FoodVision Mini
Overview
FoodVision Mini is a food image classification model built using PyTorch and EfficientNet-B2.
The model classifies food images into three categories:
- Pizza
- Steak
- Sushi
Model Details
- Architecture: EfficientNet-B2
- Framework: PyTorch
- Task: Image Classification
- Number of Classes: 3
- Model Weights:
09_pretrained_effnet_b2.pth
Usage
Download the model weights using Hugging Face Hub:
from huggingface_hub import hf_hub_download
import torch
model_path = hf_hub_download(
repo_id="Koustav-717/foodvision-mini",
filename="09_pretrained_effnet_b2.pth"
)
Load the downloaded weights into your model architecture:
model.load_state_dict(
torch.load(model_path, map_location="cpu")
)
model.eval()
Intended Use
This model is intended for educational and demonstration purposes, particularly for exploring transfer learning and image classification using PyTorch.
Limitations
- Predictions are limited to pizza, steak, and sushi.
- Performance may vary depending on image quality, lighting, and image composition.
- The model is not intended for production-critical applications.