---
title: Embryo Classifier
emoji: 🐢
colorFrom: blue
colorTo: pink
sdk: streamlit
sdk_version: 1.36.0
app_file: app.py
pinned: false
license: apache-2.0
short_description: Embryo Quality Identifier
---

Embryo Quality Assessment: A Tandem of Machine Learning and Medicine
Overview
This project leverages the power of machine learning to assist in the medical field, specifically in the assessment of embryo quality during in vitro fertilization (IVF) procedures. By using a trained machine learning model, we aim to provide embryologists with accurate and reliable assessments of embryo quality, thereby increasing the chances of successful pregnancies and reducing the emotional and financial burden on prospective parents.

Model Description
The model is based on EfficientNet, a state-of-the-art Convolutional Neural Network (CNN) architecture. It is trained to classify embryo images into two categories, originally labeled as "0" and "1", which you can map to Low Quality and High Quality, respectively. The model utilizes advanced image processing techniques to analyze and predict the quality of embryos based on provided images.

Features

Predict the quality of embryos from uploaded images.
Provide confidence scores for each quality category.
User-friendly interface built with Streamlit for easy interaction.
Installation

Requirements

Python 3.x
TensorFlow
Streamlit
Pillow
NumPy


Setup

Install the required packages:
pip install streamlit tensorflow pillow numpy

Clone the repository:

git clone https://github.com/yourusername/embryo-quality-assessment.git
cd embryo-quality-assessment
Ensure the trained model is saved in the saved_model/embryo_classifier directory:

If the model is not saved, you can save it using TensorFlow's tf.saved_model.save method.

Usage
Run the Streamlit app:


streamlit run app.py

Upload an Embryo Image:

Open your web browser and navigate to the provided URL (usually http://localhost:8501). Upload an embryo image in JPG, JPEG, or PNG format.

View the Results:

The app will display the uploaded image, classify its quality, and show the confidence scores for each quality category.



Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference