-
Notifications
You must be signed in to change notification settings - Fork 1.7k
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
推理ppliteseg时间问题 #3369
Comments
你好,我也在复现这个代码,可以交流一下吗 |
qq3406124214 |
没有达到论文中的速度可能是显卡的性能问题,2060没有1080ti性能好。 |
老哥知不知道他的量化大概是怎么做的?速度问题我感觉应该花费在UAFM模块上 |
可以参考一下此处的文档,既然没有特别提及,我推测应该是默认的部署配置。 |
以上回答已经充分解答了问题,如果有新的问题欢迎随时提交issue,或者在此条issue下继续回复~ |
请问模型导出的时候出现这个错误是怎么回事呀 TypeError: The type of received input == |
问题确认 Search before asking
请提出你的问题 Please ask your question
按照教程部署ppliteseg模型,将模型导出后,使用
![ppliteseg_T1_infer](https://private-user-images.githubusercontent.com/102734479/252859661-282ffc76-c305-4baa-b4c5-a1df806fe6a0.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjExMDU5NDksIm5iZiI6MTcyMTEwNTY0OSwicGF0aCI6Ii8xMDI3MzQ0NzkvMjUyODU5NjYxLTI4MmZmYzc2LWMzMDUtNGJhYS1iNGM1LWExZGY4MDZmZTZhMC5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNzE2JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDcxNlQwNDU0MDlaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT02MzQ2MDMzZTk3MTc1OWI2ZjRjNDdhY2Y2MDY5YzU5OWNjNzUxZmVlZjM1NWNlZmJiMTg5YWQ5MGQ5ZmE2MzJlJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.SpN2ANdIEC-UQ7h_KDSBaOQAjiQjo-6zDCtMGsTs8Z4)
python deploy/python/infer.py
--config output/inference_model/ppliteseg_T1/deploy.yaml
--image_path /home/dfl/resize_half/leftImg8bit_512/train/aachen/aachen_000001_000019_leftImg8bit.png
--save_dir output/result/ppliteseg_T1
--device 'gpu'
--use_trt True
--enable_auto_tune True
--benchmark True
--precision 'fp32'
进行部署推理,这里推理时间只有7.5ms,改为"int8"后最高也只有5.17ms
查看issue说是转为onnx进行trt加速会比Paddle Inference快,可以达到论文中的速度,然而按照教程进行推理后速度并没有达到预期速度
![ppliteseg_T1_infer_onnx](https://private-user-images.githubusercontent.com/102734479/252859776-f812ed1f-dcec-4293-8f5c-e7fb41e4bf92.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjExMDU5NDksIm5iZiI6MTcyMTEwNTY0OSwicGF0aCI6Ii8xMDI3MzQ0NzkvMjUyODU5Nzc2LWY4MTJlZDFmLWRjZWMtNDI5My04ZjVjLWU3ZmI0MWU0YmY5Mi5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNzE2JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDcxNlQwNDU0MDlaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT1hMGZkZDFlNmM4NWU3MzYzNDNjZmE3YjA0MjhjNjhmZTJiYzU0YzVmMDA2MDViNmZkNGNkOTFhZjkwM2YxZDcxJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.-GJc8Cg65J5s7HWrT05MUAxWZyCbHeCFVZlqX3BaIvE)
![Screenshot 2023-07-12 13:02:46](https://private-user-images.githubusercontent.com/102734479/252860128-451ec145-4f20-4981-9354-bf4a6debe5c8.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjExMDU5NDksIm5iZiI6MTcyMTEwNTY0OSwicGF0aCI6Ii8xMDI3MzQ0NzkvMjUyODYwMTI4LTQ1MWVjMTQ1LTRmMjAtNDk4MS05MzU0LWJmNGE2ZGViZTVjOC5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNzE2JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDcxNlQwNDU0MDlaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT0wYmY1NmE4MDc3YjQyZjMxZTM0NzNlZjY5NzhhN2YyYmYzNGVlYjE5NGNkNGFjNTMwYjQwOTkzYmU3NjU3MjkwJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.BYp0UtXOUbftEkQi6n6kFWQQK7_VXi_nZtIOdVgWj_Y)
python deploy/python/infer_onnx_trt.py
--config configs/stdcseg/stdc1_seg_cityscapes_1024x512_160k_if_RegSeg_5.yml
--width 1024 --height 512
--enable_profile
所使用的的tensorrt为8.4.1.5 GPU为2060
同时我还试了STDC1_Seg50
python deploy/python/infer.py
--config output/inference_model/stdc1_seg50/deploy.yaml
--image_path /home/dfl/resize_half/leftImg8bit_512/train/aachen/aachen_000001_000019_leftImg8bit.png
--save_dir output/result/stdc1_seg50
--device 'gpu'
--use_trt True
--enable_auto_tune True
--benchmark True
--precision 'int8'
fp32 推理速度为6ms左右,采用"int8"后最高能到4.446ms,比ppliteseg_T1快好多,使用onnx和tensorrt加速后速度为7.427ms
请问论文中的推理有没有进行量化处理 速度能达到273FPS
The text was updated successfully, but these errors were encountered: