darknet: ./src/utils.c:256: error: Assertion `0' failed.

[ivankg89]

Thanks to provide the source! Hope your reply!

I convert the exam yolov3-tiny successful, but when I convert my own yolov3 model, I recipe the message: First section must bu [net] or [network]: Success. darknet2ncnn: ./src/utils.c: 256: error: Assertion '0' failed. Aborted (core dumped).

[wutianze]

I have the same problem, I can run with my own weights and .cfg, but the initial weights doesn't work

[wutianze]

I solve this by replacing the yolov3.cfg with a new one, may this help you

[ivankg89]

Could you please send me your cfg?

[wutianze]

I use the yolov3.cfg in pjreddie/darknet

[neverstoplearn]

i meet the same error , have someone help me? thanks

[goldengrisha]

In my case, that was the problem with images width and height, please check.

[martinrkeyser]

Hey people. I had the same issue, in the end I had to update the ARCH line in my makefile and rebuild. Please note, I did have to install CUDA V10 because I am running a GTX 1650 using the compute_75 architecture.

[dm0mb]

In my case, that was the problem with images width and height, please check.

I think you are right, I change width and height get this issue. if you want it work well , change your width = height in yolo_*.cfg. I think yolo can not work good in this issue. so any one have good idea about this.

[dm0mb]

yolov4.cfg - 245 MB: yolov4.weights (Google-drive mirror yolov4.weights ) paper Yolo v4 just change width= and height= parameters in yolov4.cfg file and use the same yolov4.weights file for all cases:

width=608 height=608 in cfg: 65.7% mAP@0.5 (43.5% AP@0.5:0.95) - 34(R) FPS / 62(V) FPS - 128.5 BFlops width=512 height=512 in cfg: 64.9% mAP@0.5 (43.0% AP@0.5:0.95) - 45(R) FPS / 83(V) FPS - 91.1 BFlops width=416 height=416 in cfg: 62.8% mAP@0.5 (41.2% AP@0.5:0.95) - 55(R) FPS / 96(V) FPS - 60.1 BFlops width=320 height=320 in cfg: 60% mAP@0.5 ( 38% AP@0.5:0.95) - 63(R) FPS / 123(V) FPS - 35.5 BFlops

[Prasanna-icefire]

I managed to solve this issue by changing the subdivisions=16 to subdivisions=64 in my yolo-obj.cfg file.

[Cococatty]

Hey all, I cloned the repo today and having the same issue.

I tried the ImageNet, Cifar-10 (Classifier) examples on darknet official site but neither of them are working. :(

Error message as below: First section must be [net] or [network]: Success darknet: ./src/utils.c:256: error: Assertion `0' failed. Aborted (core dumped)

I have re-cloned the repo but not helping.

Any advice?

Thanks! :D

[thunfischtoast]

If you copied the config file from windows to linux, here is something to try, it solved the problem for me: https://github.com/pjreddie/darknet/issues/235#issuecomment-340679060

TLDR: When copying config files from windows to linux, run dos2unix on it before continuuing.

[sba17]

Updated subdivision to 64 has resolved the issue.

[hoffm621]

In my case, that was the problem with images width and height, please check.

Can you tell me exactly how you fixed the height and width problems?