-
Hi,
I tested the tiny model on a CPU, it turned on approximately 350ms per image, at the same time, I tested the nano version of YOLOv5 on the same CPU and it was two times faster than YOLOv7-tiny. H…
-
# New Operator
SiLU
### Describe the operator
SiLU is the main activation function used in [YOLOV5](https://github.com/ultralytics/yolov5)
### Can this operator be constructed using existing onn…
-
您好，我想要下您那个overlap后拼接的NMS的代码，不知道您能不能分享下呀
-
## error log | 日志或报错信息 | ログ
## context | 编译/运行环境 | バックグラウンド
## how to reproduce | 复现步骤 | 再現方法
1. Android Studio打包NCNN Demo(ARM64)
2. 小米12Pro安装
3. 打开APP ，点击子功能，卡死
## more | 其他 | その他
-
以yolov5为例
我通过修改了 这两部分的代码
 int8 TFLite model to EdgeTPU, but LeakyRelu and Hardswish ops are not supported. (https://github.com/ultralytics/yolov5/pull/…
-
![image](https://github.com/WongKinYiu/yolov9/assets/83396614/ba5041ea-d47e-44c9-978c-7468b9c844c…
-
I Only got a detect py file. Please Tell me where to make the necessary changes. I just want my object to be tracked while it's been detected. I got my model runnung on yolov5.