Using modanet fashion dataset, the clothes images were classified under 5 season (summer,winter,spring,autumn,all).

Combine Python with machine learning principles to discover hidden patterns in raw data

Puthon 3 with already compiled OpenCV, SimpleCV, TensorFlow, Kera, Scikit-image & learn and many more libraries

Implementation of the model "sketch-RNN" by google for generating sketches with a variational auto encoder

Using CNN to recognize indoor scenes. Dataset: MIT Indoor 67

Fruitify is a charming fruit recognition project that harnesses the power of TensorFlow, an advanced machine learning framework.

Image classification with Keras and Tensorflow

How to build, train, and evaluate a Generative Adversarial Network (GAN) for generating fashion images. The project covers all essential steps, from model building to training and evaluation.

Condutional gan for generating images from sketch

Train a model from a dataset for predicting cat and dog from image.

comparison of different machine learning models such as GB, XGB and NN to see which performs better at real time SYN flood detection

Tuberculosis Vision Scan is an AI-driven tool for detecting tuberculosis from chest X-rays using a fine-tuned VGG16 model with 93.5% accuracy. The project integrates MLOps tools like MLflow, DVC, and AWS CI/CD for efficient model tracking and deployment. A Flask web app allows users to upload X-ray images and receive real-time TB detection results

Image Classifier using CIFAR-10 and TensorFlow/Keras

Developed a working prototype of a University Security Monitoring System using Deep Learning to assist Reva University in maintaining a database of known and unknown persons entering through the entrance gate by detecting the frontal faces of students.

This Streamlit app showcases a compact GPT-based autoregressive language model.

The project is a neural network-based fashion recommendation system built using Python. The model used for this system is Resnet50, which is a deep learning model used for image recognition. The data used for training the model is scraped from Flipkart, with a total of 65,000 images.