Cat segmentation with deep learning.
Database created by myself.

Orijinal	Segmented

python3 predict.py <ImageFileName>

python3 train.py

tensorboard --logdir=Data/Checkpoints/logs

• Input Data Shape: 64x64x3

• Convolutional Layer 32 filter Filter shape: 3x3 Strides: 1x1

• Activation Function: ReLu

• Convolutional Layer 64 filter Filter shape: 3x3 Strides: 1x1

• Activation Function: ReLu

• Transpose Convolutional Layer 64 filter Filter shape: 3x3 Strides: 1x1

• Activation Function: ReLu

• Merge Layer

• Transpose Convolutional Layer 1 filter Filter shape: 3x3 Strides: 1x1

• Activation Function: Sigmoid

• Used Python Version: 3.6.0

• Install necessary modules with sudo pip3 install -r requirements.txt command.

• We work on 64x64 image also if you use bigger, program will automatically return to 64x64.