search

WongKinYiu / yolov7

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
GNU General Public License v3.0
13.38k stars 4.22k forks source link

training error got labels、p、r all 0 #938

Open hu-luoye opened 2 years ago

hu-luoye commented 2 years ago

image

liu-h-ning commented 2 years ago

I have the same question,how to solved it

hu-luoye commented 2 years ago

I have the same question,how to solved it

try this model/yolo.py line 517 with open(cfg) as f: replace: with open(cfg,encoding='GB18030', errors='ignore') as f:

liu-h-ning commented 2 years ago

not work

---Original--- From: @.> Date: Wed, Oct 19, 2022 11:30 AM To: @.>; Cc: @.**@.>; Subject: Re: [WongKinYiu/yolov7] training error got labels、p、r all 0 (Issue #938)

I have the same question,how to solved it

try this model/yolo.py line 517 with open(cfg) as f: replace: with open(cfg,encoding='GB18030', errors='ignore') as f:

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

aliwaqas333 commented 2 years ago

I am having the same problem in validation phase. Class Images Labels P R mAP@.5 mAP@.5:.95: all 220 0 0 0 0 0

Why are Labels 0. Its a custom dataset. Labels are not 0 in training phase though.

Ahmadreza1365 commented 1 year ago

I am having the same problem in validation phase. Class Images Labels P R mAP@.5 mAP@.5:.95: all 220 0 0 0 0 0

Why are Labels 0. Its a custom dataset. Labels are not 0 in training phase though.

Were you able to resolve this?