SkillEnhance.in


Development >> Data Science

Learn TensorRT-ONNX Detection,Segmentation,Tracking Projects

Development of ONNX, TENSORRT FAST PRECISION INFERENCE in Docker, All Yolo version for fast detect and segmentation,

Ratings 4.77 / 5.00
Learn TensorRT-ONNX Detection,Segmentation,Tracking Projects

What You Will Learn!

  • 1. What is Docker and How to use Docker & their practical usage
  • 2. What is Kubernet and How to use with Docker & their practical usage
  • 3. Nvidia SuperComputer and Cuda Programming Language & their practical usage
  • 4. What are OpenCL and OpenGL and when to use & their practical usage
  • 6.(LAB) Tensorflow/TF2 and Pytorch Installation, Configuration with DOCKER
  • 7. (LAB)DockerFile, Docker Compile and Docker Compose Debug file configuration
  • 8. (LAB)Different YOLO version, comparisons, and when to use which version of YOLO according to your problem
  • 9. (LAB)Jupyter Notebook Editor as well as Visual Studio Coding Skills
  • 10. (LAB) Visual Studio Code Setup and Docker Debugger with VS
  • 11. (LAB) what is ONNX fframework and how to use apply onnx to your custom problems
  • 11. (LAB) What is TensorRT Framework and how to use apply to your custom problems
  • 12. (LAB) Custom Detection, Classification, Segmentation problems and inference on images and videos
  • 13. (LAB) Python3 Object Oriented Programming
  • 14.(LAB)Pycuda Language programming
  • 15. (LAB) Deep Learning Problem Solving Skills on Edge Devices, and Cloud Computings
  • 16. (LAB) How to generate High Performance Inference Models , in order to get high precision, FPS detection as well as less gpu memory consumption
  • 17. (LAB) Visual Studio Code with Docker
  • 18.(LAB Challenge) yolov4 onnx inference with opencv dnn
  • 19.(LAB Challenge) yolov5 onnx inference with opencv dnn
  • 20.(LAB Challenge) yolov5 onnx inference with Opencv DNN
  • 21.(LAB Challenge) yolov5 onnx inference with TensorRT and Pycuda
  • 22.(LAB) ResNet Image Classificiation with TensorRT and Pycuda
  • 23.(LAB) yolov5 onnx inference on Video Frames with TensorRT and Pycuda
  • 24. (LAB) Prepare Yourself for Python Object Oriented Programming Inference!
  • 25. (LAB) Python OOP Inheritance Based on YOLOV7 Object Detection
  • 26. Deep Theoretical Knowledge about Small Target Detection and Image Masking
  • 27. Deep Insight on Yolov5/Yolov6/Yolov7/Yolov8 Architectures and Practical Use Cases
  • 28. Deep Insight on YoloV5 P5 and P6 Models & Their Practical Usage
  • 29. Key Differences:Explicit vs. Implicit Batch Size
  • 30. (Theory) TenSorRT Optimization Profile Tutorial
  • 31. (Theory) Boost TensorRT Knowledge for Beginner Level Quizzies
  • 32. (Theory Challenge) Boost TensorRT Knowledge for  Intermediate Level Quizzies
  • 33. Theory Challenge) Boost TensorRT  Knowledge for Advance Level Quizzies
  • 34.(Theory Challenge) Boost  Cuda Runtime for Beginner/Intermediate/Advance practical & theorytical Quizzies
  • 35.(Theory Challenge) Boost your OpenCV-ONNX Knowledge by doing Mixed  practical & theorytical Quizzies
  • 36.(Deep Theoratical Knowledge) YoloV8 ONNX Model Input and Output Inference
  • 37.(Deep Theoratical Knowledge) YoloV8 Model usage and applied sectors.
  • 38.(Deep Practical Knowledge) YoloV8 ONNX Model for Detection and Segmentation

Description

For WHOM , THIS COURSE is HIGHLY ADVISABLE:


