BowenXu
BowenXu
> you are right, in my YOLOX, the depth ratio also control the number of decoupled conv in the head part, I just want to check if the 1.0 width...
> Our work starts from reproducing yolov5 with more flexible training arch design. After obtaining the same ap/param/flops effect as the github version, we use consistent hyperparameters to train the...
> @BowieHsu Thanks for your attention! We 'll release large size models for YOLOv6, and the results shown in the table seem much different from ours. Thank you for your...
But your code shows that if I want to call repopt mode for finetune, the loading module is RealVGGBlock, and the scale parameter of optimizer must be read from LinearAddBlock...
yes, in fact, we will frequently finetune the model based on the newly received data, this part can be written more elegantly.
> > yes, in fact, we will frequently finetune the model based on the newly received data, this part can be written more elegantly. > > We have update the...
@kalluwa 你好，简易的教程已经更新了，其实就是Tensorflow官方给的分类的例子，然后把project的输入替换成tensorflow.lib和protobuf.lib，然后把tensorflow.dll放在生成的可执行文件的目录下，就可以运行了
我只在自己的环境上(Win7 + VS2015 + CUDA 8 + cudnn5.1)测试过，你试试solution能不能跑起来先
@kalluwa 好的，我检查一下
@kalluwa gpu那个文件夹我去掉了 应该不会对编译产生影响，这个error2我检查了也没有遇到过，你是在Release下用x64进行编译的么，因为这个项目是有Preprocessor Definitions的