Ayushman Choudhuri's repositories
Mobile_Robotics_Projects
Robot Localization , SLAM , Path Planning and Navigation algoithms implemented using the ROS framework
yolov5-deepsort
The YOLOv5 DeepSORT GitHub repository is an open-source project for real-time object tracking using the YOLOv5 and DeepSORT algorithms. The code is written in Python using PyTorch
crack_detection_and_segmentation
Crack detection and segmentation using a Mask RCNN model from detectron2 library
TerraWatch
TerraWatch is a proof of concept system developed during the TUM AI Hackathon 2024 to detect deforestation from satellite images and reason out the causes and potential environmental effects using computer vision models and multimodal large language models.
unet_segmentation_from_scratch
This is the implementation of the original UNet Architecture with some optimizations. The datasets being used for binary image segmentation is the Carvana dataset and for multiclass segmentation on the Cityscape dataset is being added
AI-Ideation-Assistant
Sokrates is a AI ideation assistant to suggest AI use cases for SME companies in the automotive sector. This was built in collaboration with few students from TU Munich during the TUM AI Makeathon
Complete-Python-3-Bootcamp
Course Files for Complete Python 3 Bootcamp Course on Udemy
Fraunhofer_ICNAP_Hackathon
Time Series Classification of Engine Data using Transformers
Parallel-Manipulator-Platform
Software and Hardware files for the Circle - Parallel Manipulator Robot. This project was completed in 2021
RWTH_Computer_Vision
Computer Vision Assignments - Summer Semester 2022
Stereo_Visual_Odometry
Implementation of Visual Odometry using the KITTI stereo images dataset.
Object_Tracking_Case_Study
Potato detection and tracking - schmiede.one interview task
RWTH_Reinforcement_Learning
This repository contains all the Assignments worked on in the course Reinforcement Learning and Learning based Control
transformer_from_scratch
This repository is a implementation of the original "Attention is all you need" paper from Google. Tensorflow and associated tools have been used for the implementation