2020-10-14

在运行https://github.com/MonkeyDTH/h52pb中的load_pb_test.py时出现以下的错误：

File "load_pb_test.py", line 67, in <module>
    recognize(img, pb_path)
  File "load_pb_test.py", line 16, in recognize
    tensors = tf.import_graph_def(output_graph_def, name="")
  File "/home/ed/anaconda3/envs/cam/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 313, in import_graph_def
    op_def=op_def)
  File "/home/ed/anaconda3/envs/cam/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/home/ed/anaconda3/envs/cam/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1204, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): NodeDef mentions attr 'explicit_paddings' not in Op<name=Conv2D; signature=input:T, filter:T -> output:T; attr=T:type,allowed=[DT_HALF, DT_FLOAT]; attr=strides:list(int); attr=use_cudnn_on_gpu:bool,default=true; attr=padding:string,allowed=["SAME", "VALID"]; attr=data_format:string,default="NHWC",allowed=["NHWC", "NCHW"]>; NodeDef: conv2d/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], explicit_paddings=[], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/gpu:0"](_arg_conv2d_input_0_0/_1, conv2d/Conv2D/ReadVariableOp). (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).
         [[Node: conv2d/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], explicit_paddings=[], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/gpu:0"](_arg_conv2d_input_0_0/_1, conv2d/Conv2D/ReadVariableOp)]]

当前环境：conda 虚拟环境中

tensorflow                1.3.0                         0    https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
tensorflow-base           1.3.0            py36h5293eaa_1    https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
tensorflow-gpu            1.3.0                         0    https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
tensorflow-gpu-base       1.3.0           py36cuda8.0cudnn6.0_1    https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
tensorflow-tensorboard    0.1.8                    pypi_0    pypi
theano                    0.9.0                    py36_0    https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
tk                        8.6.10               hbc83047_0    defaults
toolz                     0.8.2                    py36_0    https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
 

于是更换环境，将tensorflow-gpu换成1.14的，再次输入命令python load_pb_test.py，运行成功。