A dogs & cats classifier

In this project, it was classified whether the image shows a dog or a cat by means of a convolutional neural network. Likewise, a graphical interface was developed that allows the user to interact with the designed classification model.

1. The input data is normalized and the image labels are encoded in one-hot.
2. Divide the data set following the 60-20-20 rule
3. The neural network model is generated.
4. The designed neural network is trained.
5. The designed classification model is evaluated.
6. The classification model designed with an image foreign to the data with which it was trained, validated and tested is classified.
7. The confusion matrix was calculated from the results obtained.
8. Additionally, the previous steps were repeated, but now with an increase in the training data.
9. Performance is described in terms of the value of the cost function J ("loss") and in terms of accuracy ("accuracy").
10. The model is evaluated: precision, f1

Examples with different images