Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Apache License 2.0
12.65k
stars
2.87k
forks
source link
Compiled with WITH_GPU, but no GPU found in runtime #8617
The code runs fine while running on my local gpu but in ml.p2.xlarge instance with aws docker sagemaker i get the above error, tried with many combinations of images still same issue, can you help me with this?
问题确认 Search before asking
请提出你的问题 Please ask your question
FROM paddlepaddle/paddle:2.4.2-gpu-cuda11.7-cudnn8.4-trt8.4 I have used above image as base image.
RUN python -m pip install --no-cache-dir paddlepaddle-gpu==2.4.2.post117 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html
I am using above versionof paddle only because I get error during export to onnx with other versions. https://github.com/PaddlePaddle/Paddle2ONNX/issues/1147
The code runs fine while running on my local gpu but in ml.p2.xlarge instance with aws docker sagemaker i get the above error, tried with many combinations of images still same issue, can you help me with this?