Cat Emotion Classifier

🚀 vit-base-cat-emotions

This model is a fine - tuned version of [google/vit - base - patch16 - 224 - in21k](https://huggingface.co/google/vit - base - patch16 - 224 - in21k) for cat emotion classification, achieving certain accuracy on the evaluation set.

🚀 Quick Start

You can try out the model live [here](https://cat - emotion - classifier.streamlit.app/), and check out the [GitHub repository](https://github.com/semihdervis/cat - emotion - classifier) for more details.

This model is a fine - tuned version of [google/vit - base - patch16 - 224 - in21k](https://huggingface.co/google/vit - base - patch16 - 224 - in21k) on the custom dataset. It achieves the following results on the evaluation set:

• Loss: 1.0160
• Accuracy: 0.6353

📚 Documentation

Model Information

Model Index

The model named vit - base - cat - emotions has the following results:

• Task: Image Classification
• Dataset: Custom dataset of type imagefolder (split: validation)
• Metrics: Accuracy with a value of 0.6352941176470588

🔧 Technical Details

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: 10
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.44.1
• Pytorch 2.2.2+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1

📄 License

This project is under the Apache 2.0 license.