Modern Computer Vision™ PyTorch, Tensorflow2 Keras & OpenCV4
Using Python Learn OpenCV4, CNNs, Detectron2, YOLOv5, GANs, Tracking, Segmentation, Face Recognition & Siamese Networks
What you’ll learn
-
All major Computer Vision theory and concepts!
-
Learn to use PyTorch, TensorFlow 2.0 and Keras for Computer Vision Deep Learning tasks
-
OpenCV4 in detail, covering all major concepts with lots of example code
-
All Course Code works in accompanying Google Colab Python Notebooks
-
Learn all major Object Detection Frameworks from YOLOv5, to R-CNNs, Detectron2, SSDs, EfficientDetect and more!
-
Deep Segmentation with U-Net, SegNet and DeepLabV3
-
Understand what CNNs ‘see’ by Visualizing Different Activations and applying GradCAM
-
Generative Adverserial Networks (GANs) & Autoencoders – Generate Digits, Anime Characters, Transform Styles and implement Super Resolution
-
Training, fine tuning and analyzing your very own Classifiers
-
Facial Recognition along with Gender, Age, Emotion and Ethnicity Detection
-
Neural Style Transfer and Google Deep Dream
-
Transfer Learning, Fine Tuning and Advanced CNN Techniques
-
Important Modern CNNs designs like ResNets, InceptionV3, DenseNet, MobileNet, EffiicentNet and much more!
-
Tracking with DeepSORT
-
Siamese Networks, Facial Recognition and Analysis (Age, Gender, Emotion and Ethnicity)
-
Image Captioning, Depth Estimination and Vision Transformers
-
Point Cloud (3D data) Classification and Segmentation
-
Making a Computer Vision API and Web App using Flask
Requirements
-
No programming experience (some Python would be beneficial)
-
Basic highschool mathematics
-
A broadband internet connection
Description
Welcome to Modern Computer Vision™ Tensorflow, Keras & PyTorch!
AI and Deep Learning are transforming industries and one of the most intriguing parts of this AI revolution is in Computer Vision!
But what exactly is Computer Vision and why is it so exciting? Well, what if Computers could understand what they’re seeing through cameras or in images? The applications for such technology are endless from medical imaging, military, self-driving cars, security monitoring, analysis, safety, farming, industry, and manufacturing! The list is endless.
Job demand for Computer Vision workers are skyrocketing and it’s common that experts in the field are making $200,000+ USD salaries. However, getting started in this field isn’t easy. There’s an overload of information, many of which is outdated, and a plethora of tutorials that neglect to teach the foundations. Beginners thus have no idea where to start.
======================================================
Computer vision applications involving Deep Learning are booming!
Having Machines that can ‘see‘ will change our world and revolutionize almost every industry out there. Machines or robots that can see will be able to:
- Perform surgery and accurately analyze and diagnose you from medical scans.
- Enable self-driving cars
- Radically change robots allowing us to build robots that can cook, clean, and assist us with almost any task
- Understand what’s being seen in CCTV surveillance videos thus performing security, traffic management, and a host of other services
- Create Art with amazing Neural Style Transfers and other innovative types of image generation
- Simulate many tasks such as Aging faces, modifying live video feeds, and realistically replacing actors in films
======================================================
This course aims to solve all of that!
- Taught using Google Colab Notebooks (no messy installs, all code works straight away)
- 27+ Hours of up-to-date and relevant Computer Vision theory with example code
- Taught using both PyTorch and Tensorflow Keras!
In this course, you will learn the essential very foundations of Computer Vision, Classical Computer Vision (using OpenCV) I then move on to Deep Learning where we build our foundational knowledge of CNNs and learn all about the following topics:
======================================================
Detailed OpenCV Guide covering:
- Image Operations and Manipulations
- Contours and Segmentation
- Simple Object Detection and Tracking
- Facial Landmarks, Recognition and Face Swaps
- OpenCV implementations of Neural Style Transfer, YOLOv3, SSDs and a black and white image colorizer
- Working with Video and Video Streams
Our Comprehensive Deep Learning Syllabus includes:
- Classification with CNNs
- Detailed overview of CNN Analysis, Visualizing performance, Advanced CNNs techniques
- Transfer Learning and Fine Tuning
- Generative Adversarial Networks – CycleGAN, ArcaneGAN, SuperResolution, StyleGAN
- Autoencoders
- Neural Style Transfer and Google DeepDream
- Modern CNN Architectures including Vision Transformers (ResNets, DenseNets, MobileNET, VGG19, InceptionV3, EfficientNET and ViTs)
- Siamese Networks for image similarity
- Facial Recognition (Age, Gender, Emotion, Ethnicity)
- PyTorch Lightning
- Object Detection with YOLOv5 and v4, EfficientDetect, SSDs, Faster R-CNNs,
- Deep Segmentation – MaskCNN, U-NET, SegNET, and DeepLabV3
- Tracking with DeepSORT
- Deep Fake Generation
- Video Classification
- Optical Character Recognition (OCR)
- Image Captioning
- 3D Computer Vision using Point Cloud Data
- Medical Imaging – X-Ray analysis and CT-Scans
- Depth Estimation
- Making a Computer Vision API with Flask
- And so much more
This is a comprehensive course, is broken up into two (2) main sections. This first is a detailed OpenCV (Classical Computer Vision tutorial) and the second is a detailed Deep Learning
======================================================
This course is filled with fun and cool projects including these Classical Computer Vision Projects:
- Sorting contours by size, location, using them for shape matching
- Finding Waldo
- Perspective Transforms (CamScanner)
- Image Similarity
- K-Means clustering for image colors
- Motion tracking with MeanShift and CAMShift
- Optical Flow
- Facial Landmark Detection with Dlib
- Face Swaps
- QR Code and Barcode Reaching
- Background removal
- Text Detection
- OCR with PyTesseract and EasyOCR
- Colourize Black and White Photos
- Computational Photography with inpainting and Noise Removal
- Create a Sketch of yourself using Edge Detection
- RTSP and IP Streams
- Capturing Screenshots as video
- Import Youtube videos directly
======================================================
Deep Learning Computer Vision Projects:
- PyTorch & Keras CNN Tutorial MNIST
- PyTorch & Keras Misclassifications and Model Performance Analysis
- PyTorch & Keras Fashion-MNIST with and without Regularisation
- CNN Visualisation – Filter and Filter Activation Visualisation
- CNN Visualisation Filter and Class Maximisation
- CNN Visualisation GradCAM GradCAMplusplus and FasterScoreCAM
- Replicating LeNet and AlexNet in Tensorflow2.0 using Keras
- PyTorch & Keras Pretrained Models – 1 – VGG16, ResNet, Inceptionv3, MobileNetv2, SqueezeNet, WideResNet, DenseNet201, MobileMNASNet, EfficientNet and MNASNet
- Rank-1 and Rank-5 Accuracy
- PyTorch and Keras Cats vs Dogs PyTorch – Train with your own data
- PyTorch Lightning Tutorial – Batch and LR Selection, Tensorboards, Callbacks, mGPU, TPU and more
- PyTorch Lightning – Transfer Learning
- PyTorch and Keras Transfer Learning and Fine Tuning
- PyTorch & Keras Using CNN’s as a Feature Extractor
- PyTorch & Keras – Google Deep Dream
- PyTorch Keras – Neural Style Transfer + TF-HUB Models
- PyTorch & Keras Autoencoders using the Fashion-MNIST Dataset
- PyTorch & Keras – Generative Adversarial Networks – DCGAN – MNIST
- Keras – Super Resolution SRGAN
- Project – Generate_Anime_with_StyleGAN
- CycleGAN – Turn Horses into Zebras
- ArcaneGAN inference
- PyTorch & Keras Siamese Networks
- Facial Recognition with VGGFace in Keras
- PyTorch Facial Similarity with FaceNet
- DeepFace – Age, Gender, Expression, Headpose and Recognition
- Object Detection – Gun, Pistol Detector – Scaled-YOLOv4
- Object Detection – Mask Detection – TensorFlow Object Detection – MobileNetV2 SSD
- Object Detection – Sign Language Detection – TFODAPI – EfficientDetD0-D7
- Object Detection – Pot Hole Detection with TinyYOLOv4
- Object Detection – Mushroom Type Object Detection – Detectron 2
- Object Detection – Website Screenshot Region Detection – YOLOv4-Darknet
- Object Detection – Drone Maritime Detector – Tensorflow Object Detection Faster R-CNN
- Object Detection – Chess Pieces Detection – YOLOv3 PyTorch
- Object Detection – Hardhat Detection for Construction sites – EfficientDet-v2
- Object DetectionBlood Cell Object Detection – YOLOv5
- Object DetectionPlant Doctor Object Detection – YOLOv5
- Image Segmentation – Keras, U-Net and SegNet
- DeepLabV3 – PyTorch_Vision_Deeplabv3
- Mask R-CNN Demo
- Detectron2 – Mask R-CNN
- Train a Mask R-CNN – Shapes
- Yolov5 DeepSort Pytorch tutorial
- DeepFakes – first-order-model-demo
- Vision Transformer Tutorial PyTorch
- Vision Transformer Classifier in Keras
- Image Classification using BigTransfer (BiT)
- Depth Estimation with Keras
- Image Similarity Search using Metric Learning with Keras
- Image Captioning with Keras
- Video Classification with a CNN-RNN Architecture with Keras
- Video Classification with Transformers with Keras
- Point Cloud Classification – PointNet
- Point Cloud Segmentation with PointNet
- 3D Image Classification CT-Scan
- X-ray Pneumonia Classification using TPUs
- Low Light Image Enhancement using MIRNet
- Captcha OCR Cracker
- Flask Rest API – Server and Flask Web App
- Detectron2 – BodyPose
Who this course is for:
- College/University Students of all levels Undergrads to PhDs (very helpful for those doing projects)
- Software Developers and Engineers looking to transition into Computer Vision
- Start up founders lookng to learn how to implement thier big idea
- Hobbyist and even high schoolers looking to get started in Computer Vision
Created by Rajeev D. Ratan
Last updated 6/2022
English
English [Auto]
Size: 12.74 GB
Google Drive Links
Download Part 1 | Download Part 2 | Download Part 3
Torrent Links
https://www.udemy.com/course/modern-computer-vision/.
ignore previous msg. download works. thank you.
Thanks u so much, <3
Please seed it.
Please seed it, please.