search

elyha7 / yoloface

Yolov5 Face Detection
GNU General Public License v3.0
120 stars 37 forks source link

ONNX converting #5

Open Papenkov opened 2 years ago

Papenkov commented 2 years ago

Hello, mate @elyha7 . I'm trying to convert face detector to onnx via your "export.py" file and have some issue: after convertion output sizes don't fit with output sizes from loaded model ("model = YoloDetector( ... )")

yolo output netron_model_output Is it ok? And I'm confused, which postprocessing I need to do with these outputs? Any ideas? P.S. thx a lot for your repo))

Wo-oh-oh-ooh-oh commented 1 year ago

I want to use "export.py" file to convert detector to onnx but I got a mistake [KeyError: 'model' ] in torch.load(w, map_location=map_location)['model'].float().fuse().eval()". This code in function attempt_load in "experimental.py" file. image It maybe in "torch.load" hasn't key " model",but why?