Instructions to use TweeeZT/Nutrivision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use TweeeZT/Nutrivision with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://TweeeZT/Nutrivision") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from TweeeZT/Nutrivision: direct link, hf CLI and curl.
- Browser
- Download file 1.19 kB
-
https://huggingface.co/TweeeZT/Nutrivision/resolve/main/README.md
- Command line
-
hf download hf://TweeeZT/Nutrivision/README.md
-
curl -L -o README.md https://huggingface.co/TweeeZT/Nutrivision/resolve/main/README.md
1.19 kB
metadata
license: gpl-3.0
library_name: tensorflow
tags:
- tensorflow
- keras
- image-classification
- computer-vision
- food
- nutrition
- nutrivision
NutriVision CNN Model
This repository contains the trained CNN model used by NutriVision, a mobile application designed to analyze food and nutrition labels from images.
The model is distributed separately from the main NutriVision source repository because the trained weights are a relatively large binary file and are better suited to dedicated model hosting.
About NutriVision
NutriVision is a full-stack mobile application that combines image processing, OCR, machine learning, and nutrition/ingredient parsing to turn information from food packaging into structured results that are easier to understand.
The overall pipeline looks roughly like this:
Food / Nutrition Label
│
â–¼
Camera Image
│
â–¼
Image Processing
│
â–¼
OCR
(EasyOCR)
│
â–¼
Nutrition / Ingredient
Parsing
│
â–¼
CNN Processing
│
â–¼
Structured Analysis
│
â–¼
NutriVision App