Mastering Computer Vision with PyTorch and Machine Learning

This book is a valuable resource for professionals, researchers, and students who want to expand their knowledge of advanced computer vision techniques using PyTorch. PRELIMS.pdf Outline placeholder What this book is about Prerequisites to readers Structure of the book Keywords Acknowledgements Author biography Dr Caide Xiao CH001.pdf Chapter Mathematical tools for computer vision 1.1 Probability, entropy and Kullback–Leibler divergence 1.1.1 Probability and Shannon entropy 1.1.2 Kullback–Leibler divergence and cross entropy 1.1.3 Conditional probability and joint entropies 1.1.4 Jensen's inequality 1.1.5 Maximum likelihood estimation and over fitting 1.1.6 Application of expectation-maximization algorithm to find a PDF 1.2 Using a gradient descent algorithm for linear regression 1.3 Automatic gradient calculations and learning rate schedulers 1.4 Dataset, dataloader, GPU and models saving 1.5 Activation functions for nonlinear regressions References CH002.pdf Chapter Image classifications by convolutional neural networks 2.1 Classification of hand written digits in the MNIST database 2.2 Mathematical operations of a 2D convolution 2.3 Using ResNet9 for CIFAR-10 classification 2.4 Transfer learning with ResNet for a dataset of Vegetable Images References CH003.pdf Chapter Image generation by GANs 3.1 The GAN theory 3.1.1 Implement a GAN for quadratic curve generation 3.1.2 Using a GAN with two fully connected layers to generate MINST Images 3.2 Applications of deep convolutional GANs 3.2.1 Mathematical operations of ConvTranspose2D 3.2.2 Applications of a DCGAN for MNIST and fashion MNIST 3.2.3 Using a DCGAN to generate fake anime-faces and fake CelebA images 3.3 Conditional deep convolutional GANs 3.3.1 Applications of a cDCGAN to MNIST and fashion MNIST datasets 3.3.2 Applications of a cDCGAN to generate fake Rock Paper Scissors images References CH004.pdf Chapter Image generation by WGANs with gradient penalty 4.1 Using a WGAN or a WGAN-GP for generation of fake quadratic curves 4.2 Using a WGAN-GP for Fashion MNIST 4.3 WGAN-GP for CelebA dataset and Anime Face dataset 4.4 Implementation of a cWGAN-GP for Rock Paper Scissors dataset References CH005.pdf Chapter Image generation by VAEs 5.1 VAE and beta-VAE 5.2 Application of beta-VAE for fake quadratic curves 5.3 Application of beta-VAE for the MNIST dataset 5.4 Using VAE-GAN for MNIST, Fashion MNIST & Anime-Face Dataset References CH006.pdf Chapter Image generation by infoGANs 6.1 Using infoGAN to generate quadratic curves 6.2 Implementation of infoGAN for the MNIST dataset 6.3 infoGAN for fake Anime-face dataset images 6.4 Implementation of infoGAN to the rock paper scissors dataset Reference CH007.pdf Chapter Object detection by YOLOv1/YOLOv3 models 7.1 Bounding boxes of Pascal VOC database for YOLOv1 7.2 Encode VOC images with bounding boxes for YOLOv1 7.2.1 VOC image augmentations with bounding boxes 7.2.2 Encoding bounding boxes to grid cells for YOLOv1 model training 7.2.3 Chess pieces dataset from Roboflow 7.3 ResNet18 model, IOU and a loss function 7.3.1 Using ResNet18 to replace YOLOv1 model 7.3.2 Intersection over union (IOU) and the loss function 7.4 Utility functions for model training 7.5 Applications of YOLOv3 for real-time object detection References CH008.pdf Chapter YOLOv7, YOLOv8, YOLOv9 and YOLO-World 8.1 YOLOv7 for object detection for a custom dataset: MNIST4yolo 8.2 YOLOv7 for instance segmentation 8.3 Using YOLOv7 for human pose estimation (key point detection) 8.4 Applications of YOLOv8, YOLOv9 and YOLO-World models 8.4.1 Image object detection, segmentation, classification and pose estimation 8.4.2 Object counting on an image or a video frame 8.4.3 Car tracking and counting for a video file 8.4.4 Fine tuning YOLOv8 for objection detection and annotation for a custom dataset References CH009.pdf Chapter U-Nets for image segmentation and diffusion models for image generation 9.1 Retinal vessel segmentation by a U-Net for DRIVE dataset 9.2 Using an attention U-Net diffusion model for quadratic curve generation 9.2.1 The forward process in a DDPM 9.2.2 The backward process in the DDPM 9.3 Using a pre-trained U-Net from Hugging Face to generate images 9.4 Generate photorealistic images from text prompts by stable diffusion References CH010.pdf Chapter Applications of vision transformers 10.1 The architecture of a basic ViT model 10.2 Hugging Face ViT for CIFAR10 image classification 10.3 Zero shot image classification by OpenAI CLIP 10.4 Zero shot object detection by Hugging Face's OWL-ViT 10.5 RT-DETR (a vision transformers-based real-time object detector) References CH011.pdf Chapter Knowledge distillation and its applications in DINO and SAM 11.1 Knowledge distillation for neural network compression 11.2 DINO: emerging properties in self-supervised vision transformers 11.3 DINOv2 for image retrieval, classification and feature visualization 11.4 Segment anything model: SAM and FastSAM References CH012.pdf Chapter Applications of NeRF and 3D Gaussian splatting for synthesis of 3D scenes 12.1 Using MiDaS for image depth estimation 12.2 Neural Radiance Fields (NeRF) for synthesis of 3D scenes 12.2.1 Camera intrinsic and extrinsic matrices 12.2.2 Using MLP with Gaussian Fourier feature mapping to reconstruct images 12.2.3 The physics principle of render volume density in NeRF 12.3 Introduce 3D Gaussian splatting by 2D Gaussian splatting References APP.pdf Chapter A Kullback–Leibler divergence of two multivariate normal distributions B Expectation-maximization algorithm C Gradients of MSE loss function to weights in a linear regression D Application of a VAE-GAN to generate fake Anime-faces dataset images E Applications of a cWGAN-GP system to MNIST or fashion MNIST F Four applications of pre-trained Detectron2 models G Traffic tracking and counting for objects in multiple COCO classes H U-Net Wasserstein generative adversarial networks for retina I DDPM forward process posterior distribution and LVLB J An Improved Version of Project 11.3.1 to Avoid a FAISS Issue K Tiny NeRF codes for lego 3D scene synthesis