mainakpal08 / Perro_gato

An image classifier made using deep learning to detect if it is a "cat" image or a "dog" image.

🐶 Perro_gato 🐱

An image classifier that uses deep learning to detect if it is a "cat" image or a "dog" image.

Example:

Cat image :

Result :

Dog image :

Result :

Dependancies

• Used Python Version: 3.6.0
• Install necessary modules with sudo pip3 install -r requirements.txt command.

Predict an image :

You can predict an image with the exsisting trained model by--> python3 predict.py <ImageFileName>

Model Training:

To train the model--> python3 train.py

Model Architecture:

• Input Data Shape: 64x64x3

Layer 1:

• Convolutional Layer 32 filter Filter shape: 3x3

• Activation Function: ReLu

• Max Pooling Pool shape: 2x2

Layer 2:

• Convolutional Layer 32 filter Filter shape: 3x3

• Activation Function: ReLu

• Max Pooling Pool shape: 2x2

Layer 3:

• Convolutional Layer 64 filter Filter shape: 3x3

• Activation Function: ReLu

• Max Pooling Pool shape: 2x2

Classification:

• Flatten

• Dense Size: 64

• Activation Function: ReLu

• Dropout Rate: 0.5

• Dense Size: 2

• Activation Function: Sigmoid

Optimizer: Adadelta

Loss: Binary Crossentropy

Author

Mainak Pal ( @mpalrocks )