Image recognition implementation with Keras. A CNN is built and trained with the CIFAR-10 dataset. Two models are trained: one without data-augmentation (77.25% accuracy) and the other with data-augmentation (78.04% accuracy). Process:
image_recognition.py
- Data processing: one-hot encoding and scaling
- Building and training the CNN
- Training the model
- Training process evaluation
- Evaluation of the model
- Saving the trained model
my_image_recognition.py
- Loading the trained model
- Predicting on the test set
- Evaluation of the predictions
- Predicting on my own images
Followed Course
Some are correct ✔️ some are not ❌
