DETECTRON2 Custom Object Detection, Custom Instance Segmentation: Part 1 (Develop Custom Dataset)

แชร์
ฝัง
  • เผยแพร่เมื่อ 27 พ.ย. 2024

ความคิดเห็น • 18

  • @TheCodingBug
    @TheCodingBug  3 ปีที่แล้ว

    ► My Other Tutorials:
    Detectron2 on Colab
    th-cam.com/video/bjay7fT934Y/w-d-xo.html
    Instance Segmentation as Rendering
    th-cam.com/video/gnXlE9BO0lo/w-d-xo.html
    Detectron2 Complete Tutorial
    th-cam.com/video/Pb3opEFP94U/w-d-xo.html
    Colorize Black and White Images and Videos using Python OpenCV
    th-cam.com/video/EZWHAd0IH1M/w-d-xo.html
    Build and Install OpenCV 4.5.1 With CUDA GPU Support on Windows 10
    th-cam.com/video/YsmhKar8oOc/w-d-xo.html
    Face Detection Using OpenCV Python with CUDA GPU Acceleration
    th-cam.com/video/GXcy7Di1oys/w-d-xo.html
    YOLOv4 On Android Using TFLite
    th-cam.com/video/YzAjAS6Os8c/w-d-xo.html
    Install TensorFlow GPU Under 90 Seconds
    th-cam.com/video/toJe8ZbFhEc/w-d-xo.html
    Install PyTorch GPU Under 90 Seconds
    th-cam.com/video/raBkhUoeOHs/w-d-xo.html
    Custom YOLOv4 Object Detection with TensorFlow and TFLite
    th-cam.com/video/vzTCJM18uoM/w-d-xo.html
    Darknet YOLOv4 Custom Object Detection: Part 2 (Training YOLOv4 Darknet)
    th-cam.com/video/-NEB5P-SLi0/w-d-xo.html
    Darknet YOLOv4 Custom Object Detection: Part 1 (Preparing Custom Dataset)
    th-cam.com/video/sKDysNtnhJ4/w-d-xo.html
    YOLOv4 Object Detection with TensorFlow, TFLite and TensorRT
    th-cam.com/video/tCmC7nyfJp8/w-d-xo.html
    Darknet YOLOv4 Object Detection for Windows 10 on Images, Videos, and Webcams
    th-cam.com/video/FE2GBeKuqpc/w-d-xo.html
    Real Time Object Detection on Webcam and Videos Using OpenCV With YOLOv3 and YOLOv4 | Windows Linux
    th-cam.com/video/FjyF03uawsA/w-d-xo.html
    Build and Install OpenCV 4.4.0 with CUDA (GPU) Support on Windows 10
    th-cam.com/video/tjXkW0-4gME/w-d-xo.html
    Install TensorFlow GPU and PyTorch with CUDA on Windows 10 Anaconda | CUDA 10.1 cuDNN 7.6
    th-cam.com/video/PlW9zAg4cx8/w-d-xo.html
    Real-time Multiple Object Tracking with YOLOv4 TensorFlow and Deep Sort | Linux, Windows
    th-cam.com/video/GagII5PAeKg/w-d-xo.html

    • @coder5199
      @coder5199 2 ปีที่แล้ว

      Hi thanks for this video. There are TONS of YT vids on Detectron2 on object detection and instance segmentation but NONE on semantic segmentation for custom datasets. Can you be the one that fill the gap?

  • @muddassarjilani4637
    @muddassarjilani4637 3 ปีที่แล้ว

    excellent video series

  • @bahubalipatil9432
    @bahubalipatil9432 ปีที่แล้ว +1

    how can we get approx size of the object cm from mask? or is there any way to do it? can it be done while labelling the images if yes then how?

    • @TheCodingBug
      @TheCodingBug  ปีที่แล้ว

      It'd be easier to calculate if we have any reference object in the scene (let's say a coin), whose size we already know. And using that as a reference, we can calculate sizes of other objects.
      But all the objects should be on the same plane as we are not factoring in the depth information (objects away from the camera appear smaller than objects closer to camera).

  • @saltanatkhalyk3397
    @saltanatkhalyk3397 3 ปีที่แล้ว

    thank you very much.

  • @damubadminton
    @damubadminton ปีที่แล้ว

    Humble question from here: if i am not using labelme how should i do?

  • @muddassarjilani4637
    @muddassarjilani4637 3 ปีที่แล้ว

    excellent video series, how to deploy instance segmentation model

  • @rzoo1531
    @rzoo1531 2 ปีที่แล้ว +1

    is it possible to add more classes of objects to be detected using detectron2? how to apply it?

    • @TheCodingBug
      @TheCodingBug  2 ปีที่แล้ว

      Yes. I have done one class in this tutorial. You can annotate and train on multiple classes too.

  • @franciscoalberto4774
    @franciscoalberto4774 2 ปีที่แล้ว

    Hello, once you have the detectron2 model, can you paint only the objects that are whole?

  • @abheeshtamn6027
    @abheeshtamn6027 5 หลายเดือนก่อน

    why does test dataset need json file? cant i use some random images without annotations? if test data also needs annotations, then what is the point of doing all this?

  • @nguyentranminhtan.1999
    @nguyentranminhtan.1999 2 ปีที่แล้ว

    amazing god job (y)

  • @arshadshah114
    @arshadshah114 2 ปีที่แล้ว +1

    Can we read the text from the number plate ?
    and store it in a file.

    • @TheCodingBug
      @TheCodingBug  2 ปีที่แล้ว

      Yes. Use tesseract to get text from bounding box and then you can store it in the file

    • @arshadshah114
      @arshadshah114 2 ปีที่แล้ว

      Thank you very much for the reply can you make a video on it ? or if you have any video so please give the link of the video it will be a great help I am a beginner so that's why I need it.

  • @boppadapusaiteja8074
    @boppadapusaiteja8074 ปีที่แล้ว

    so many exceptions are raising with the simple_image_downloading
    example: