Modern Computer Vision & Deep Learning With Python & Pytorch

Modern Computer Vision & Deep Learning With Python & Pytorch
Published 7/2023
MP4 | Video: h264, 1280×720 | Audio: AAC, 44.1 KHz

Computer Vision with Python using Deep Learning for Classification, Instance & Semantic Segmentation, & Object Detection

What you’ll learn

Learn Computer Vision and Deep Learning with Real-world Applications in Python

Learn Deep Convolutional Neural Networks (CNN) for Computer Vision

Computer Vision for Single and Multi-label Classification with Python and Pytorch

Computer Vision for Image Semantic Segmentation with Python and Pytorch

Computer Vision for Image Instance Segmentation with Python and Pytorch

Computer Vision for Object Detection with Python and Pytorch

Google Colab with GPU for Writing Python and Pytorch Code

Learn Data Augmentation with Different Image Transformations

Custom Datasets for Image Classification, Image Segmentation and Object Detection

Hyperparameters Optimization of Deep Learning Models to Improve Performance

Learn Performance Metrics (Accuracy, IOU, Precision, Recall, Fscore)

Transfer Learning with Pretrained Models of Deep Learning in Pytorch

Train Image Segmentation, Classification and Object Detection Models on Custom Datasets

Evaluate and Deploy Image Segmentation, Image Classification and Object Detection Models

Perform Object Detection using RCNN, Fast RCNN, Faster RCNN Models with Python and Pytorch

Perform Semantic Segmentation with UNet, PSPNet, DeepLab, PAN, and UNet++ Models with Pytoch and Python

Perform Instance Segmentation using Mask RCNN on Custom Dataset with Pytorch and Python

Perform Image Single and Multi-label Classification using Deep Learning Models (ResNet, AlexNet) with Pytorch and Python

Visualization of Results, Datasets, and Complete Python/Pytorch Code is Provided for Classification, Segmentation, and Object Detection

Requirements

Computer Vision and Deep Learning with Python and Pytorch is taught in this course by following a complete pipeline from Zero to Mastery

No prior knowledge of Computer Vision and Deep Learning is assumed. Everything will be covered with hands-on trainings

Description

Overview

Section 1: Introduction

Lecture 1 Introduction to Course

Section 2: What is Computer Vision & its Applications

Lecture 2 Introduction to Computer Vision and its Real-world Applications

Lecture 3 Major Computer Vision Tasks

Section 3: Deep Convolutional Neural Networks (CNN) for Computer Vision

Lecture 4 Introduction to Convolutional Neural Networks (CNN)

Section 4: Setting-up Google Colab for Writing Python Code

Lecture 5 Introduction to Google Colab for Python Coding

Lecture 6 Connect Google Colab with Google Drive

Section 5: Image Classification Task of Computer Vision

Lecture 7 Introduction to Single and Multi-label Image Classification

Section 6: Pretrained Models for Single and Multi-Label Image Classification

Lecture 8 Introduction to Pretrained Models

Lecture 9 Deep Learning ResNet and AlexNet Architectures

Lecture 10 Access Data from Google Drive to Colab

Lecture 11 Data Preprocessing for Image Classification

Lecture 12 Single-Label Image Classification using ResNet and AlexNet PreTrained Models

Lecture 13 Single Label Classification Python and Pytorch Code

Lecture 14 Multi-Label Image Classification using Deep Learning Models

Lecture 15 Multi-Label Classification Python and PyTorch Code

Section 7: Transfer Learning for Image Classification

Lecture 16 Introduction to Transfer Learning

Lecture 17 Dataset, Data Augmentation, and Dataloaders

Lecture 18 Dataset for Classification

Lecture 19 FineTuning Deep ResNet Model

Lecture 20 HyperParameteres Optimization for Model

Lecture 21 Training Deep ResNet Model

Lecture 22 Fixed Feature Extractraction using ResNet
Lecture 23 Model Optimization, Training and Results Visualization

Lecture 24 Complete Python Code for Transfer Learning and Dataset

Section 8: Semantic Segmentation Task Of Computer Vision

Lecture 25 Introduction to Semantic Image Segmentation

Lecture 26 Semantic Segmentation Real-World Applications

Section 9: Deep Learning Architectures For Segmentation (UNet, PSPNet, PAN)

