CaiOrange

> Use low for nano or small models, medium for medium, and high for larger models. If I replace the Backbone with another network, does this rule still apply? In...

Update some information:I try to use the five hyp files of yolov5 for training and get five models. I found that their results under deepstream are different, but they are...

> > `Jetpack 4.6 deepstream 6.0.1 yolov5 6.1 ` I tested yolov5s , yolov7 , yolor （untrained,all of them），the can work well. I trained yolov5（changed backbone，but layers(CBH , LC_block ,...

Maybe you can edit ./nvdsinfer_custom_impl_Yolo/nvdsparsebbox_Yolo.cpp

backbone中使用大佬的改进方法，neck使用DWConv，这两部分都能正常训练，而将后两个Concat替换为ADD后报如题错误。链接中是改动了的网络yaml文件、common.py（添加的模块在最下部）、yolo.py。 链接：https://pan.baidu.com/s/1x7Bv-wW60aA1wixVI2ksWw?pwd=1111 提取码：1111

It is my models:` from n params module arguments 0 -1 1 928 models.common.conv_bn_relu_maxpool [3, 32] 1 -1 1 8812 models.common.Shuffle_Block [32, 120, 2] 2 -1 3 24300 models.common.Shuffle_Block [120,...

I send them to your email,many thanks for your help!

Hi,about this issue，I had sent my model and common file to your email,can I get your help?My email adress is [email protected]

Thank you most sincerely.

First, thanks abouts it! I tested the project with the new gen_wts_yoloV5 file in these days,and no errors were encountered.But in the end I tested project "DeepStream-Yoolo-master" with an H264...