Udemy – BOOTCAMP for TensorRT-ONNX 12+ Projects and Python 2023-6 – Downloadly

Description

BOOTCAMP course for TensorRT-ONNX 12+ projects and Python. This course is mainly aimed at any student (students, engineers, experts) who are highly motivated to learn training and deployment of deep learning models. Candidates will have extensive knowledge of Docker and how to use TENSORFLOW, PYTORCH and KERAS models using DOCKER. Moreover, they will be able to optimize deep learning models using ONNX and TensorRT frameworks for deployment in various sectors like Edge devices (Nvidia Jetson Nano, tx2, agx, xavier, qualcomm rb5, rasperry pi, Photon/Photon2 particles, quantization), AUTOMATIC, ROBOTICS and also Cloud Computing via AWS, AZURE DEVOPS, GOOGLE CLOUD, VALOHAI, SNOWFLAKES. Using TensorRT and ONNX on Edge Devices: Edge devices have a built-in hardware accelerator with NVIDIA GPU, enabling up to 20x faster real-time inference acceleration for fast and accurate performance.

  1. Nvidia Jetson Nano, TX2, AGX, Xavier: Jetpack 4.5/4.6 Cuda accelerator libraries
  2. Qualcomm RB5 with monocular camera and stereo vision (CSI/MPI, USB camera)
  3. Photon/Photon2 IoT particles for accessing the web API via speech recognition systems for smart homes
  4. Robotics: Robot operating system packages for monocular cameras and stereo vision, for 3D relaxation, for tracking and tracking people, unusual target and sound detection (gunshots, very high background noise)
  5. Raspberry Pi 3A/3B/4B GPU-based OpenGL compiler

Using TensorRT and ONNX in robotic devices:

  1. An overview of Nvidia devices and the Cuda compiler language
  2. Familiarity with OpenCL and OpenGL
  3. Training and installation of Docker from scratch
  4. Prepare DockerFiles, Docker Compose and the Docker Compose debug file
  5. Python implementations and codes via Jupyter notebooks and Visual Studio codes
  6. Configure and install plugin packages in Visual Studio Code
  7. Training, installation and configuration of frameworks like Tensorflow, Pytorch, Kears with Docker images from scratch
  8. Preprocessing and preparing deep learning datasets for training and testing
  9. OpenCV DNN
  10. Training, testing and validating deep learning frameworks
  11. Converting pre-trained models to Onnx and Onnx inference on images
  12. Convert the Onnx model to the TensorRT engine
  13. TensorRT engine inference on images and videos
  14. Comparison of obtained metrics and results between TensorRT and Onnx Inference
  15. Get ready to learn object-oriented programming in Python!
  16. In-depth knowledge of the major Yolov5 P5 and P6 models
  17. In-depth knowledge of the Yolov5/YoloV6 architecture and its use cases
  18. Theoretical and practical in-depth programming knowledge in research work on small and large models of Yolov7/Yolov8
  19. Expanding TensorRT knowledge for beginner-level exams
  20. Extending TensorRT knowledge for intermediate level testing
  21. Expand your knowledge of TensorRT for advanced level testing
  22. Improved Nvidia drivers for practical and theoretical tests for beginners/intermediate/advanced users
  23. Increased Cuda runtime for practical and theoretical tests for beginner/intermediate/advanced users
  24. Strengthen your OpenCV-ONNX knowledge by taking combined practical and theoretical tests
  25. Beginner ONNX and advanced Python coding skills to automatically tune metaparameters and inputs to the Yolov8 ONNX model (fast image or video processing before sending) for semantic recognition and segmentation.
  26. Intensive reinforcement training with practical examples and deep Python programming like Game of Frozen Lake, Drone of Lunar Ladder, etc.
  27. Individual training models for beginners, intermediate and advanced
  28. Beginner, Intermediate vs. Advanced Object Classification
  29. Beginner, Intermediate vs. Advanced Object Localization and Detection
  30. Beginner, intermediate vs. advanced image segmentation

What you will learn in the BOOTCAMP for TensorRT-ONNX 12+ projects and the Python course

  • 1. What is Docker and how is Docker used and how is it used in practice?

  • 2. What is Kubernetes and how is it used with Docker and how is it applied in practice?

  • 3. The programming languages ​​Nvidia SuperComputer and Cuda and their practical application

  • 4. What are OpenCL and OpenGL and when are they used and their practical application?

