SAJAD WALOO's Projects
Image classification is a fundamental task in computer vision, and Transfer Learning is a powerful technique that leverages pre-trained models to solve new image classification problems with limited data.
The Art Generator using PyTorch is a captivating project that employs the power of Generative Adversarial Networks (GANs) to create imaginative and vivid art-inspired images. Leveraging the PyTorch framework, this model consists of a generator and discriminator duo that collaborate in a dynamic training process.
The goal of this project is to develop an Explainable Deep Learning model that can provide insights and justifications for the decisions made by Convolutional Neural Networks (CNNs) in image classification tasks.
Facial Emotion Recognition is a cutting-edge application of deep learning and computer vision that involves automatically detecting and recognizing emotions from human facial expressions.
This project demonstrates an anomaly detection system using autoencoders, an unsupervised deep learning technique, for fraud detection. The model is trained on a dataset containing normal and fraudulent credit card transactions and showcases its ability to identify fraudulent patterns.
Let's simulate the denoising process using a simple GAN architecture with pre-trained weights for illustrative purposes.
Developed an image classification system using deep learning techniques and Convolutional Neural Networks (CNN) to accurately classify images into predefined categories. The project involved building a CNN model using Python, TensorFlow, and Keras, and training it on the CIFAR-10 dataset.
The "Object Detection using MobileNetV2" project demonstrates the implementation of deep learning techniques for object detection tasks. In this project, we utilize the MobileNetV2 architecture, a lightweight and efficient convolutional neural network, to perform object detection on the CIFAR-10 dataset.
Object Detection with YOLO: Detect multiple objects in real-time using the YOLO algorithm. Pre-trained weights, visualization, and easy integration.
Our sentiment analysis RNN model predicts sentiment (positive/negative) of text data. Trained on customer reviews, it captures sequential dependencies for accurate classification. Evaluate performance using accuracy metrics and visualize training plots. Gain insights into customer opinions and brand perception.
This project utilizes LSTM to predict stock prices. Trained on historical data, it forecasts future prices. Gain insights into potential market trends.