Welcome to our project!
Explore the docs »
View Video
·
View Demo
·
Report Bug
·
Request Feature
Table of Contents
As of 2021, the world generated over 2.01 billion tons of municipal solid waste annually. At least 33% of that waste was not managed in an environmentally safe manner. It is estimated that up to 8 million metric tons of plastic reach the planet’s oceans each year. That equates to five grocery bags filled with plastic for every foot of shoreline on earth. Garbage segregation is a critical issue in modern times due to the rising amount of waste generated by society. Traditional methods of garbage segregation involve manual sorting, which is time-consuming, labor-intensive, and often inefficient. AI/ML can provide a solution to this problem by automating the process of garbage segregation. In this project, we propose a system that utilizes AI/ML algorithms to identify and segregate different types of garbage. The system uses image recognition techniques to analyze the images captured by a camera, and then applies machine learning algorithms to classify the garbage into different categories. The system can also learn from its mistakes and improve its accuracy over time. By automating the process of garbage segregation, we can reduce the workload on human workers, increase efficiency, and reduce environmental pollution.
Image classification for recycling has the potential to create significant social impact in a number of ways:
- Environmental sustainability: By automating the sorting of recyclable materials, image classification can help increase the recovery of valuable materials and reduce waste. This can help promote environmental sustainability by conserving resources and reducing greenhouse gas emissions associated with the production of new materials.
- Job creation: The implementation of image classification technology in recycling facilities can create new job opportunities for individuals with skills in technology and data analysis. These jobs can help promote economic growth and provide new career pathways for individuals in the recycling industry.
- Education and awareness: Image classification for recycling can also be used as a tool for education and raising awareness about the importance of recycling. By creating more efficient and accurate recycling processes, individuals and communities may become more engaged in sustainable practices and waste reduction efforts.
- Equity and access: Image classification can also help promote equity and access to recycling services, particularly in communities that may have limited resources or access to recycling facilities. By making recycling processes more efficient, these communities may have greater access to recycling services and a reduced burden of waste disposal. Overall, image classification for recycling has the potential to create significant social impact by promoting environmental sustainability, job creation, education and awareness, and equity and access.
This section should list any major frameworks/libraries used to bootstrap your project. Leave any add-ons/plugins for the acknowledgements section. Here are a few examples.
Intel OneAPI is a comprehensive development platform for building high-performance, cross-architecture applications. It provides a unified programming model, tools, and libraries that allow developers to optimize their applications for Intel CPUs, GPUs, FPGAs, and other hardware. Intel OneAPI includes support for popular programming languages like C++, Python, and Fortran, as well as frameworks for deep learning, high-performance computing, and data analytics. With Intel OneAPI, developers can build applications that can run on a variety of hardware platforms, from edge devices to data centers, and take advantage of the performance benefits of Intel architectures.
In this project os.environ['TF_ENABLE_ONEDNN_OPTS'] = '1' line sets an environment variable called TF_ENABLE_ONEDNN_OPTS to '1'. This enables the use of Intel's OneAPI Deep Neural Network Library (OneDNN) optimizations for TensorFlow on the system where this code is being run. OneDNN is a high-performance library for deep learning that is designed to optimize the performance of deep neural network computations on a variety of hardware platforms. By enabling OneDNN optimizations, this code may run faster on certain hardware architectures that are compatible with OneDNN. In this project, the Conv2D and Dense layers will be automatically optimized using oneDNN, which should result in faster training and inference times on compatible hardware.
The tensorflow.keras module is used to create a convolutional neural network (CNN) model for image classification. The model architecture consists of three convolutional blocks, each followed by a max pooling layer, and three fully connected layers with dropout for regularization.
Finally, the model.compile method is called to configure the optimizer, loss function, and evaluation metric for the model. The optimizer used is Adam, and the loss function used is sparse categorical cross-entropy. The model is also evaluated using the accuracy metric.
The garbage segregation project using AI/ML automates the process of identifying and sorting different types of waste. The system uses image recognition techniques to analyze images captured by a camera and machine learning algorithms to classify the waste into different categories. By accurately identifying and segregating waste, the system can reduce the workload on human workers, increase efficiency, and reduce environmental pollution. The project also promotes responsible waste disposal practices by making people more aware of the types of waste they generate and the proper ways to dispose of them.
These are the steps involved in making this project:
- Importing Libraries
- Data Importing
- Data Exploration
- Data Configuration
- Preparing the Data
- Creating a Generator for Training Set
- Creating a Generator for Testing Set
- Writing the labels into a text file 'Labels.txt'
- Model Creation
- Model Compilation
- Training the Model (batch_size = 32, epochs = 10)
- Testing Predictions
- Saving model as 'modelnew.h5'
- Deploying the Model as a Web Application using Streamlit
✅Building a Garbage Classification for Recycling project using OneDNN provided the opportunity to leverage highly optimized building blocks for implementing deep neural networks. OneDNN's library includes optimized algorithms for common neural network layers, such as convolution, pooling, and normalization, enabling fast and efficient execution of the model. In addition, OneDNN offers support for a variety of programming languages, including C++, Python, and Java. Leveraging OneDNN's optimization capabilities, it was possible to accelerate the training and inference of the deep learning models for garbage classification, and improve the overall throughput and scalability of the system.
✅ Waste management: I gained knowledge of waste management. It is the process of collecting, treating, disposing, and recycling waste materials. It is essential for maintaining a clean and healthy environment as well as preventing the negative impacts of waste on human health and the environment.
✅Image Processing: Building a Garbage Classification for Recycling using machine learning techniques involves processing large amounts of image data. During the project, I have learned how to preprocess the images and extract relevant features to improve the accuracy of your classification models.
✅Machine Learning: While building your Garbage Classification for Recycling system, I gained a deeper understanding of the different types of machine learning algorithms, including supervised, unsupervised, and reinforcement learning. I have also learned how to use deep learning models such as convolutional neural networks (CNNs) for image classification.
✅Model Evaluation: Evaluating the performance of your machine learning models is a critical step in building an effective Garbage Classification for Recycling system. I have learned how to use metrics such as accuracy, precision, and recall to assess the performance of your models and identify areas for improvement.
✅Data Analysis: In addition to collecting and analyzing data, I gained experience in data cleaning, data wrangling, and data visualization. These skills are essential for preparing data for machine learning models and communicating insights to stakeholders.
✅Environmental Sustainability: By working on a project that promotes waste reduction and recycling, you likely gained a deeper understanding of the importance of environmental sustainability. This knowledge has motivated me to explore other ways to reduce waste and promote sustainable practices in your community.
✅Collaboration: Building a project like this likely required collaboration with a team of experts in various fields, such as waste management, machine learning, and data analysis, and I learned the importance of working together to achieve common goals.
Overall, the skills and knowledge I have gained while building Garbage Classification for Recycling system are highly valuable and applicable to a wide range of fields beyond waste management and recycling. Building Garbage Classification for Recycling was a challenging and rewarding experience .