  • 6. (LAB) Tensorflow/TF2 and Pytorch installation, configuration with DOCKER

  • 7. (LAB) Configure DockerFile, Docker Compile and Docker Compose Debug

  • 8. (LAB) Different versions of YOLO, comparisons and when to use which version of YOLO depending on the problem

  • 9. (LAB) Jupyter notebook editor and Visual Studio programming skills

  • 10. (LAB) Visual Studio Code Setup and Docker Debugger with VS

  • 11. (LAB) What is the ONNX framework and how to use the OnNX application for your custom problems?

  • 11. (LAB) What is the TensorRT framework and how can you apply it to your custom problems?

  • 12. (LAB) Custom detection, classification, segmentation and inference problems on images and videos

  • 13. (LAB) Object-oriented programming Python3

  • 14. (LAB) Pycuda Language Programming

  • 15. (LAB) Deep Learning Problem Solving Capabilities in Edge Devices and Cloud Computing

  • 16. (LAB) How to generate high-performance inference models to achieve high accuracy, FPS detection, and lower GPU memory consumption.

  • 17. (LAB) Visual Studio Code with Docker

  • 18. (Lab Challenge) Inference yolov4 onnx with opencv dnn

  • 19. (Lab Challenge) yolov5 onnx inference with opencv dnn

  • 20. (Lab Challenge) yolov5 onnx inference with Opencv DNN

  • 21. (Lab Challenge) Derivation of yolov5 onnx with TensorRT and Pycuda

  • 22. (LAB) ResNet image classification with TensorRT and Pycuda

  • 23. (LAB) yolov5 onnx inference on video images with TensorRT and Pycuda

  • 24. (LAB) Get ready to derive object-oriented programming in Python!

  • 25. (LAB) Python OOP inheritance based on YOLOV7 object detection

  • 26. Deep theoretical knowledge of small target detection and image coverage

  • 27. Deep dive into Yolov5/Yolov6/Yolov7/Yolov8 architecture and practical use cases

  • 28. Deep insight into the YoloV5 P5 and P6 models and their practical use

  • 29. Key Differences: Explicit vs. Implicit Stack Size

  • 30. (Theory) TenSorRT profile optimization training

  • 31. (Theory) Consolidating TensorRT knowledge for beginner level exams

  • 32. (Theory Challenge) Deepen your TensorRT knowledge for intermediate level testing

  • 33. Theory Challenge) Expanding TensorRT knowledge for advanced testing

  • 34. (Theory Challenge) Cuda runtime extension for beginner/intermediate/practice tests and advanced theory

  • 35. (Theory Challenge) Strengthen your OpenCV-ONNX knowledge by completing combined practical and theoretical tests

  • 36. (Deep theoretical knowledge) Inference of input and output of YoloV8 ONNX model

  • 37. (Deep theoretical knowledge) YoloV8 model usage and functional parts.

  • 38. (deep practical knowledge) YoloV8 ONNX model for detection and segmentation

BOOTCAMP for TensorRT-ONNX 12+ projects and the Python course are suitable for people who

  • New graduates
  • Students of the University
  • Experts in artificial intelligence
  • Embedded Software Engineer
  • Robotics Engineer

BOOTCAMP Course Specifications for TensorRT-ONNX 12+ Projects and Python

Course topics on 3/2024

BOOTCAMP for TensorRT-ONNX 12+ projects and Python BOOTCAMP for TensorRT-ONNX 12+ projects and Python BOOTCAMP for TensorRT-ONNX 12+ projects and Python

BOOTCAMP Course Prerequisites for TensorRT-ONNX 12+ Projects and Python

  • Basic knowledge of Python programming
  • basic deep learning knowledge
  • PC laptop with CPU or GPU

Pictures of the BOOTCAMP course for TensorRT-ONNX 12+ projects and Python

BOOTCAMP for TensorRT-ONNX 12+ projects and Python

Sample video of the course

installation Guide

After extracting, you can watch it with your favorite player.

Subtitles: None

Quality: 720p

Download link

Download Part 1 – 1 GB

Download Part 2 – 1 GB

Download Part 3 – 1 GB

Download Part 4 – 1 GB

Download Part 5 – 1 GB

Download Part 6 – 433 MB

free download software

Size

5.4GB

free download software latest version