ML & AI Internship Assignment

Objective

Your task is to develop a machine learning model to classify images of items/industrial equipment into two categories:

• Defective
• Non-Defective

Bonus Objectives (Optional)

1. Identify and classify the specific types of defects in the defective images.
2. Optimize the model for hardware-accelerated inference (e.g., using GPU, TPU, NPU, FPGA, etc.).

---

What You'll Do

1. Data Preparation

• Select or create a dataset containing images of industrial equipment labeled as defective or non-defective.
• (Optional) For defective images, include additional labels for specific defect types.
• Preprocess the data (e.g., resizing, normalization, or augmentation, etc.)

---

2. Model Development

• Train a machine learning model (e.g., a Convolutional Neural Network) to classify images into the two categories. You can use any or even multiple types of machine learning that you think fits this problem statement.
• (Optional) Extend the model to classify defect types.
• Ensure your code is modular and well-documented.

---

3. Model Evaluation

• Evaluate the model using metrics such as accuracy, precision, recall, and F1-score, or any other metric you deem necessary.
• Use a confusion matrix to analyze misclassifications.
• Document your findings and provide any insights gained from the analysis.

---

Deliverables

1. Source Code

   • Include your data preprocessing, model training, and evaluation scripts.
   • Ensure all dependencies are listed in a requirements.txt file.

2. Project Report

   • A concise summary (report.md or report.pdf) describing:
     • Your approach and methodology.
     • Model performance and metrics.
     • Insights or challenges faced.
   • If you complete any of the bonus objectives, document them in your report and include the relevant code.

---

Submission Instructions

1. Clone Your Repository

   • Use the following command to clone the repository to your local machine:

     git clone <your-repository-url>

2. Work on Your Solution

   • Implement your code and add your files to the repository.
   • Make sure to regularly commit your work:

     git add .
     git commit -m "Initial implementation of classification model"
     git push origin main

3. Final Submission

   • Push all your changes to the repository.
   • Ensure your main branch contains:
     • Your source code.
     • The project report.
     • Any other relevant files.
   • Verify everything is up-to-date by visiting your repository on GitHub.

4. Notify Us

   • Once you're ready, submit the assignment through GitHub Classroom.

---

Evaluation Criteria

Your submission will be evaluated based on:

1. Understanding of the Problem

   • Demonstrates a clear grasp of the objectives and challenges.

2. Technical Proficiency

   • Quality of the code, use of appropriate tools/frameworks, and methodology.

3. Model Performance

   • Metrics such as accuracy, precision, recall, and F1-score.

4. Documentation Quality

   • Clarity and structure of the report and code comments.

5. Adherence to Guidelines

   • Proper use of Git and timely submission.

---

Need Help?

If you have any questions or need clarification, feel free to reach out through the communication channels provided. Good luck, and enjoy working on the assignment!