Share Description
In this course, you will :
- All major Computer Vision theory and concepts are covered!
- Learn how to use PyTorch, TensorFlow 2.0, and Keras for Deep Learning tasks in Computer Vision.
- OpenCV4 is covered in depth, with numerous examples of code for each major concept.
- All Course Code is compatible with Google Colab Python Notebooks.
- Learn about all of the major Object Detection Frameworks, including YOLOv5, R-CNNs, Detectron2, SSDs, EfficientDetect, and more!
- U-Net, SegNet, and DeepLabV3 are used for deep segmentation.
- Understand what CNNs'see' by visualising various activations and using GradCAM.
- Autoencoders and Generative Adversarial Networks (GANs) - Generate digits, animate 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
Syllabus :
- OpenCV - Image Operations
- OpenCV - Image Segmentation
- OpenCV - Haar Cascade Classifiers
- OpenCV - Image Analysis and Transformation
- OpenCV - Motion and Object Tracking
- OpenCV - Facial Landmark Detection & Face Swaps
- OpenCV Projects1
- OpenCV - Working With Video
- Deep Learning in Computer Vision Introduction
- Building CNNs in PyTorch
- Building CNNs in TensorFlow with Keras
- Assessing Model Performance
- Improving Models and Advanced CNN Design
- Visualizing What CNN's Learn
- Advanced Convolutional Neural Networks
- Building and Loading Advanced CNN Archiectures and Rank-N Accuracy
- Using Callbacks in Keras and PyTorch
- PyTorch Lightning
- Transfer Learning and Fine Tuning
- Google DeepStream and Neural Style Transfer
- Autoencoders
- Generative Adversarial Networks (GANs)
- Siamese Network
- Face Recognition (Age, Gender, Emotion and Ethnicity) with Deep Learning
- Object Detection
- Modern Object Detectors - YOLO, EfficientDet, Detectron
- Gun Detector - Scaled-YoloV
- Mask Detector TFODAPI MobileNetV2_SSD
- Sign Language Detector TFODAPI EfficentDet
- Pothole Detector - TinyYOLOv
- Mushroom Detector Detectron
- Website Region Detector YOLOv4 Darknet
- Drone Maritime Detector R-CNN
- Chess Piece YOLOv
- Bloodcell Detector YOLOv
- Hard Hat Detector EfficentDet
- Plant Doctor Detector YOLOv
- Deep Segmentation - U-Net, SegNet, DeeplabV3 and Mask R-CNN
- Body Pose Estimation
- Tracking with DeepSORT
- Deep Fakes
- Vision Transformers - ViTs
- BiT BigTransfer Classifier Keras
- Depth Estimation
- Image Similarity using Metric Learning
- Image Captioning with Keras
- Video Classification usign CNN+RNN
- Video Classification with Transformers
- Point Cloud Classification PointNet
- Point Cloud Segmentation Using PointNet
- Medical Project - X-Ray Pneumonia Prediction
- Medical Project - 3D CT Scan Classification
- Low Light Image Enhancement MIRNet
- Deploy your CV App using Flask RestFUL API & Web App
- OCR Captcha Cracker
