目标检测：SqueezeDet（linux）

1.创建python虚拟环境

a.安装anaconda

b.conda create -n python2 python=2.7

c.conda activate python2（进入虚拟环境）

2.进入到自己代码的目录执行 pip install -r requirements.txt

3.下载模型（需要连接外网）

4.执行python ./src/demo.py这时候会报错：

Traceback (most recent call last):
  File "./src/demo.py", line 21, in <module>
    import tensorflow as tf
  File "/home/supermicro/anaconda3/envs/python2.7/lib/python2.7/site-packages/tensorflow/__init__.py", line 24, in <module>
    from tensorflow.python import *
  File "/home/supermicro/anaconda3/envs/python2.7/lib/python2.7/site-packages/tensorflow/python/__init__.py", line 72, in <module>
    raise ImportError(msg)
ImportError: Traceback (most recent call last):
  File "/home/supermicro/anaconda3/envs/python2.7/lib/python2.7/site-packages/tensorflow/python/__init__.py", line 61, in <module>
    from tensorflow.python import pywrap_tensorflow
  File "/home/supermicro/anaconda3/envs/python2.7/lib/python2.7/site-packages/tensorflow/python/pywrap_tensorflow.py", line 28, in <module>
    _pywrap_tensorflow = swig_import_helper()
  File "/home/supermicro/anaconda3/envs/python2.7/lib/python2.7/site-packages/tensorflow/python/pywrap_tensorflow.py", line 24, in swig_import_helper
    _mod = imp.load_module('_pywrap_tensorflow', fp, pathname, description)
ImportError: libcudart.so.8.0: cannot open shared object file: No such file or directory


Failed to load the native TensorFlow runtime.

See https://github.com/tensorflow/tensorflow/blob/master/tensorflow/g3doc/get_started/os_setup.md#import_error

for some common reasons and solutions.  Include the entire stack trace
above this error message when asking for help.

解决方法：pip install tensorflow

再执行一次就好啦～

之前出现过得错误有的情况是python3.5环境很多错、自己一步步装它所需要的依赖，也很多错。这个步骤下来就很顺畅