can compile successfully, but can't be executed.

[xiaohedu]

Hi , I try to run your work , but it occurs some questions, as followings:

1. E tensorflow/core/common_runtime/executor.cc:643] Executor failed to create kernel. Invalid argument: NodeDef mentions attr 'dilations' 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: model/encoder/Conv/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](model/encoder/Pad, model/encoder/Conv/weights). (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.). [[Node: model/encoder/Conv/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, device="/job:localhost/replica:0/task:0/device:GPU:0"](model/encoder/Pad, model/encoder/Conv/weights)]] 2018-10-16 15:55:45.548550: F /home/dyh/work/code/monodepth-cpp/src/monodepth.cpp:166] Non-OK-status: session->Run(input, {outputname}, {}, &depth_ ) status: Invalid argument: NodeDef mentions attr 'dilations' 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: model/encoder/Conv/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](model/encoder/Pad, model/encoder/Conv/weights). (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.). [[Node: model/encoder/Conv/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](model/encoder/Pad, model/encoder/Conv/weights)]] Aborted (core dumped)

2. Besides , I want to ask what modifications have been done in mrharicot/monodepth to make sure the frozen graph， could you share your experience ? thank you !

look forward to your answers. Best wishes ！

[yan99033]

Hi, I have uploaded the monodepth.py file in the freeze_graph folder. Check it out and see if the file helps.

[xiaohedu]

Thank you, I have solved it.