Scribd Logo
Upload

Welcome to Scribd!

  • 59 views

    Deep Learning With Pytorch: Ai Courses by Opencv

    Uploaded by

    Lohith B M Bandi
    This document outlines the modules of an AI course in computer vision using PyTorch. Module 1 introduces neural networks and their history as well as applications of deep learning such as speech recognition and medical diagnostics. Module 2 covers image classification, including network architectures like AlexNet and ResNet, and evaluation metrics. Module 3 is about image segmentation, including semantic segmentation and network architectures like U-Net and DeepLab. Module 4 discusses object detection, both traditional and deep learning-based approaches. Module 5 focuses on deploying applications using PyTorch's C++ API and cloud deployment.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Deep Learning With Pytorch: Ai Courses by Opencv

    Uploaded by

    Lohith B M Bandi
    59 views5 pages
    This document outlines the modules of an AI course in computer vision using PyTorch. Module 1 introduces neural networks and their history as well as applications of deep learning such as speech recognition and medical diagnostics. Module 2 covers image classification, including network architectures like AlexNet and ResNet, and evaluation metrics. Module 3 is about image segmentation, including semantic segmentation and network architectures like U-Net and DeepLab. Module 4 discusses object detection, both traditional and deep learning-based approaches. Module 5 focuses on deploying applications using PyTorch's C++ API and cloud deployment.

    Original Title

    dlwp-syllabus

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document outlines the modules of an AI course in computer vision using PyTorch. Module 1 introduces neural networks and their history as well as applications of deep learning such as speech recognition and medical diagnostics. Module 2 covers image classification, including network architectures like AlexNet and ResNet, and evaluation metrics. Module 3 is about image segmentation, including semantic segmentation and network architectures like U-Net and DeepLab. Module 4 discusses object detection, both traditional and deep learning-based approaches. Module 5 focuses on deploying applications using PyTorch's C++ API and cloud deployment.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    59 views5 pages

    Deep Learning With Pytorch: Ai Courses by Opencv

    Uploaded by

    Lohith B M Bandi
    This document outlines the modules of an AI course in computer vision using PyTorch. Module 1 introduces neural networks and their history as well as applications of deep learning such as speech recognition and medical diagnostics. Module 2 covers image classification, including network architectures like AlexNet and ResNet, and evaluation metrics. Module 3 is about image segmentation, including semantic segmentation and network architectures like U-Net and DeepLab. Module 4 discusses object detection, both traditional and deep learning-based approaches. Module 5 focuses on deploying applications using PyTorch's C++ API and cloud deployment.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 5

    AI Courses by OpenCV

    DEEP LEARNING WITH


    PYTORCH

    Module 1 : Introduction to Neural Networks

    1. History of Artificial Intelligence

    • Turing Test
    • Perceptron
    • First AI Winter
    • Backpropagation Algorithm
    • Second AI Winter
    • Post AI Winter
    • AI Spring

    2. Applications of Deep Learning

    • Speech Recognition
    • Natural Language Processing
    • Automation
    • Medical Diagnostics
    • Facial Analysis
    • Content Creation

    Module 2 : Image Classification

    1. Image Classification Overview

    • Introduction to Image Classification


    • ImageNet

    https://courses.opencv.org
    • LeNet and LeNet-5
    • Types of layers
    1. Convolutional Layer
    2. Activation Layer
    3. Pooling Layer
    4. Fully Connected Layer
    2. Evaluation Metrics

    • Confusion Matrix
    • Accuracy
    • Precision
    • Recall
    • Specificity
    • F1 Score
    • ROC Curve, AUC ROC

    3. Image Classification Architecture

    • AlexNet
    • VGG-16
    • GoogleNet
    • Resnet
    • Comparison of methods
    • Creating your own architecture

    4. Mathematics of Neural Networks

    • Mathematical definition of Classifier, Training and Iteration


    • Forward Pass
    • Loss Function
    • Backpropagation
    • Deep Learning as Optimization Problem
    • Gradient Descent and Weights Update
    • Stochastic GD and Mini-Batch GD
    • ADAM

    https://courses.opencv.org
    • Training Scheme

    5. Good Practice + Bias, Batchnorm, Dropout

    • Data Shuffling
    • Dataset Splits
    • Fitting the training set
    • Overfitting
    • Bias and Variance
    • Regularization
    • Data Augmentations

    Module 3 : Image Segmentation

    1. Semantic Segmentation

    • Problem Formulation
    • Histogram Based Methods
    • Conditional Random Fields
    • Datasets – PASCAL VOC 2012, CAMVID, CITYSCAPES, FASSEG
    • Evaluation Metrics

    2. Architecture of Semantic Segmentation

    • Fully Convolutional Network


    • U-Net
    • SegNet
    • DeepLab v1, v2
    • DeepLab v3
    • DeepLab v3+

    3. Loss Function and Blocks

    • Commonly used Loss Functions


    • Mathematical Formulation
    • Implementation

    https://courses.opencv.org
    Module 4 : Object Detection

    1. Introduction of Object Detection

    • Problem Formulation
    • Challenges
    • Accuracy Improvement
    • Datasets – VOC PASCAL, MS COCO, ImageNet

    2. Traditional Approach to Object Detection

    • Background Subtraction
    • Sliding Window
    • Selective Approach
    • Traditional ML
    • Hand-crafted Features

    3. Evaluation Metrics

    • Problem Formulation
    • Popular Competitions
    • IoU
    • Confidence Score
    • TP, FP, TN, FN
    • Recall & Precision
    • Non-maximum Suppression

    4. Single stage Object Detection

    • Main pipeline
    • YOLO
    • SSD
    • RetinaNet

    5. Two Stage Object Detection

    • Main Pipeline

    https://courses.opencv.org
    • R-CNN
    • Fast-RCNN
    • Faster-RCNN
    • Comparison between Fast-RCNN and Faster-RCNN

    Module 5 : Deploying Applications


    1. PyTorch C++ API and LibTorch

    • Learn LibTorch for using in deployment


    • How to convert models to be used in C++ API
    • How to train models in C++ API

    2. Cloud Deployment

    • Learn about Azure Machine Learning


    • Deploy Deep Learning models on the cloud

    https://courses.opencv.org

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy