Purushothaman's Projects
This repository contains implementation and evaluation scripts for various pre-trained deep learning models applied to binary classification of cats and dogs using transfer learning on a balanced dataset. Explore different architectures such as VGG16, VGG19, ResNet50, InceptionV3, DenseNet121, and MobileNetV2 fine-tuned for accurate classification.
Random Codes - For Learning
Spacy for Key:Value pairs
This repository provides the training codes to classify aerial images using a custom-built model (transfer learning with InceptionResNetV2 as the backbone) and explainers to explain the predictions with LIME and GradCAM on an interface that lets you upload or paste images for classification and see visual explanations.
Leaf-Expert is an AI-powered tool that predicts leaf issues, provides detailed explanations, and offers actionable solutions to cure and prevent plant ailments. Perfect for researchers and gardeners, it combines advanced machine learning with practical plant care insights.
This project offers advanced techniques in text preprocessing, word embeddings, and text classification. Explore methods like Word2Vec and GloVe, and master Multinomial Naive Bayes for accurate predictions. Dive into the world of text clustering and conquer challenges like unbalanced data.
The No-Code Image Classifier provides an intuitive Gradio-based interface for developing and testing image classification models using TensorFlow. This repository simplifies the model development process, allowing users to upload images, configure data augmentation and splits, train models, and make predictions—all without writing code.
The No-Code Image Classifier provides an intuitive Gradio-based interface for developing and testing image classification models using Pytorch. This repository simplifies the model development process, allowing users to upload images, configure data augmentation and splits, train models, and make predictions—all without writing code.
PCOS Diagnostic Analysis
My Github Profile
A chat bot designed to answer queries from a PDF file that you upload- developed utilizing BERT & Transfomers
We've developed a powerful binary dog and cat image classifier, driven by advanced deep learning techniques, and enhanced its transparency using Local Interpretable Model-agnostic Explanations (LIME). Witness the magic as the model accurately predicts dog and cat images while LIME reveals the intricate decision-making process behind each result.
This repository offers a robust solution for multilabel image classification. Utilizing advanced neural networks like VGG16, VGG19, ResNet50, InceptionV3, DenseNet121, and MobileNetV2, the project achieves precise classification across 107 diverse categories.