利用image_retrain训练的output_graph.pb识别图片出错

运行python afterselect.py –image_file ~/552.jpg，出现问题

Traceback (most recent call last):

File “afterselect.py”, line 9, in

image = tf.gfile.FastGFile(“home/py/552.jpg”, ‘rb’).read()

File “/usr/local/lib/python2.7/dist-packages/tensorflow/python/lib/io/file_io.py”, line 118, in read

self._preread_check()

File “/usr/local/lib/python2.7/dist-packages/tensorflow/python/lib/io/file_io.py”, line 78, in _preread_check

compat.as_bytes(self.__name), 1024 * 512, status)

File “/usr/lib/python2.7/contextlib.py”, line 24, in exit

self.gen.next()

File “/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/errors_impl.py”, line 466, in raise_exception_on_not_ok_status

pywrap_tensorflow.TF_GetCode(status))

tensorflow.python.framework.errors_impl.NotFoundError: home/py/552.jpg

很明显是读取图片出现问题，但是检查 home/py/552.jpg的确存在，待解决

已解决：相当基础且愚蠢的错误：代码为image_file = sys.argv[1]，那么–image_file则没有任何的意义。

运行：python afterselect.py ~/big.jpg

显示：

2017-06-30 18:19:15.028642: W tensorflow/core/framework/op_def_util.cc:332] Op BatchNormWithGlobalNormalization is deprecated. It will cease to work in GraphDef version 9. Use tf.nn.batch_normalization().

(‘sunflowers’, 0.99449819)

(‘dandelion’, 0.0037702098)

(‘daisy’, 0.0014854319)

(‘tulips’, 0.00020141728)

(‘roses’, 4.4729328e-05)

测试成功