博客
关于我
工程实践_LFFD模型训练过程疑难杂症debug
阅读量:537 次
发布时间:2019-03-08

本文共 2359 字,大约阅读时间需要 7 分钟。

1.MxNet版本的LFFD需要安装CUDA10.1版本和CuDNN

若不满足会出现如下问题:

安装的CUDA版本太低或没有安装:

raceback (most recent call last):  File "configuration_10_320_20L_5scales_v2.py", line 17, in 
import mxnet File "/usr/local/lib/python3.6/dist-packages/mxnet/__init__.py", line 24, in
from .context import Context, current_context, cpu, gpu, cpu_pinned File "/usr/local/lib/python3.6/dist-packages/mxnet/context.py", line 24, in
from .base import classproperty, with_metaclass, _MXClassPropertyMetaClass File "/usr/local/lib/python3.6/dist-packages/mxnet/base.py", line 213, in
_LIB = _load_lib() File "/usr/local/lib/python3.6/dist-packages/mxnet/base.py", line 204, in _load_lib lib = ctypes.CDLL(lib_path[0], ctypes.RTLD_LOCAL) File "/usr/lib/python3.6/ctypes/__init__.py", line 348, in __init__ self._handle = _dlopen(self._name, mode)OSError: libcudart.so.10.1: cannot open shared object file: No such file or directory

没有安装CuDNN:

terminate called after throwing an instance of 'dmlc::Error'  what():  [20:48:36] ../include/mshadow/./stream_gpu-inl.h:173: Check failed: err == CUDNN_STATUS_SUCCESS (4 vs. 0) : CUDNN_STATUS_INTERNAL_ERRORAborted (core dumped)

2.正确使用Python和正确安装MxNet版本

若已经正确安装CUDA和CUDNN,仍然出现:

terminate called after throwing an instance of 'dmlc::Error'  what():  [20:48:36] ../include/mshadow/./stream_gpu-inl.h:173: Check failed: err == CUDNN_STATUS_SUCCESS (4 vs. 0) : CUDNN_STATUS_INTERNAL_ERRORAborted (core dumped)

有两种可能:首先查看MxNet版本是否正确,再在configuration_10_560_25L_8scales_v1.py代码中将如下代码注释:

# add mxnet python path to path env if needmxnet_python_path = '/home/heyonghao/libs/incubator-mxnet/python'sys.path.append(mxnet_python_path)

我们只需要使用我们本地默认的Python就行。

3.正确安装OpenCV

如出现如下问题:

During handling of the above exception, another exception occurred:Traceback (most recent call last):  File "_ctypes/callbacks.c", line 234, in 'calling callback function'  File "/root/work/mxnet/python/mxnet/operator.py", line 1052, in backward_entry    print('Error in CustomOp.backward: %s' % traceback.format_exc())UnicodeEncodeError: 'ascii' codec can't encode characters in position 369-376: ordinal not in range(128)

说明OpenCV版本没有正确安装,删除旧版本之后安装如下版本:

pip install opencv-python==3.4.5.20

4.正确设置batch_size

遇到如下问题,很可能是batch_size设置的太大:

MXNetError: cudaMalloc retry failed: out of memory

可以设置batch_size=16

转载地址:http://gsbiz.baihongyu.com/

你可能感兴趣的文章
mysql5.7.19安装图解_mysql5.7.19 winx64解压缩版安装配置教程
查看>>
MySQL5.7.37windows解压版的安装使用
查看>>
mysql5.7免费下载地址
查看>>
mysql5.7命令总结
查看>>
mysql5.7安装
查看>>
mysql5.7性能调优my.ini
查看>>
MySQL5.7新增Performance Schema表
查看>>
Mysql5.7深入学习 1.MySQL 5.7 中的新增功能
查看>>
Webpack 之 basic chunk graph
查看>>
Mysql5.7版本单机版my.cnf配置文件
查看>>
mysql5.7的安装和Navicat的安装
查看>>
mysql5.7示例数据库_Linux MySQL5.7多实例数据库配置
查看>>
Mysql8 数据库安装及主从配置 | Spring Cloud 2
查看>>
mysql8 配置文件配置group 问题 sql语句group不能使用报错解决 mysql8.X版本的my.cnf配置文件 my.cnf文件 能够使用的my.cnf配置文件
查看>>
MySQL8.0.29启动报错Different lower_case_table_names settings for server (‘0‘) and data dictionary (‘1‘)
查看>>
MYSQL8.0以上忘记root密码
查看>>
Mysql8.0以上重置初始密码的方法
查看>>
mysql8.0新特性-自增变量的持久化
查看>>
Mysql8.0注意url变更写法
查看>>
Mysql8.0的特性
查看>>