This Brand New and Modern Deep Learning & Computer Vision Course will teach you everything you will need to know to learn the fundamentals of computer vision.
Deep Learning & Computer Vision is currently one of the most increasing fields of Artificial Intelligence and Companies like Google, Apple,
Facebook, Amazon are highly investing in this field. Deep Learning & Computer Vision jobs are increasing day by day & provide some of the highest paying jobs all over the world.
If We Want Machines to Think, We Need to Teach Them to See.-Fei Fei Li, Director of Stanford AI Lab and Stanford Vision Lab
Computer Vision allows us to see the world & process digital images & videos to extract useful information to do a certain task from classification, object detection, and much more. Python is one of the most popular used programming language in Deep Learning and Computer Vision.
All the tools, techniques & technologies used in this course –
•Learning Computer Vision & Deep Learning Fundamentals
•Setting up Anaconda, Installing Libraries & Jupyter Notebook
•Learning fundamentals of OpenCV & Numpy – Reading images, Colorspaces, Drawing & Callbacks
•Advanced OpenCV – Image Preprocessing, Geometrical transformations, Perspective transformations & affine transformations, image blending & pyramids, image gradients & thresholding, Canny Edge Detector and contours
•Working with videos in OpenCV – Using webcam, Haar Cascades & Object Detection, Lane Detection
•Deep Learning & How Neural Network Works? – Artificial neural networks, Convolution Neural Networks & Transfer Learning
Image Classification – Plant leaf Classification
•Working on very recent Kaggle Competitions
•Using Google Colab & Kaggle Kernels
•Using the latest Tensorflow 2.0 & Keras
•Using Keras Data Generators & Data Argumentation
•Using Transfer Learning & Ensemble learning
•Using State of The Art Deep Learning Models
•Using GPU & TPU for Model Training
•Hyperparameter Tuning
•Using Weights & Biases for recording Deep Learning experimentations
•Saving & Loading Models
•Creating a Weights & Biases Report & Showcasing the Project!
Object Detection – Wheat heads Detection
•Working on Kaggle Competitions, again!
•Using Facebook’s Detectron2 for Object Detection
•Creating COCO Dataset from scratch
•Training Faster RCNN Model and Custom Weights & Biases callback
•Using Retinanet
•Saving & Loading Detectron2 models
Generative Adversarial Networks – Creating Fake Leaf Images
•Learning How Generative Adversarial Networks works
•Using FastAI
•Creating & Training Generative Adversarial Networks
•Making Fake Images using GAN
Making ML Web Application
•Getting started with Streamlit
•Creating an ML Web Application from scratch using Streamlit
•making a React Web Application
Deploying ML Applications
•Learning how to use Cloud Services to Deploy Models & Applications
•Using Heroku
•Learning how to Open Source Projects on GitHub
•How to showcase your projects to impress boss & employees & Get Hired!
A lot of bonus lectures!
This is what included in the package
•All lecture codes are available for downloadable for free
•110+ HD video lectures ( over 50 more to come very soon! )
•Free support in course Q/A
•All videos with English captions available
This course is for you if..
•… you want to learn the Latest Tools & Techniques used in Deep Learning & Computer Vision
•… you want to get more experience to Win Kaggle Competitions
•… you want to get started with Computer Vision to become a Computer Vision Engineer
•.. you are interested in learning Image Classification, Object Detection, Generative Adversarial Networks, Making & Deploying Machine Learning Applications