alpha-131,Varun Pillai,github

Hi , I'm Varun (白ひげ海賊団隊長)

🎮 Gamer and anime fan
📚 Currently diving deep into the world of Machine Learning.
💻 MLOps intern, exploring the intersection of machine learning and operations.
🌟 Always seeking opportunities to grow and contribute to the AI and ML community.
📫 Reach out to me at [email protected] for any inquiries or collaborations.

Varun Pillai's Projects

fictive-frames

Fictive Frames is text-to-image synthesis model, employing variational autoencoders, transformers, and UNET architecture. By encoding textual descriptions into latent spaces, it generates high-quality images, optimizing parameter efficiency. This innovative approach streamlines content creation, catering to diverse industries.

llamaindex-slack-bot

This project showcases a Slackbot leveraging LlamaIndex for NLP, OpenAI LLM for context-aware responses, and Qdrant for efficient data storage. Explore how this bot listens, learns, and interacts intelligently in Slack channels.

mlops-pipeline

This project deploys a pre-trained GPT-2 language model on Amazon SageMaker using Hugging Face Transformers. It encompasses model download, S3 upload, SageMaker deployment, Lambda function integration, and API Gateway setup. Dedicated scripts manage these tasks, supported by a CI/CD pipeline for efficient deployment.

mlpack

mlpack: a fast, header-only C++ machine learning library

opencv

Open Source Computer Vision Library

pneumonia-detection-cnn

This project utilizes VGG16 and ResNet152V2 pre-trained models to detect pneumonia in pediatric chest X-ray images. The dataset includes 5,863 images categorized into Pneumonia and Normal. The models are implemented using TensorFlow and Keras, with a focus on accuracy, precision, recall, and F1-score metrics for evaluation.

text-summarizer

Built with Streamlit, this Text Summarizer leverages spaCy to generate concise summaries by extracting key sentences from input text. Simplify lengthy content effortlessly, enhancing readability and saving time.

transliteration

Transliteration data and models

tweet-emotion-recognition

I crafted a robust sentiment analysis model featuring Bidirectional LSTM layers and embeddings. Leveraging a Sequential model structure and fine-tuning with 'sparse_categorical_crossentropy' loss and 'adam' optimizer, the implementation excels in capturing contextual nuances for precise emotion classification in natural language data.