This course is mainly considered for any candidates(students, engineers,experts) that have great motivation to learn deep learning model training and deeployment. Candidates will have deep knowledge of docker, usage of TENSORFLOW ,PYTORCH, KERAS models with DOCKER. In addition, they will be able to OPTIMIZE , QUANTIZE deeplearning models with ONNX and TensorRT frameworks for deployment in variety of sectors such as on edge devices (nvidia jetson nano, tx2, agx, xavier, qualcomm rb5, rasperry pi, particle photon/photon2), AUTOMATIVE, ROBOTICS as well as cloud computing via AWS, AZURE DEVOPS, GOOGLE CLOUD, VALOHAI, SNOWFLAKES. 


Usage of TensorRT and ONNX in Edge Devices:

      Edge Devices are built-in hardware accelerator with nvidia gpu that allows to acccelare real time inference 20x Faster to achieve fast and accurate performance.

  1. nvidia jetson nano, tx2, agx, xavier : jetpack 4.5/4.6 cuda accelerative libraries

  2. Qualcomm rb5  together with Monoculare and Stereo Vision Camera(CSI/MPI , USB camera )

  3. Particle photon/photon2  IoT in order to achieve Web API, through speech recognition systems , for Smart House

  4. Robotics: Robot Operations Systems packages  for monocular and Stereo Vision Camera, in order to 3D Tranquilation ,for Human Tracking and Following, Anomaly Target and Noise Detection such as (gun noise, extremely high background  noise)

  5. Rasperry Pi 3A/3B/4B gpu OpenGL compiler based


Usage of TensorRT and ONNX in Robotics Devices:


  1. Overview of Nvidia Devices and Cuda compiler language

  2. Overview Knowledge of OpenCL and OpenGL

  3. Learning and Installation of Docker from scratch

  4. Preparation of DockerFiles, Docker Compose as well as Docker Compose Debug file

  5. Implementing and Python codes via both Jupyter notebook as well as Visual studio code

  6. Configuration and Installation of Plugin packages in Visual Studio Code

  7. Learning, Installation and Confguration of frameworks such as Tensorflow, Pytorch, Kears with docker images from scratch

  8. Preprocessing and Preparation of Deep learning datasets for training and testing

  9. OpenCV  DNN 

  10. Training, Testing and Validation of Deep Learning frameworks

  11. Conversion of prebuilt models to Onnx  and Onnx Inference on images

  12. Conversion of onnx model to TensorRT engine

  13. TensorRT engine Inference on images and videos

  14. Comparison of achieved metrices and result between TensorRT and Onnx Inference

  15. Prepare Yourself for Python Object Oriented Programming Inference!

  16. Deep Knowledge on Yolov5 P5 and P6 Large Models

  17. Deep Knowledge on Yolov5/YoloV6 Architecture and Their Use Cases

  18. Deep Theoretical and Practical Coding Skill on Research Paper of Yolov7/Yolov8 Small and Large Models

  19. Boost TensorRT Knowledge for Beginner Level Quizzies

  20. Boost TensorRT Knowledge for  Intermediate Level Quizzies

  21. Boost TensorRT  Knowledge for Advance Level Quizzies

  22. Boost Nvidia-Drivers for Beginner/Intermediate/Advance practical & theorytical Quizzies

  23. Boost  Cuda Runtime for Beginner/Intermediate/Advance practical & theorytical Quizzies

  24. Boost your OpenCV-ONNX Knowledge by doing Mixed  practical & theorytical Quizzies

  25. ONNX beginner and Advance Pythons coding Skills for auto-tuning Yolov8 ONNX model hyperparameters and Input (Fast Image or Video Pre-Post processing) for Detection and Semantic Segmentation

Who Should Attend!

  • new graduates
  • university students
  • AI experts
  • Embedded Software Engineer
  • Robotics Engineer

TAKE THIS COURSE

Tags

Subscribers

231

Lectures

110

TAKE THIS COURSE