        Activation(activation),

        MaxPooling2D((2, 2)),

        # Second convolution layer with 256 filters

        Conv2D(256, (3, 3), padding='same'),

        BatchNormalization(),

        Activation(activation),

        MaxPooling2D((2, 2)),

        # Flatten the output from 2D to 1D before passing to the dense layer

        Flatten(),

        Dense(2048, activation='relu', kernel_regularizer=l2(0.01)),

        Dropout(0.5),

        # Output layer with linear activation to predict a continuous value

        Dense(1, activation='linear')

    ])

    # Compile the model with Adam optimizer and mean squared error loss

    model.compile(optimizer=Adam(learning_rate=0.0001), loss='mean_squared_error', metrics=['mae'])

    # Return the model

    return model

```