Lecture 27 Pyramid Scene Parsing Network (PSPNet) For Segmentation

Lecture 28 UNet Architecture For Segmentation

Lecture 29 Pyramid Attention Network (PAN)

Lecture 30 Multi-Task Contextual Network (MTCNet)

Section 10: Segmentation Datasets, Annotations, Data Augmentation & Data Loading

Lecture 31 Datasets for Semantic Segmentation

Lecture 32 Data Annotations Tool for Semantic Segmentation

Lecture 33 Data Loading with PyTorch Customized Dataset Class

Lecture 34 Data Loading for Segmentation with Python and PyTorch Code

Lecture 35 Data Augmentation using Albumentations with Different Transformations

Lecture 36 Augmentation Python Code

Lecture 37 Learn To Implement Data Loaders In Pytorch

Section 11: Performance Metrics (IOU) For Segmentation Models Evaluation

Lecture 38 Performance Metrics (IOU, Pixel Accuracy, Precision, Recall, Fscore)

Lecture 39 Code (Python and PyTorch)

Section 12: Encoders and Decoders For Segmentation In PyTorch

Lecture 40 Transfer Learning And Pretrained Deep Resnet Architecture

Lecture 41 Encoders for Segmentation with PyTorch Liberary

Lecture 42 Decoders for Segmentation in PyTorch Liberary

Section 13: Implementation, Optimization and Training Of Segmentation Models

Lecture 43 Implement Segmentation Models (UNet, PSPNet, DeepLab, PAN, and UNet++)

Lecture 44 Segmentation Models Code with Python

Lecture 45 Learn To Optimize Hyperparameters For Segmentation Models

Lecture 46 Model Optimaztion Code (Python And PyTorch)

Lecture 47 Training of Segmentation Models

Lecture 48 Model Training Code (Python And PyTorch)

Section 14: Test Models and Visualize Segmentation Results

Lecture 49 Test Models and Calculate IOU,Pixel Accuracy,Fscore

Lecture 50 Test Models and Calculate Performance Scores (Python Code)

Lecture 51 Visualize Segmentation Results and Generate RGB Segmented Map

Lecture 52 Segmentation Results Visualization (Python Code)

Section 15: Complete Code and Dataset for Semantic Segmentation

Lecture 53 Final Code Review

Lecture 54 Complete Code and Dataset is Attached

Section 16: Object Detection Task Of Computer Vision

Lecture 55 Object Detection and its Applications

Section 17: Deep Learning Architectures for Object Detection (R-CNN Family)

Lecture 56 Deep Convolutional Neural Network (VGG, ResNet, GoogleNet)

Lecture 57 RCNN Deep Learning Architectures for Object Detection

Lecture 58 Fast RCNN Deep Learning Architectures for Object Detection

Lecture 59 Faster RCNN Deep Learning Architectures for Object Detection

Section 18: Detectron2 for Ojbect Detection

Lecture 60 Detectron2 for Ojbect Detection with PyTorch

Lecture 61 Perform Object Detection using Detectron2 Pretrained Models

Lecture 62 Python and PyTorch Code

Section 19: Training, Evaluating and Visualizing Object Detection on Custom Dataset

Lecture 63 Custom Dataset for Object Detection

Lecture 64 Dataset for Object Detection

Lecture 65 Train, Evaluate Object Detection Models & Visualizing Results on Custom Dataset

Lecture 66 Python and PyTorch Code

Section 20: Complete Code and Custom Dataset for Object Detection

Lecture 67 Resources: Code and Custom Dataset for Object Detection

Section 21: Instance Segmentation Task of Computer Vision

Lecture 68 What is Instance Segmentation

Section 22: Mask RCNN for Instance Segmentation

Lecture 69 Mask RCNN for Instance Segmentation

Section 23: Training, Evaluating and Visualizing Instance Segmentation on Custom Dataset

Lecture 70 Train, Evaluate Instance Segmentation Model & Visualizing Results on Custom Data

Section 24: Complete Code and Custom Dataset for Instance Segmentation

Lecture 71 Resources: Complete Code and Custom Dataset for Instance Segmentation