Empty annotation data

[naruto553]

Hi, I tried to auto-annotate the images by custom YOLOv8 model. It successfully completed the process and detects the objects, but the text files of the annotation data are empty. Do you have any idea why this could happen? Please see below for the log.

===COMMAND===
!python autoAnotYolo.py --dataset input/images --model_type yolov8
--model model.pt --confidence 0.5
===OUTPUT===
The console stream is logged into XXXX
Successfully Created 202103.txt
Successfully Annotated 202103.jpg
Successfully Created 202103_1.txt
Successfully Annotated 202103_1.jpg
[INFO] Saved Labelmap to: input/images/classes.txt
[INFO] yolov8-Auto_Annotation Successfully Completed
[2023-06-22 12:52:00] INFO - crash_tips_setup.py - Crash tips is enabled. You can set your environment variable to CRASH_HANDLER=FALSE to disable it
[2023-06-22 12:52:01] WARNING - redirects.py - NOTE: Redirects are currently not supported in Windows or MacOs.
[2023-06-22 12:52:03] WARNING - init.py - Failed to import pytorch_quantization
[2023-06-22 12:52:03] WARNING - calibrator.py - Failed to import pytorch_quantization
[2023-06-22 12:52:03] WARNING - export.py - Failed to import pytorch_quantization
[2023-06-22 12:52:03] WARNING - selective_quantization_utils.py - Failed to import pytorch_quantization
[2023-06-22 12:52:03] WARNING - env_sanity_check.py - Failed to verify operating system: Deci officially supports only Linux kernels. Some features may not work as expected.

0: 320x640 1 A, 1 V, 1 Z 86.9ms
Speed: 3.0ms preprocess, 86.9ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)

0: 320x640 1 Q, 1 S, 1 X 105.8ms
Speed: 2.5ms preprocess, 105.8ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)

[NASEEM A P]

Hi @naruto553 ,
I will test it and let you know.
Thank you for finding this issue.

[NASEEM A P]

Hi @naruto553 ,
I fixed this issue please check the updated repo.
Let me know this is solved your issue.
Thank you.