Timm Haucke

> Thank you for the scripts @timmh. I have been trying to export larger size models but the script freezes and I have to kill the computer manually to restart...

@yohannes-taye I can reproduce the issue but to be honest I have no idea where the issue stems from. Probably there is some tensor in the model which is created...

adding `CFLAGS='-stdlib=libc++'` worked for me, e.g.: `CFLAGS='-stdlib=libc++' pip install PyMaxflow` (similar to https://github.com/huggingface/neuralcoref/issues/97)

Nevermind, I solved the above issue by calling: ```diff -model = YOLOv5.load_from_yolov5( +model = YOLO.load_from_yolov5( input_weights, - size=size, - size_divisible=size_divisible, score_thresh=score_thresh, nms_thresh=nms_thresh, ) ``` The resulting model seems to accept...

For anyone still interested in this, I've implemented working ONNX export for metric depth models here: https://github.com/timmh/Depth-Anything

This sounds to me like you might be running out of memory while the visualization script extracts image and proposal-level features. Could you try monitoring your memory consumption and possibly...