-
Notifications
You must be signed in to change notification settings - Fork 86
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
只添加fastreid模型 #8
Comments
主要修改featuretensor.h/cpp文件 FeatureTensor类会使用rknn_fp初始化fastreid模型 |
谢谢博主,感激百忙之中抽空回复 |
how does fastreid compare to osnet? Do you find it better? Is there a repo you can share? |
Sorry, I don’t know OSnet very well, I mainly know fast-reid more, this toolkit is more convenient and fast to use. |
thanks, one last question if you dont mind: What is the chip that you are using? On that chip, what is the inference time for fast-reid - for a single extraction of features? |
Yor are welcome. My device is RK1808 which is processing by NUP.The processing time is about 60ms.If you don't mind, we can communicate further, such as ins, wechat and so on.(Please forgive my broken english.) |
博主您好,我在尝试使用yolov5和fastreid进行人物识别,主要就行利用fastreid对我特定的人进行识别,想知道怎么在您的工作上进行改动呢,具体流程就是yolo检测到目标后,通过fastreid提取特征,进行特征对比,输出相应结果
The text was updated successfully, but these errors were encountered: