vit-base-patch16-224-in21k_male_or_female_eyes

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: 0.0810
• Accuracy: 0.9727
• F1: 0.9741
• Recall: 0.9666
• Precision: 0.9818

Model description

This is a binary classification model to distinguish between male and female eyes.

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/Male%20or%20Female%20Eyes/are_they_male_or_female_eyes_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/pavelbiz/eyes-rtte

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Recall	Precision
0.1998	1.0	577	0.2365	0.9072	0.9196	0.9976	0.8530
0.0846	2.0	1154	0.0810	0.9727	0.9741	0.9666	0.9818
0.0309	3.0	1731	0.0852	0.9809	0.9821	0.9837	0.9805

Framework versions

• Transformers 4.25.1
• Pytorch 1.12.1
• Datasets 2.8.0
• Tokenizers 0.12.1