search

Lornatang / YOLOv3-PyTorch

Pytorch implements yolov3.Good performance, easy to use, fast speed.
Apache License 2.0
32 stars 15 forks source link

CUDA out of memory! #3

Closed JamesZhan107 closed 1 year ago

JamesZhan107 commented 4 years ago

When i train custom data , It always gives this error. image

Are there any parameters I need to set ???

JamesZhan107 commented 4 years ago

I solved this problem after add --image-size in train command! But the mAP is very low...

JamesZhan107 commented 4 years ago

@Lornatang

Lornatang commented 4 years ago

I don't seem to have encountered this problem, and if there is not enough batch, there may be a problem loading the dataset.

JamesZhan107 commented 4 years ago

I don't seem to have encountered this problem, and if there is not enough batch, there may be a problem loading the dataset.

The mAP is still very low after i modify the batch-size to 64.

But when i trained on ultralytics/yolov3 , it works well. @Lornatang

JamesZhan107 commented 4 years ago

when i use your mobilenetv3-large cfg file on ultralytics/yolov3, It produces the following error.

image

Is this a problem with the cfg file or what function needs to be modified？ @Lornatang

I'm sorry to disturb you !

Lornatang commented 4 years ago

I didn't test enough on the mobilenetv3 large configuration file. Don't use it first

JamesZhan107 commented 4 years ago

OK, there is no problem with v1 and v2. Mobilenetv3 large and small configuration file has something wrong.