lidehuihxjz

How much memery is needed when train with single GPU?

1

I trained the model wiht single GPU when batchsize is 2 and got error of _out of memery_. I tried to test with a very simple backbone, containing only 4...

masks of lane segmentation are not aligned

1

Hello, When I visualize the land segmentation masks，I found that they are not aligned with the RGB images. How can I solve this problem？ Thanks！  

YOLOv5的模型怎么转换为NCNN?

1

YOLOv5提供了转换为ONNX的工具，请问有转换为NCNN模型的工具吗？

When I train with multi gpu, there always comes the erorr: _OSError: [Errno 24] Too many open files_ Do you know what's going on?

ImportError: No module named addict

2

When I ran the train command, there was an error: _File "./Pelee.Pytorch/configs/CC.py", line 14, in from addict import Dict ImportError: No module named addict_ I can't deal with this problem...

SSD用于检测6个输出特征图的来自不同的卷积阶段，其分辨率也不同，但是在本代码中，输出检测分辨率都是原图的1/32，请问大佬这样改动是有什么收益吗？

ValueError: some parameters appear in more than one parameter group

2

Hi, when I used DiverseBranchBlock to replace Conv-Bn in my network, I met this error _ValueError: some parameters appear in more than one parameter group_ Have you met it before?

got error: Segmentation fault (core dumped)

1

when I run "from pytorch2caffe import pytorch2caffe", I always got error: Segmentation fault (core dumped). Anyone know about why? Thanks!