FruitsClassifier with Pytorch Lightning

On this project, I convert my FruitsClassifier from Pytorch to Pytorch Lightning. I employ a callback module, a checkpoint mode to store and save the model state_dict. I conduct resume training, plot loss and accuracy from previous trains. I check the accuracy for each class and make predictions on images from outside the dataset.

Documentation:

- Convert my Pytorch model to Pytorch Lightning

- FruitsClassifier on Fruits 360

- Full Training on Kaggle | GoogleNet | 94% Acc

- GitHub Page

Training Epochs

Visualize Loss and Accuracy

Visualize model performance on test dataset

Accuracy of each class

Image Predictions from outside the Dataset

Accuracy of each class: green(correct predictions), red(incorrect predictions)