Deep Learning and Computer Vision enthusiast. Primary Skills: Python, OpenCV, Linux (Ubuntu & RHEL), Docker DL Frameworks: Tensorflow, PyTorch, Keras Deep Architectures: ViT (Vision Transformer), VGG, Inception, ResNet, FaceNet etc... Video analytics Framework: Deepstream-5.1, 6, Gstreamer, Nvidia TLT Multi-Media library: FFMPEG Distributed data Streaming: Kafka Object Detection Models: SSD, Faster RCNN, YOLO, RetinaNet 3D Object Detection: MediaPipe Pose Estimation (2D & 3D) & Action Recognition: TRT-Pose, Open Pif-Paf, HRNet, SlowFast, VideoPose3D Object Tracking and Re-Identification: Centroid, SORT, DeepSort, MOT ML CI-CT-CD platform: SageMaker, RoboFlow Cloud Platform: AWS, GCP Big Data Technologies: Spark Retail Solutions: 1. Deep Learning model to capture live inventory from Retail store's. 2. Open-CV and DNN model to convert IP Camera video feed from stores into actionable insights to improve profitability. Research Project: Research Project: Design & Implementation of Deep Learning model to quantify the degree of Human Face acceptability.