README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - f1
  - recall
  - precision
model-index:
  - name: vit-base-patch16-224-in21k_Simpsons_Family_Members
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9529702970297029
language:
  - en
pipeline_tag: image-classification

vit-base-patch16-224-in21k_Simpsons_Family_Members

This model is a fine-tuned version of google/vit-base-patch16-224-in21k.

It achieves the following results on the evaluation set:

• Loss: 0.2431
• Accuracy: 0.9530
• F1
  • Weighted: 0.9522
  • Micro: 0.9530
  • Macro: 0.9521
• Recall
  • Weighted: 0.9530
  • Micro: 0.9530
  • Macro: 0.9531
• Precision
  • Weighted: 0.9605
  • Micro: 0.9530
  • Macro: 0.9601

Model description

This is a multiclass image classification model of members of The Simpsons family.

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/Multiclass%20Classification/Simpsons%20Family%20Images/Simpsons_family_with_hf_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/williamu32/dataset-bart-or-homer

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	Weighted F1	Micro F1	Macro F1	Weighted Recall	Micro Recall	Macro Recall	Weighted Precision	Micro Precision	Macro Precision
1.5773	1.0	373	1.0482	0.7772	0.7263	0.7772	0.7261	0.7772	0.7772	0.7778	0.8933	0.7772	0.8922
0.1598	2.0	746	0.3902	0.9059	0.9028	0.9059	0.9026	0.9059	0.9059	0.9060	0.9224	0.9059	0.9219
0.027	3.0	1119	0.2431	0.9530	0.9522	0.9530	0.9521	0.9530	0.9530	0.9531	0.9605	0.9530	0.9601

Framework versions

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

License Notice

This model is a fine-tuned derivative of a pretrained model. Users must comply with the original model license.

Dataset Notice

This model was fine-tuned on third-party datasets which may have separate licenses or usage restrictions.