vit-base-patch16-224-in21k_car_or_motorcycle

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0301
• Accuracy: 0.9938
• F1: 0.9939
• Recall: 0.9927
• Precision: 0.9951

Model description

This is a binary classification model to distinguish between images of cars and images of motorcycles.

For more information on how it was created, check out the following link: https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/blob/main/Computer%20Vision/Image%20Classification/Binary%20Classification/Car%20or%20Motorcycle/Car_or_Motorcycle_ViT.ipynb

Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

Training and evaluation data

Dataset Source: https://www.kaggle.com/datasets/utkarshsaxenadn/car-vs-bike-classification-dataset

Sample Images From Dataset:

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Recall	Precision
0.6908	1.0	200	0.0372	0.99	0.9902	0.9902	0.9902
0.6908	2.0	400	0.0301	0.9938	0.9939	0.9927	0.9951

Framework versions

• Transformers 4.22.2
• Pytorch 1.12.1
• Datasets 2.5.2
• Tokenizers 0.12.1