Food Type Classification Model

🚀 food_type_classification_model

Easily classify any food product into Plant-based (PLANT_BASED) or Animal-based (ANIMAL_BASED) based on ingredients or product title.

This model simplifies the process of categorizing food products. It uses data from USDA FoodData Central, which labels foods as ANIMAL_BASED or PLANT_BASED according to the available protein type. It's a fine - tuned version of distilbert-base-uncased, achieving excellent results on the evaluation set:

• Loss: 0.0249
• Accuracy: 0.9940

🚀 Quick Start

This model can quickly classify food products into plant - based or animal - based categories. Just input the ingredients or product title, and the model will output the corresponding classification.

✨ Features

• Accurate Classification: Based on the rich data from USDA FoodData Central, it can accurately classify food products.
• Fine - Tuned Model: It is a fine - tuned version of distilbert - base - uncased, which improves the performance on food classification tasks.

🔧 Technical Details

Training Hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e - 05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• num_epochs: 2

Training Results

Framework Versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0

📄 License

This project is licensed under the Apache - 2.0 license.