How to Run YOLOv4 on Images and Video

Darknet and YOLOV4 Installation Documentation

Hey guys and welcome back, so in the last lecture, we spent some time setting up the prerequisites for YOLOv4, like Visual Studio, Python, CUDA, CuDnn and OpenCV. If you have not completed the previous tutorial, then I highly suggest that you do because this lecture builds upon the steps we took in the previous tutorial. So if you have completed that tutorial, then this lecture we are going to be installing Darknet Framework and thus YOLOv4. By the end of this tutorial you will be able to implement YOLOv4 on an Image and on Video.

I’m sure you must be excited, Okay so let’s get into the tutorial. Watch the Full Video Tutorial Here

Step 1

  • Cloned repository from official Github of AlexyAB [link]

Step 2

  • Copy OpenCV_ffmpeg and _world dll’s for 4.1.0 version(can be used for OpenCV video processing) near to darknet.exe

Step 3

  • Copied cuDNN.dll(for accelerating the neural network processes) near to darknet.exe

Step 4

  • Change the CUDA version if you’re not using CUDA 10.0.
  • I’m using 10.2 so made change in two files
darknet.vcxproj [Line:55]
yolo_cpp_dll.vcxproj [Line:309]
  • Save it.

Step 5

Compile yolo_cpp_dll.vcxproj with updated CUDA version

  • Open yolo_cpp_dll.vcxproj with VS.
  • Open VS and Select Release and x64.
  • Right click on yolo_cpp_dll and select build.
  • Should be -1 succeeded without fail-
  • If failed then make sure you have followed upper steps properly.

Step 6 - Compile darknet.sln

  • Open darknet.sln with VS
  • Set Release and x64
  • Right click on darknet and select properties
  • Make Four changes
C/C++ -> General -> Additional Include Directories: C:\OpenCV\build\install\include .
  • Click Ok and Apply If you followed my instructions then path should be same -
C/C++ -> Preprocessor -> Preprocessor Definitions
  • Remove CUDNN_HALF as Yolo v4/3 uses Tensor cores We don’t need to use it for 1080Ti [Optional] If you have GPU with Tensor Cores (nVidia Titan V / Tesla V100 / DGX-2 and later) then add CUDNN_HALF for speedup in detection 3x and training 2x.
CUDA C/C++ -> Device -> Code Generation
  • Remove compute_75, sm_75 if you’re not using CUDA 10.0 - Linker -> General Add lib from OpenCV build
C:\OpenCV\build\install\x64\vc16\lib
  • Right click on darknet and select build
  • After the successfully build try and import darknet in Python from x64 directory Should be imported otherwise right click on darknet and select clean the build and try to follow upper steps properly.

Step 7 Run Detection on Images

darknet.exe detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights It’ll ask for the input path of the image

Step 8 Run Detection on Videos

darknet.exe detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights PATH_TO_THE_VIDEO

If you got this working then GREAT!! Now what I want you to do, is to try this out with a different images and video and post a link to your video/images in the comments, I would love to see what images and videos that you guys have tried and testing. If not, try and go back and follow the steps precisely and do a clean build where applicable.

If you are interested in Enrolling in my upcoming course on YOLOv4 then sign up over here when it gets released - Click Here

YOLOV4 Course - Coming Soon!

Road Map

Okay great! So now that we have YOLOv4 working, lets take a look out road map going forth:

  • Tut 1 we spend setting up the pre-requisites
  • Tut 2, we will install Darknet & implement YOLOv4 on an image
  • Tut 3 we take YOLOv4 into real time object detection on video, for processing and saving a video and detection on a webcam.
  • Tut 4, we create a social Distancing App using YOLOv4.

Okay so let’s get into the tutorial - Click this link to get started

Comments

Post a Comment

Popular posts from this blog

Movidius NCS (with Raspberry Pi) vs. Google Edge TPU (Coral) vs. Nvidia Jetson Nano – A Quick Comparison

Image
Lately, there has been a lot of talk regarding the possibility of machines learning to do what human beings do in factories, homes, and offices. With the advancement in artificial intelligence , there has been widespread fear and excitement about what AI, machine learning, and deep learning is capable of doing. What is really cool is that Deep Learning and AI models are making their way from the cloud and bulky desktops to smaller and lower powered hardware. In this article, we will help you understand the strengths and weaknesses about three of the most dominant deep learning AI hardware platforms out there. The Intel Movidius Neural Compute Stick (NCS) with Raspberry Pi Developed by Intel Corporation, the Movidius Neural Compute Stick can efficiently operate without an active internet connection. Its computing capabilities come from the Myriad 2 Vision Processing Unit (VPU) . It offers profiling, tuning, and compiling a Deep Neural Network (DNN) on a development computer with the ri...
Read more

DeepSORT - Deep Learning applied to Object Tracking

Image
Introduction So in this article, Im going to give to you a clear and simple explanation on how Deep SORT works and why its so amazing compared to other models like Tracktor++, Track-RCNN and JDE. But to understand how DeepSORT works, we first have to go back, waaay back and understand the fundamentals of object tracking and the key innovations that had to happen along the way, for DeepSORT to emerge. Before we get started, if you are interested in developing object tracking apps, then checkout my course in the link down below, where I show you how you can fuse the popular YOLOv4 with DeepSORT for robust and real-time applications. Okay so back to Object Tracking. Now lets imagine that you that you are working for Space X, and Mr. Musk has tasked you with ensuring that on launch, the ground camera is always pointing at the Falcon 9 as it thrust into the atmosphere. As much as you are excited to be personally chosen by Elon to work on this task you ask yourself, “How will I go about th...
Read more

OpenCV AI Kit - An Introduction to OAK-1 and OAK-D

Image
Introduction Okay so I just got my OpenCV AI Kit and I am really excited to play with. But even though Iv seen a bunch of features on Kickstarter, I don’t quite understand the true capabilities of this device and why I should even care . Well in this video we going take a deep dive into this device and find out exactly what its capable off, and at the end of the video I will share my thoughts on if this device is worth all the hype as well how it matches up to the competition. What is the OpenCV AI Kit So before we get into that, lets get into the first question of What exactly is the OpenCV AI Kit or OAK. According to the creators, it is a tiny, powerful, open source Spatial AI system. So you can think of it as if an embedded 4k camera and neural compute stick had a baby, make that two babies OAK-1 and OAK-D Difference between the OAK 1 – OAK D Now What sets these two devices apart is that the OAK-1 has automatic motion-based lossless digital zooming which means that the sensor has ...
Read more