FruitsClassifier on Fruits 360

On this project, I build a classifier on the Fruits 360 dataset using Pytorch. I use a pretrained model and transfer learning, as well as do hyper-parameter search to help increase the accuracy.

 

✍️ Documentation:

- Full Training on Kaggle | GoogleNet | 94% Acc

- Efficient Training with Pytorch Lightning

- GitHub Page

 

📰 Dataset structure

train/test
    |___apple_braeburn_1
        |___r0_0.jpg
        |___r0_10.jpg
            ...
    |___carrot_1
        |___r0_0.jpg
        |___r0_10.jpg
        ...

 

Large batch visualization

 

Separate visualization

 

Single fruit visualization

 

Single fruit visualization with transforms

 

Separate visualization with transforms

 

Batch visualization with transforms

 

Pixel Intensity

 

Visualize the number of classes

 

Visualize loss and accuracy

 

Visualize model predictions: green(correct) and red(incorrect)