Toybrick

标题: 1808算力棒，跑yolov3demo [打印本页]

作者: dszs 时间: 2023-3-9 09:21
标题: 1808算力棒，跑yolov3demo
您好：
我使用你们的1808算力棒，运行sdk中的yolov3 demo。报如下错误。

root@debian10:/home/toybrick/yolov3# python3 test.py
Traceback (most recent call last):
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/pywrap_tensorflow.py", line 62, in <module>
from tensorflow.python._pywrap_tensorflow_internal import *
ImportError: /usr/local/lib/python3.7/dist-packages/tensorflow/python/../../tensorflow_cpu_aws.libs/libgomp-d22c30c5.so.1.0.0: cannot allocate memory in static TLS block

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "test.py", line 8, in <module>
from tensorflow.python.platform import gfile
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/__init__.py", line 37, in <module>
from tensorflow.python.tools import module_util as _module_util
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/__init__.py", line 36, in <module>
from tensorflow.python import pywrap_tensorflow as _pywrap_tensorflow
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/pywrap_tensorflow.py", line 78, in <module>
f'{traceback.format_exc()}'
ImportError: Traceback (most recent call last):
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/pywrap_tensorflow.py", line 62, in <module>
from tensorflow.python._pywrap_tensorflow_internal import *
ImportError: /usr/local/lib/python3.7/dist-packages/tensorflow/python/../../tensorflow_cpu_aws.libs/libgomp-d22c30c5.so.1.0.0: cannot allocate memory in static TLS block

Failed to load the native TensorFlow runtime.
See https://www.tensorflow.org/install/errors for some common causes and solutions.
If you need help, create an issue at https://github.com/tensorflow/tensorflow/issues and include the entire stack trace above this error message.
root@debian10:/home/toybrick/yolov3#

作者: dszs 时间: 2023-3-9 09:22
是环境哪里有问题吗？

作者: jefferyzhang 时间: 2023-3-9 09:56
这看过去是tensorflow没装好，我建议你如果在1808上跑模型的话，用rknntoolkit-lite，不要用完整版rknntoolkit，这样不会依赖到tensorflow、pytorch这么大的包

作者: dszs 时间: 2023-3-9 10:21
sdk中有没有基于rknntoolkit-lite的demo.我试一下

欢迎光临 Toybrick (https://t.rock-chips.com/)