This is a notebook where I test the VIT (Vision Transformer) model under various settings for classifying 10 wildlife animals from the ImageNet dataset. The animals I'm classifying are:
- zebra
- antelope
- bear
- condor
- manatee
- giraffe
- bison
- bald eagle
- alligator
- cheetah
The VIT model is a powerful neural network architecture that has been shown to perform well on a variety of image classification tasks. In this notebook, I'll be testing the model's performance on this specific set of animals, and experimenting with different settings to see how they affect the model's accuracy.
- Predictions:
