This course was created with the
course builder. Create your online course today.
Start now
Create your course
with
Autoplay
Autocomplete
Previous Lesson
Complete and Continue
.
Introduction to Ultimate AI-CV
Introduction to Ultimate AI-CV Pro
Course Requirements
How to Join the Private FB Group
Module 1 - YOLO v3 - Robust Deep Learning Object Detection in 1 hour
1.1 - Yolo V3 Intuition (12:10)
1.2 - Execute Yolo V3 (8:50)
1.3 - 4 Steps to Setting up a Supervisely Deep Learning Cluster (9:32)
1.4 - How to Web Scrape Images for your Dataset like a PRO! (6:21)
1.5 - The Best Way to Annotate your Dataset (4:22)
1.6 - How to let the AI Annotate your Dataset for you - Human in the Loop Annotation (2:49)
1.7 - Got Little Data? No Problem! Data Augmentation to the Rescue ;) (4:28)
1.8 - How to Train a Yolo V3 Network (5:04)
1.9 - A Quick and Easy Method Deploying your Custom Object Detector after Training (6:37)
1.10 - How to Record video, change bounding box color and add confidence percentage (5:32)
1.11 - Cleaning up you Supervisely Cluster and Cluster Maintenance (1:37)
Module 2 - Mask R-CNN - Robust Deep Learning Segmentation in 1 hour
2.1 - Mask R-CNN Intuition (10:07)
2.2 - Anaconda Install and Setup for Mask RCNN (1:57)
2.3 - Installing the requirements, dependencies (10:56)
2.4 - Real-time Mask RCNN - How to execute like a boss. (5:32)
2.5 - Set up Supervisely Cluster (9:32)
2.6 - Annotating Images (8:10)
2.7 - Data Augmentation (4:38)
2.8 - How to Train a Mask RCNN model (5:50)
2.9- How to Deploy a Custom Mask RCNN after Training (3:55)
2.10 - Segmentation Area Analysis - How to Count Potholes and its Area Size (2:55)
Module 3 - Pose Estimation Master Class using OpenPose Framework
3.1 - OpenPose Intuition & How it Works (11:07)
3.2 - OpenPose Github Repository
3.3 - Setup & Execution of Pose Estimation (5:30)
3.4 - App 1 : People Counter using Open Pose (4:26)
3.5 -App 2 : Fall Detection (6:52)
3.6 - App 3 : Yoga Pose Angle Corrector (6:44)
3.7 - App 4: Plank Pose Recongition (7:41)
3. 8 - App 5 : Body Ratio Calculator (6:52)
3.9 - App 6 : OpenPose in Unity [UPDATED!!] (6:04)
Module 4 - AI Android Development
4. Introduction to AI Development on Android - TensorFlow Lite (6:01)
4.1 - Data Collection, Cleaning & Annotation (non-supervisely solution)
4.2 - Data Training [Coming Soon]
4.3 - Data Validation [Coming Soon]
4.4 - Data Testing [Coming Soon]
4.5 - Frozen graph & model generation in Tensorflow [Coming Soon]
4.5.1 - Convert to TFLite Model (TOCO API) [Coming Soon]
4.5.2 - Tensorflow Lite Basics [Coming Soon]
4.5.3 - Import Tensorflow in Gradle [Coming Soon]
4.6 - Project Setup and Run Inference on Android [Coming Soon]
4.6.1 - Object Detection - Selecting between image, video or live camera [Coming Soon]
4.6.2 - Adding logic to AI on Android [Coming Soon]
4.6.3 - App 1 [Coming Soon]
4.6.4 - App 2 [Coming Soon]
Project E.D.I.T.H. - Spiderman (Far from Home) AI Glasses [BONUS]
Phase 1 - AI Face Detection in Unity (9:36)
Phase 2 - Facial Recognition (17:09)
Phase 3 - Object Detection (19:49)
Phase 4 - AI Assistant Text to Speech (TTS) & Speech to Text (STT) (18:18)
Phase 5 - IoT using AI Assistant (11:53)
Phase 6 - Android Integration of Project E.D.I.T.H. (10:00)
Phase 7 - AR Glasses Integration of AI Capabilities [Coming Soon]
Bonus Section
B1 - Artificial Neural Networks (18:30)
B2 - Convolutional Neural Network (11:17)
B3 - Recurrent Neural Networks (12:22)
B4 - FREE Accelerated Deep Learning on Raspberry Pi Course
4.6.1 - Object Detection - Selecting between image, video or live camera [Coming Soon]
Lesson content locked
If you're already enrolled,
you'll need to login
.
Enroll in Course to Unlock