Model Description:

This model embodies a Vision Transformer (ViT) architecture tailored for image classification tasks. It's honed to accurately categorize images into three specific classes: Button, RadioButton, and CheckBox.

Training Data:

It's trained on a dataset comprising images from the three classes—Button, RadioButton, and CheckBox—enabling it to adeptly recognize and classify these distinct visual elements.

Model Trained Using AutoTrain

• Problem type: Multi-class Classification
• Model ID: 84935142669
• CO2 Emissions (in grams): 1.0491

Validation Metrics

• Loss: 0.111
• Accuracy: 0.969
• Macro F1: 0.935
• Micro F1: 0.969
• Weighted F1: 0.969
• Macro Precision: 0.934
• Micro Precision: 0.969
• Weighted Precision: 0.970
• Macro Recall: 0.939
• Micro Recall: 0.969
• Weighted Recall: 0.969