8000 Loss is NAN · Issue #104 · hank-ai/darknet · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
Loss is NAN #104
Open
Open
@iko0167

Description

@iko0167

When i try to train yolov4-crowdhuman dataset with yolov4, loss and avg_loss is always nan, but when i try to train same dataset with yolov4-tiny or yolov4-tiny-3l or even yolov7-tiny its ok.

In addition when i try to train same dataset with same system (Same CUDA and CUDNN version, same laptop) with AlexeyAB repo and yolov4, its working fine.

My System:

NVIDIA GeForce RTX 3070 Mobile
12th Gen Intel i7-12700H
CUDA Version 12.4 with drivers
CUDNN 8.9.7

Metadata

Metadata

Labels

bugSomething isn't working

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions

    0