Deep Learning for Computer Vision

Deep Learning – Computer Vision

Foundation of Computer Vision

  1. Common Architectural Principles of Deep Networks
  2. Building Blocks of Deep Networks
  3. Convolutional Neural Networks (CNNs)
  4. Recurrent Neural Networks
  5. Recursive Neural Networks; Applications to Sequence Data
  6. Anomaly Detection
  7. Tuning Deep Networks
  8. Vectorization
  9. Data Mining (Pre-requisites)

CNN overview

  1. CNN Definition
  2. CNN based Architectures
  3. End to end CNN network
  4. Training CNN
  5. Deployment in Azure Cloud
  6. Performance tuning of CNN network

Advance Computer Vision – Part 1

  1. CNN Architectures with research paper and mathematics
  2. Resnet-5 variants with research paper and practical
  3. AlexNet variants with research paper and practical
  4. GoogleNet variants with research paper and practical
  5. Transfer learning
  6. VGGNet variants with research paper and practical
  7. Inception net variants with research paper and practical
  8. Darknet variants with research paper and practical

Advance Computer Vision – Part 2

  1. Object detection in-depth
  2. Transfer learning
  3. RCNN with research paper and practical
  4. Fast RCNN with research paper and practical
  5. Faster RCNN with research paper and practical
  6. SSD with research paper and practical
  7. SSD lite with research paper and practical

Training of Custom Object Detection

  1. TFOD introduction
  2. Environment setup wtih TFOD
  3. GPU vs TPU vs CPU
  4. GPU Comparison

Advance Computer Vision – Part 3

  1. Yolo v1 with research paper and practical
  2. Retina net
  3. Face net
  4. Detectron2 with practical and live testing

Object segmentation

  1. Semantic segmentation
  2. Panoptic segmentation
  3. Masked RCNN
  4. Practical with Detectron
  5. Practical with TFOD

Object tracking

  1. Detail of object tracking
  2. Kalman filtering
  3. Sort
  4. Deep sort
  5. Object tracking live project with live camera testing

OCR

  1. Introduction to OCR
  2. Various framework and API for OCR
  3. Practical implementation of OCR
  4. Live project deployment for bill parsing

Image captioning

  1. Image captioning overview
  2. Image captioning project with deployment