PaddlePaddle
Segmentation fault (core dumped)
问题确认 Search before asking
- [X] 我已经查询历史issue(包括open与closed)，没有发现相似的bug。I have searched the open and closed issues and found no similar bug report.
Bug描述 Describe the Bug
python: class Predictor: def predict(self, processed_img):
input_names = self.predictor.get_input_names()
input_handle = self.predictor.get_input_handle(input_names[0])
processed_img = np.expand_dims(processed_img, 0)
input_handle.reshape(processed_img.shape)
input_handle.copy_from_cpu(processed_img)
self.predictor.run()
output_names = self.predictor.get_output_names()
output_handle = self.predictor.get_output_handle(output_names[0])
output = output_handle.copy_to_cpu()
return (np.argmax(output.squeeze(), axis=0)*255).astype('uint8')
the problem comes in "self.predictor.run()"
bug:
C++ Traceback (most recent call last):
No stack trace in paddle, may be caused by external reasons.
Error Message Summary:
FatalError: Segmentation fault is detected by the operating system.
[TimeInfo: *** Aborted at 1685362505 (unix time) try "date -d @1685362505" if you are using GNU date ***]
[SignalInfo: *** SIGSEGV (@0x0) received by PID 8826 (TID 0x7fe4ca50b740) from PID 0 ***]
Segmentation fault (core dumped)
复现环境 Environment
os: linux paddlepaddle-gpu 2.4.0 python 3.7.12 CUDA: 11.4
Bug描述确认 Bug description confirmation
- [X] 我确认已经提供了Bug复现步骤、代码改动说明、以及环境信息，确认问题是可以复现的。I confirm that the bug replication steps, code change instructions, and environment information have been provided, and the problem can be reproduced.
是否愿意提交PR？ Are you willing to submit a PR?
- [ ] 我愿意提交PR！I'd like to help by submitting a PR!
There are a bunch of reasons causing a segmentation fault, and I think the first thing is to check if the inference library is perperly built on your machine. Please run this demo to do the check.
