Custom object detection using 6 lines of code(yolov3)

Dear sir, I followed the all steps in “https://medium.com/deepquestai/train-object-detection-ai-with-6-lines-of-code-6d087063f6ff” to create the custom object detection model. But when I start training it will stop after the following.

Generating anchor boxes for training images and annotation…
Average IOU for 9 anchors: 0.69
Anchor Boxes generated.
Detection configuration saved in Yolo check/json/detection_config.json

After that, it won’t start epochs.so many times I have tried. But it won’t work. Please, let me know sir.

1 Like

@kavitha In what machine are you training your model :

  • Google Colab
  • Laptop/System with NVIDIA GPU
  • Laptop/System with only CPU?

Dear sir,

 I have tried this program with system Nvidia gpu.in that also it won't work.after that I have tried Google colab also.there also not worked.

Thank youl sir,

Kavitha

  • What is the size of your dataset?
  • Also, when using Google Colab, did you ensure you set the Runtime GPU?
  • On your local system, did you ensure you have CUDA and cudNN installed?

Dear sir,I have tried this code last two months back.At that time it works fine with 15 epochs.Now i am again trying the same thing it wont work sir.In Googlecolab and local system .I didn’t get even error also. Please kindly let me know sir.