Keras-CNN-cats-vs-dogs-image-classification
This project is an image classification project using a deep-learning based on Convolutional Neural Networks (CNNs) with Keras.
The Dogs vs. Cats is a classic problem for anyone who wants to dive deeper into deep-learning.
The classifier is based on a rather simple CNN architecture and achieved a test accuracy of 94.84 %.
- You can find a link provided by microsoft to the dataset used in ths project here .
- You can find a link to the code output, including history logs and model weights here .
Model performance:
Validation accuracy and loss
Confusion matrix
Model predictions visualized :
Predicting dog images
Predicting Dog images
Predicting cat images
Predicting Cat images