Description: Mastering Computer Vision with PyTorch and Machine Learning by Caide Xiao This book is a valuable resource for professionals, researchers, and students who want to expand their knowledge of advanced computer vision techniques using PyTorch. FORMAT Hardcover CONDITION Brand New Publisher Description This book, together with the accompanying Python codes, provides a thorough and extensive guide for mastering advanced computer vision techniques for image processing by using the open-source machine learning framework PyTorch. Known for its user-friendly interface and Python programming style, PyTorch is accessible and one of the most popular tools among researchers and practitioners in the field of artificial intelligence.Key Features:Hands-on approach using the accompanying practical code examplesCodes for all projects listed in the book are in a same style with four parts: data input, data display, data process and data outputEmphasis on practical application development for computer visionIncludes latest computer vision technologiesOffers practical guidance on advanced computer vision techniquesUses freely available and open-source resources like Kaggle and Google Colab Author Biography Dr. Caide Xiao was born in China in and obtained his bachelors degree in physics from Centre China Normal University in 1979 and was a lecturer of medical physics in Yunyang University. Following his PhD in optical biosensors from Tsinghua University he has subsequently been a research fellow and visiting scholar at the Biotechnology Research Institute in Montreal, Oakland University in Rochester, West Virginia University and the University of Calgary. Table of Contents PrefaceAcknowledgementsAuthor biography1 Mathematical tools for computer vision1.1 Probability, entropy and Kullback–Leibler divergence1.1.1 Probability and Shannon entropy1.1.2 Kullback–Leibler divergence and cross entropy1.1.3 Conditional probability and joint entropies1.1.4 Jensens inequality1.1.5 Maximum likelihood estimation and over fitting1.1.6 Application of expectation-maximization algorithm to find a PDF1.2 Using a gradient descent algorithm for linear regression1.3 Automatic gradient calculations and learning rate schedulers1.4 Dataset, dataloader, GPU and models saving1.5 Activation functions for nonlinear regressionsReferences2 Image classifications by convolutional neural networks2.1 Classification of hand written digits in the MNIST database2.2 Mathematical operations of a convolution2.3 Using ResNet9 for CIFAR-10 classification2.4 Transfer learning with ResNet for STL-10 datasetReferences3 Image generation by GANs3.1 The GAN theory3.1.1 Implement a GAN for quadratic curve generation3.1.2 Using a GAN with two fully connected layers to generate MINST Images3.2 Applications of deep convolutional GANs3.2.1 Mathematical operations of ConvTranspose2D3.2.2 Applications of a DCGAN for MNIST and fashion MNIST3.2.3 Using a DCGAN to generate fake anime-faces and fake CelebA images3.3 Conditional deep convolutional GANs3.3.1 Applications of a cDCGAN to MNIST and fashion MNIST datasets3.3.2 Applications of a cDCGAN to generate fake Rock Paper Scissors imagesReferences4 Image generation by WGANs with gradient penalty4.1 Using a WGAN or a WGAN-GP for generation of fake quadratic curves4.2 Using a WGAN-GP for Fashion MNIST4.3 WGAN-GP for CelebA dataset and Anime Face dataset4.4 Implement of a cWGAN-GP for Rock Paper Scissors datasetReferences5 Image generation by VAEs5.1 VAE and beta-VAE5.2 Application of beta-VAE for fake quadratic curves5.3 Application of beta-VAE for the MNIST dataset5.4 Using VAE-GAN for fake images of MNIST and Fashion MNISTReferences6 Image generation by infoGANs6.1 Using infoGAN to generate quadratic curves6.2 Implementation of infoGAN for the MNIST dataset6.3 infoGAN for fake Anime-face dataset images6.4 Implementation of infoGAN to the rock paper scissors datasetReference7 Object detection by YOLOv1/YOLOv3 models7.1 Bounding boxes of Pascal VOC database for YOLOv17.2 Encode VOC images with bounding boxes for YOLOv17.2.1 VOC image augmentations with bounding boxes7.2.2 Encoding bounding boxes to grid cells for YOLOv1 model training7.2.3 Chess pieces dataset from Roboflow7.3 ResNet18 model, IOU and a loss function7.3.1 Using ResNet18 to replace YOLOv1 model7.3.2 Intersection over union (IOU)7.3.3 Loss function7.4 Utility functions for model training7.5 Applications of YOLOv3 for real-time object detectionReferences8 YOLOv7 and YOLOv8 models8.1 YOLOv7 for object detection for a custom dataset: MNIST4yolo8.2 YOLOv7 for instance segmentation8.3 Using YOLOv7 for human pose estimation (key point detection)8.4 Applications of YOLOv8 models8.4.1 Image object detection, segmentation, classification and pose estimation8.4.2 Object counting on an image or a video frame8.4.3 Car tracking and counting for a video file8.4.4 Fine tuning YOLOv8 for objection detection and annotation of a custom dataset8.5 Using YOLO-NAS models for object detectionReferences9 U-Nets for image segmentation and diffusion models for image generation9.1 Retinal vessel segmentation by a U-Net for DRIVE dataset9.2 Using an attention U-Net diffusion model for quadratic curve generation9.2.1 The forward process in a DDPM9.2.2 The backward process in the DDPM9.3 Using a pre-trained U-Net from Hugging Face to generate images9.4 Generate photorealistic images from text prompts by stable diffusionReferences10 Applications of vision transformers10.1 The architecture of a basic ViT model10.2 Hugging Face ViT for CIFAR10 image classification10.3 Zero shot image classification by OpenAI CLIP10.4 Zero shot object detection by Hugging Faces OWL-ViTReferences11 Knowledge distillation, DINO, SAM, MiDaS and NeRF11.1 Knowledge distillation for neural network compression11.2 DINO: emerging properties in self-supervised vision transformers11.3 DINOv2 for image retrieval, classification and feature visualization11.4 Segment anything model: SAM and FastSAM11.5 MiDaS for image depth estimation11.6 Neural radiance fields for synthesis of 3D scenes11.6.1 Camera intrinsic and extrinsic matrices11.6.2 Using MLP with Gaussian Fourier feature mapping to reconstruct images11.6.3 The physics principle of render volume density in NeRFReferencesAppendix Details ISBN0750362421 Author Caide Xiao Publisher Institute of Physics Publishing Series IOP ebooks ISBN-13 9780750362429 Format Hardcover Imprint Institute of Physics Publishing Place of Publication Bristol Country of Publication United Kingdom Alternative 9780750362450 Audience Professional & Vocational Year 2024 Illustrations With figures in colour and black and white Publication Date 2024-04-29 UK Release Date 2024-04-29 Pages 364 ISBN-10 0750362421 We've got this At The Nile, if you're looking for it, we've got it. With fast shipping, low prices, friendly service and well over a million items - you're bound to find what you want, at a price you'll love! TheNile_Item_ID:160091019;
Price: 164.71 AUD
Location: Melbourne
End Time: 2024-11-06T02:35:48.000Z
Shipping Cost: 15.67 AUD
Product Images
Item Specifics
Restocking fee: No
Return shipping will be paid by: Buyer
Returns Accepted: Returns Accepted
Item must be returned within: 30 Days
Format: Hardcover
ISBN-13: 9780750362429
Author: Caide Xiao
Type: Does not apply
Book Title: Mastering Computer Vision with PyTorch and Machine Learning
Language: Does not apply
