Welcome to my official submission repository for the GENZ Educatewing AI Internship held during Summer 2025.
This repository documents two major AI projects completed as part of the internship assignment – focused on real-world applications of Natural Language Processing (NLP) and Computer Vision (CV) using Deep Learning.
| Field | Details |
|---|---|
| Name | Somapuram Uday |
| Roll No | 229X1A2856 |
| College | G. Pulla Reddy Engineering College (Autonomous) |
| Branch | Computer Science and Technology |
| Department | Computer Science and Engineering |
| Organization | GENZ EDUCATEWING |
| Mode | Online (Self-paced via LMS) |
| Internship Batch | May–June 2025 |
This project explores how Convolutional Neural Networks (CNNs) can be applied to classify text sentiment from movie reviews. The objective is to build a model that predicts positive or negative sentiment using word embeddings and 1D convolution layers.
- Dataset: IMDB Movie Reviews (Keras)
- Libraries: TensorFlow, Keras, NLTK, scikit-learn
- Preprocessing: Tokenization, Stopword removal, Padding
- Model: CNN with GlobalMaxPooling, Dropout, and Sigmoid
- Evaluation: Accuracy, F1 Score, AUC, Confusion Matrix
🔗 GitHub Source: SENTIMENT_ANALYSIS_CNN/
✅ This is a standalone project and includes code, sample output, and evaluation.
This project implements YOLOv8 (You Only Look Once) for detecting and classifying objects in real-time. The focus is on training or running pre-trained YOLOv8 models to locate objects in images or video frames using bounding boxes.
- Dataset: COCO / PASCAL VOC (or custom images)
- Tools: YOLOv8 (Ultralytics), OpenCV, Python
- Model Type: Pre-trained or fine-tuned YOLOv8
- Evaluation: mAP (Mean Average Precision), IOU, FPS
🔗 GitHub Source: OBJECT_DETECTION_YOLO/
📓 Colab Notebook: yolo_object_detection.ipynb
✅ This project is now live and includes code and output screenshots.
| Component | Tools / Libraries |
|---|---|
| Language | Python 3.10 |
| Deep Learning | TensorFlow, Keras, YOLOv8 |
| NLP Tools | NLTK, Regex, scikit-learn |
| CV Tools | OpenCV, Ultralytics YOLO |
| Platform | Google Colab, Jupyter Notebooks |
💡 Recommended: Run on Google Colab for smooth experience with GPU.
SENTIMENT_ANALYSIS_CNN/code/Sentiment_Analysis_Using_CNN.ipynb
- Open in Colab
- Runtime → Change Runtime Type → Select GPU
- Click "Run All"
- Model trains in ~3–5 minutes
YOLO_Based_Object_Detection/code/yolo_object_detection.ipynb
- Open the notebook in Colab
- Follow the step-wise instructions to install, load, and run detection
- Train on
coco128.yamlor use pre-trained weights - Visualize predictions using
matplotlibandPIL
This AI internship allowed me to:
- ✅ Apply CNNs for real-world NLP problems
- ✅ Understand and utilize object detection using YOLOv8
- ✅ Gain hands-on experience in deep learning workflows
- ✅ Document and evaluate model performance
- 👨💻 Name: Somapuram Uday
- 📧 Email: 229x1a2856@gprec.ac.in
- 🔗 GitHub: github.com/udaycodespace
- 🔗 LinkedIn: linkedin.com/in/somapuramuday