Catloris - Machine Learning

Hello, this is machine learning part of Catloris application made by Capstone Team C242-PS149 ✨

Table of Contents

• Introduction
• ML Team
• What We Do?
• What We Use?
• Repositories
• Image Classification Model
• Recommendation System
• Machine Learning Model

Machine Learning Team

Name	Bangkit ID	Contacts
Rizqi Hasanuddin	M479B4KY3948	Github & Linkedin
Mohammad Iqbal Maulana	M562B4KY2570	Github & Linkedin
Zalfa Nazhifah Huwaida	M006B4KX4602	Github & Linkedin

What We Do?

We are developing a food classification & recommendation model that suggests suitable food options to users.

What Packages that we use in Google Colab/Jupyter Notebook?

Packages
Tensorflow
Keras
Scikit-Learn
Pandas
Numpy
Matplotlib

Repositories

Learning Paths	Link
Organization	Github
Machine Learning	Github
Machine Learning API	Github

Machine Learning Model

Food Classification Model

Overview

The model is designed for classifying food pictures into 15 categories to calculate their nutritional values. It uses a Sequential Model approach with TensorFlow and Keras API, leveraging MobileNetV2 for transfer learning.

Model Architecture

• Base Model: MobileNetV2

  • Transfer learning with pre-trained weights from ImageNet.
  • Fine-tuning enabled for some layers.
  • The first 100 layers are frozen to preserve pre-trained features.

• Custom Layers

  • Global Average Pooling: Extracts key features from the MobileNetV2 output.
  • Flattening: Prepares the data for dense layers.
  • Dense Layers with L2 Regularization:
    • A 1024-unit dense layer with ReLU activation and a Dropout rate of 0.3.
    • A 512-unit dense layer with ReLU activation and a Dropout rate of 0.3.
  • Output Layer: A dense layer with softmax activation for classification into 15 categories.

Model Compilation

• Optimizer: Adam
  • Learning rate: 0.0001.
• Loss Function: Categorical Cross-Entropy.
• Evaluation Metric: Accuracy.

For the second model we use KNN for product based recommendation. The recommendation is based on the Body Mass Index, age, fat level.