1

I have a problem with running my trained yolov2 network on android. I am using this project for my testing https://github.com/szaza/android-yolo-v2.

The provided network is working just fine. The problem only exists with my trained network. I converted my yolov2.weights file to a pb file using darkflow. I tried to find information on the type of error I am facing but my understanding of the inner workings of TensorFlow are too little to get what is happening.

It looks like the frozen graph is loading properly:

I/TensorFlowInferenceInterface: Successfully loaded model from 'file:///android_asset/yolov2_finderpatterns.pb'

So I guess TensorFlow has problems with something else maybe someone can explain to me what this error means:

E/TensorFlowInferenceInterface: Failed to run TensorFlow inference with inputs:[input], outputs:[output]
E/AndroidRuntime: FATAL EXCEPTION: inference
Process: org.tensorflow.yolo, PID: 16974
java.lang.IllegalArgumentException: No OpKernel was registered to support Op 'ExtractImagePatches' with these attrs.  Registered devices: [CPU], Registered kernels:
  <no registered kernels>

     [[{{node ExtractImagePatches}} = ExtractImagePatches[T=DT_FLOAT, ksizes=[1, 2, 2, 1], padding="VALID", rates=[1, 1, 1, 1], strides=[1, 2, 2, 1]](47-leaky)]]

1 Answer 1

1

There is an issue in tensorflow repository, with a solution , please see this issue

Sign up to request clarification or add additional context in comments.

Comments

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.