dataset.txt

[QiaoSiBo]

I do not understand how to make dataset.txt? Could you please tell me about this? thanks.

[YunYang1994]

dataset.txt contains image_path and the coordinates of grounding truth boxes in the image

[QiaoSiBo]

enn, but how can I get this txt? Do you have one .sh?

[YunYang1994]

Sorry, you need to generate it by yourself.

[QiaoSiBo]

ok, got it, thanks

[Ace95]

Any suggestion to generate the dataset.txt file? How do you get the "truth boxes" on the training data?

Thanks for the help!

[Ace95]

I wrote this little python script that allows you to draw the "truth boxes" on the images and saves the cooordinates in dataset.txt.

https://github.com/Ace95/tensorflow-yolov3/blob/master/Dataset_gen.py

[xycim]

@Ace95 when ran your script, I got a error: cv2.error: OpenCV(4.1.0) /io/opencv/modules/highgui/src/window.cpp:352: error: (-215:Assertion failed) size.width>0 && size.height>0 in function 'imshow' so,what your opencv verison？

[Ace95]

@Ace95 when ran your script, I got a error: cv2.error: OpenCV(4.1.0) /io/opencv/modules/highgui/src/window.cpp:352: error: (-215:Assertion failed) size.width>0 && size.height>0 in function 'imshow' so,what your opencv verison？

Sorry for late replay, I'm usign OpenCV 4.1.0. Check that the "filelist.txt" you are using is correct and that there are no blank lines. If you generated it with the code in the script it may have a blank first line, delate that and re-run the script. Let me know if you can get the dataset.txt file with the correct boxes coordinates..

[hadizand]

https://github.com/pythonlessons/YOLOv3-object-detection-tutorial/blob/master/YOLOv3-CSGO-detection/voc_to_YOLOv3_NO_CLASSES.py

[ghost]

Can anyone help how to prepare data for few images with just background(no objects) ?