An image classifier that uses deep learning to detect if it is a "cat" image or a "dog" image.
- Used Python Version: 3.6.0
- Install necessary modules with
sudo pip3 install -r requirements.txt
command.
You can predict an image with the exsisting trained model by-->
python3 predict.py <ImageFileName>
To train the model-->
python3 train.py
- 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
Mainak Pal ( @mpalrocks )