cloudml_predict error using vgg16
Opened this issue · 0 comments
Hi,
I succesfully managed to complete the example from the Deploying Model section. However when I tried it on my own model it failed.
My own model in this case is the example on page 140 (Feature Extraction with Data Augmentation) from the Deep Learning with R book. I followed the example to the letter and added export_savedmodel
to the end of the script. Calling cloudml_deploy
works and the model succesfully gets deployed. Unfortunately using another image with cloudml_predict
throws the following error:
Error in cloudml_predict(list(img), name = "hd") :
Prediction failed: Error during model execution: AbortionError(code=StatusCode.INVALID_ARGUMENT, details="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: vgg16_1/block1_conv1/convolution = Conv2D[T=DT_FLOAT, _output_shapes=[[?,150,150,64]], data_format="NHWC", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_vgg16_input_1_0_0, block1_conv1_1/kernel/read). (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).
[[Node: vgg16_1/block1_conv1/convolution = Conv2D[T=DT_FLOAT, _output_shapes=[[?,150,150,64]], data_format="NHWC", dilations=[1, 1, 1, 1], padding="SAME
I can't really decipher this error message so any help is appreciated.