CODEWITHSUNDEEP
androidpythonc++tensorflow
abd0
abd0

Reputation: 11

Running own TensorFlow model on Android gives native inference error: "Session was not created with a graph before Run()!"

I was able to run the Inception-v3 model on Android just fine, and I now want to run my own trained TensorFlow model on Android. I'm following the approach from TensorFlow's image recognition tutorial and the Android TensorFlow demo, and adapting as necessary. From Android logcat, running into this when running the app:

E/native: tensorflow_inference_jni.cc:202 Error during inference: Invalid argument: Session was not created with a graph before Run()!
...
E/native: tensorflow_inference_jni.cc:159 Output [output/Softmax:0] not found, aborting!

Environment info: OS X Yosemite (10.10.5), LGE Nexus 5 (Android 6.0.1), Android SDK 23, Android OpenCV SDK 23, Bazel 0.4.0.

These are the steps I've taken so far:

  1. Saved own model's checkpoint (.ckpt) and graph definition (.pb) files separately using tf.train.Saver() then tf.train.write_graph()
  2. Froze graph using freeze_graph.py (using bazel), gives 227.5 MB file
  3. Optimized the graph using optimize_for_inference.py (additionally tried strip_unused.py)
  4. Copied frozen, optimized, or stripped graph to android/assets
  5. Doubled the total byte limit using coded_stream.SetTotalBytesLimit() in jni_utils.cc to handle my large model size
  6. Built the tensorflow android app using bazel
  7. Installed on android device using adb and bazel

As a sanity check, I have tested my model in C++ built with bazel following the tutorial here label_image, and my model correctly outputs a prediction. I have also tried playing with the order by which I save my graph def and checkpoint files before freezing, but no change.

Any help would be great.

Upvotes: 1

Views: 1187

Answers (1)

abd0
abd0

Reputation: 11

This has been resolved (GitHub issue link here).

Steps taken: full sync with then latest tf build (last commit: 798ae42) and built using bazel -v 0.4.3-homebrew. Android SDK v23 and NDK v23. Stripped off all preprocessing (i.e., removing OpenCV from build), and just replaced out of box tf inception demo with own model and label file. Logcat now shows:

01-06 10:27:39.048 26344-26344/? I/TensorFlowImageClassifier: Reading labels from: mylabels.txt 
01-06 10:27:39.049 26344-26344/? I/TensorFlowImageClassifier: Read 7, 7 specified 
01-06 10:27:39.049 26344-26344/? I/native: tensorflow_inference_jni.cc:97 Native TF methods loaded. 
01-06 10:27:39.049 26344-26344/? I/TensorFlowInferenceInterface: Native methods already loaded. 
01-06 10:27:39.049 26344-26344/? I/native: tensorflow_inference_jni.cc:85 Creating new session variables for 25a68072eeb0d05 
01-06 10:27:39.049 26344-26344/? I/native: tensorflow_inference_jni.cc:113 Loading Tensorflow. 
01-06 10:27:39.053 26344-26344/? I/native: tensorflow_inference_jni.cc:120 Session created. 
01-06 10:27:39.053 26344-26344/? I/native: tensorflow_inference_jni.cc:126 Acquired AssetManager. 
01-06 10:27:39.053 26344-26344/? I/native: tensorflow_inference_jni.cc:128 Reading file to proto: file:///android_asset/cnn_frozen_graph.pb 
01-06 10:27:39.680 26344-26344/? I/native: tensorflow_inference_jni.cc:132 GraphDef loaded from file:///android_asset/cnn_frozen_graph.pb with 40 nodes. 
01-06 10:27:39.680 26344-26344/? I/native: stat_summarizer.cc:38 StatSummarizer found 40 nodes 
01-06 10:27:39.680 26344-26344/? I/native: tensorflow_inference_jni.cc:139 Creating TensorFlow graph from GraphDef. 
01-06 10:27:39.713 26344-26344/org.tensorflow.demo I/native: tensorflow_inference_jni.cc:151 Initialization done in 664.038ms 
01-06 10:27:39.714 26344-26344/org.tensorflow.demo I/tensorflow: ClassifierActivity: Sensor orientation: 90, Screen orientation: 0 
01-06 10:27:39.714 26344-26344/org.tensorflow.demo I/tensorflow: ClassifierActivity: Initializing at size 640x480

Upvotes: 0

Related Questions