Open ksipma opened 6 years ago
Have you ever resolved this? Currently have the same problem.
Unfortunatly i did not
How about now? Currently have the same problem too...
+1 on this. Stuck here. Is there any workaround?
Yes there is. Stop trying with this package. This project just doesn't work. I finally got around by using keras and kerassharp.
Thanks @klaas3 . I've trained the model in tensorflow though. @migueldeicaza Is there a solution to this? The examples shown are only for image classifiers and detectors. Would be good if you could show how to use DNN classifiers with your library.
Also stuck here, the last step to be resolved for my model to run. Any news on this issue?
OMG, just one year past, is there any solutions?
Same problem here. Anyone ?
I posted an answer to this on StackOverflow -- maybe this still helps someone.
I want to be able to use the dnnclassifier (estimator) on top of IIS, which has previously been trained in python. I got so far that I can now generate PB files, know the correct input/outputs, however I am stuck in tensorflowsharp using string inputs.
I can create a valid .pb file of the iris dataset (attached). It uses the following feate_spec:
I have created a simple c# console to try and spin it up. The input should be an "input_example_tensor" and the output is located in "dnn/head/predictions/probabilities". This I discoved after alex_zu provided help using the saved_model_cli command here.
As far as I am aware all tensorflow estimator API's work like this.
Here comes the problem: the input_example_tensor should be of a string format which will be parsed internally by the ParseExample function. Now i am stuck. I have found TFTensor.CreateString, but this doesn't solve the problem.
This example will give the following error:
How can I serialize tensors in such a way that i can use the pb file correctly?
Attached is the python iris example ,pb file and the console application program. pbfile and python.zip
I also posted it on stackoverflow
In my opinion solving this creates a neat solution for all tensorflow users having ancient production environments (like me).