Closed Grula closed 1 year ago
ocr infer python code, meet the same error, have you solve this, guys?
` [{'res': 'B', 'score': 0.9999068975448608, 'left_top_xy': [21.0, 13.0], 'right_top_xy': [43.0, 18.0], 'right_bottom_xy': [37.0, 49.0], 'left_bottom_xy': [15.0, 44.0], 'bbox_center_xy': (29, 31)}] [2023/12/21 16:34:59] ppocr DEBUG: dt_boxes num : 12, elapsed : 0.027253150939941406 [2023/12/21 16:34:59] ppocr DEBUG: cls num : 12, elapsed : 0.024739980697631836 (External) CUDA error(719), unspecified launch failure. [Hint: 'cudaErrorLaunchFailure'. An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointerand accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases canbe found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work willreturn the same error. To continue using CUDA, the process must be terminated and relaunched.] (at ../paddle/phi/backends/gpu/cuda/cuda_info.cc:272) [operator < reshape2 > error] (External) CUDA error(719), unspecified launch failure. [Hint: 'cudaErrorLaunchFailure'. An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointerand accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases canbe found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work willreturn the same error. To continue using CUDA, the process must be terminated and relaunched.] (at ../paddle/phi/backends/gpu/cuda/cuda_info.cc:265)
(External) CUDA error(719), unspecified launch failure. [Hint: 'cudaErrorLaunchFailure'. An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointerand accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases canbe found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work willreturn the same error. To continue using CUDA, the process must be terminated and relaunched.] (at ../paddle/phi/backends/gpu/cuda/cuda_info.cc:265)
(External) CUDA error(719), unspecified launch failure. [Hint: 'cudaErrorLaunchFailure'. An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointerand accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases canbe found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work willreturn the same error. To continue using CUDA, the process must be terminated and relaunched.] (at ../paddle/phi/backends/gpu/cuda/cuda_info.cc:265) `
@dyh What i found in my case was bug in nvidia driver, after some digging on nvidia forums, i found that driver version has that bug fixed is: NVIDIA-SMI 520.61.05 Driver Version: 520.61.05 CUDA Version: 11.8
@Grula thank you for your reply!!! we update paddle version -> PaddlePaddle 2.5.0 , and it works fine.
我也遇到这个问题了,我是ocr文本框坐标超出图像宽高范围,是旋转导致,旋转好弄成一致的就可以了
bug描述 Describe the Bug
Describe the Bug: Following the tuorial to run text detection training on icdar2015 dataset.
$ python3 tools/train.py -c configs/det/det_r50_vd_db.yml
Text Detection. Everything is same as showin in example, small adjustment was made in yml file for number of batch images. After a while (5-10 mins) terminal would freeze and following error would show:OS information :
GPU Information:
From paddle:
CPU information
installed paddle libraries ( as stated in documentation)
python & conda versions:
Run and cloned from brach: origin/release/2.4 (79fc4c5befac276de7208d0dd8f8ac0bc2d5e2b1)
其他补充信息 Additional Supplementary Information
Sidenots: I've noticed server freezing for couple of seconds before displaying the error, following message is also found from
$ dmesg