Skip to content

Kmohamedalie/Cat_and_Dog_Image_Recognition

Repository files navigation

Cat_and_Dog_Image_Recognition

Applying Deep learning(CNN) to recognise images of cats and dogs. Inspired by two of my classmates pet lovers Sophia and Ekin.

Libraries Keras: Keras Tensorflow: Tensorflow

For more try the following challenge on Kaggle:

Create your own network: Youtube

Kaggle: Competition

Google Developers Demo: Demo

image image

Output:

Data: Cats and Dogs

Validation accurary: 79.65% Training time: 28.6 ms Resources: Google Colab Standard GPU

Model Architecture: 2Cov, 2MaxPool, Flatten, Dense, Final output



Regularized output:

Please Check out the REGULARIZED - Augmented Cat_and_Dog_Image_Recognition notebook for more.

Data: Cats and Dogs

Validation accurary: 72.75% Training time: 45min 44s with magic function(%%time).
Resources: Google Colab Standard TPU
Model Architecture: Cov, MaxPool, Droupout, Flatten, Dense, Final output



Final image prediction:

image