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
Top comments (0)