-
Notifications
You must be signed in to change notification settings - Fork 225
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
python 程序中每帧图像的耗时问题 #236
Comments
因为本仓库采用了静态shape(640*640)的进行推理,然后pytorch的版本可能采用了最小padding(480x640),这样的话确实存在效率会不如pytorch. |
请问下 使用infer-det.py 进行fp16的engine模型推理时 为什么输入的图片不需要指定dtype=float16呢 。yolov5代码里是加了half()的 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
大佬 您好,我用的自己训练的yolov8s pt模型通过readme中的教程转成的engine,然后修改了infer_det.py代码使其能够调用摄像头,我想计算每帧的耗时,不知道下面的代码计算对不对:
和pt模型推理的速度相比,engine加速感觉没啥提升,如下图
修改后代码的测速
pt模型的推理速度
The text was updated successfully, but these errors were encountered: