using tensorflow 1.6.0
The model is from keras, and it is MobileNet, which is called using keras.application. (ps. I didn't make any changes to the model.)
I converted the model into a protobuf file and tried to covert it into graph using mvNCCompile, getting this error.
Is there any idea why this error happen?
Is it caused by the version of tensorflow? if so, which version is the best one for compiling to graph?
InvalidArgumentError (see above for traceback): NodeDef mentions attr 'dilations' not in Op 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"];
NodeDef: conv1/convolution = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], padding="VALID",
strides=[1, 2, 2, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"]
(Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).
[[Node: conv1/convolution = Conv2D[T=DT_FLOAT, data_format="NHWC",
dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 2, 2, 1], use_cudnn_on_gpu=true,
We have seen issues in the past when converting Keras models due to unsupported layers but this error looks different. Could you provide me a link of the model you are trying to convert as well as the commands used?
Also, which version of the ncsdk are you using?
Thank you for replying!! This is my model and also the code I generate it. https://drive.google.com/drive/folders/1ubF1ODT124XAPVLq1tNfTsNlHzpVd5zg?usp=sharing
I am using ncsdk 1
I apologize for the delay in my response. I was not able to convert your model using the NCSDK. Have you tried to convert the Keras model using the OpenVINO toolkit?