What you'll learn
- Basic fundamentals of Computer vision.
- Image and video processing with OpenCV and mediapipe libraries.
- Data augmentation and data annotation.
- CNN architecture, hyper parameter tuning and transfer learning.
- Generative Adversarial Networks.
- Image classification, Object detection, Image segmentation, Face recognition, Pose estimation, Face generation, Image filtering, Art and Painting generation etc.
- Project management, development and deployment.
- Web scraping techniques.
- Hands on experience in real world projects.
- API development using FASTAPI framework.
- Computer vision interview questions.
- Computer vision mock interview preparation.
- Helping resume creation.
Requirements
- Carry your own laptop with decent configurations
- Knowledge about Python programming language.
- Machine learning and Deep learning concepts.
- Familiar with TensorFlow and Pytorch frameworks.
-
Course overview
-
Course outcome
-
Installing anaconda, jupyter notebook
-
Working with environments
-
Industrial and real-world applications of Computer vision
-
Importance of Computer vision
-
Computer vision pipeline
-
Getting started with images
-
Getting started with videos
-
Drawing functions
-
Basic operations on image
-
Arithmetic operations on images
-
Changing colorspaces
-
Geometric transformations of images
-
Image thresholding
-
Smoothing images
-
Morphological transformations
-
Image gradients
-
Canny edge detection
-
Image pyramids
-
Contours in OpenCV
-
Template matching
-
Image segmentation with watchrshed algorithm
-
Interactive foreground extraction using grabCut algorithm
-
Feature detection
-
Object detection
-
Project 1
-
Project 2
-
Various operations on video
-
Meanshift and camshift
-
Background subtraction
-
Video filters
-
Video analysis
-
Introduction of mediapipe
-
Image processing with mediapipe
-
Video processing with mediapipe
-
Project 1
-
Project 2
-
Introduction of Data augmentation
-
Importance of Data augmentation
-
Data Augmentation with Augmentations
-
Data Augmentation with Imgaug
-
Data augmentation with scikit-image
-
Project 1
-
Introduction of Data annotation
-
Importance of Data annotation
-
Data annotation with VGG annotator
-
Data annotation with LabelImg
-
Data annotation with MakeSense.ai
-
Project 1
-
Introduction of CNN
-
CNN vs ANN
-
Importance of CNN
-
Architecture of CNN
-
Kernels, channels, filters, stride and padding
-
Convolutional, pooling and fully connected layers
-
Dropout, regularizations methods
-
Building custom Convolutional Neural Network
-
Model fine tuning
-
Project 1
-
Introduction of Transfer learning
-
Working flow and importance of transfer learning
-
Working with Pretrained models
-
VGG models
-
ResNet models
-
Inception models
-
Project 1
-
Project 2
-
Project 3
-
Introduction of Object detection
-
Object localization
-
Sliding window
-
Bounding boxes
-
Intersection over union (IoU)
-
Non-Max suppression
-
Overlapping objects
-
Single shot detector (SSD)
-
Region with CNN (RCNN)
-
Fast RCNN
-
Faster RCNN
-
YOLO models
-
Deeplabv3
-
Project 1
-
Project 2
-
Project 3
-
Introduction of Image segmentation
-
Type of Image segmentations
-
Semantic segmentation
-
Instance segmentation
-
Mask R-CNN
-
UNet model
-
Detectron2
-
Project 1
-
Project 2
-
Getting started with GANs
-
Applications of GANs
-
Building custom GANs model
-
Working with DCGAN
-
Working with CycleGAN
-
Working with StyleGAN
-
Working with Pix2PixGAN
-
Working with SRGAN
-
Project 1
-
Project 2
-
Introduction of Open AI’s Dall E 2 model
-
Web scraping techniques
-
FASTAPI development
-
GitHub management
-
Project deployment
-
Level up your Kaggle profile
Download The File
- file name
- file name
