Support all architectures by using pre-packaged dependency

I’ve copied the approach used by the Android Things sample app:
https://github.com/androidthings/sample-tensorflow-imageclassifier

This dependency downloads an AAR file which includes native binaries for all architectures, along with a Java interface (TensorFlowInferenceInterface) than can be used  to interface with TensorFlow model without needing to write any JNI code!  Documentation:
https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/android

TESTING

Before these changes, I could not install the app on my Android 7.0 x86 emulator.  It failed with this message:
`Failure [INSTALL_FAILED_NO_MATCHING_ABIS: Failed to extract native libraries, res=-113]`

After the change, I was successfully able to launch the app and Detect digits. :-)

Author: daj

app/build.gradle

@@ -42,5 +42,5 @@ dependencies {
     })
     compile 'com.android.support:appcompat-v7:25.2.0'
     testCompile 'junit:junit:4.12'
-    compile files('libs/libandroid_tensorflow_inference_java.jar')
+    compile 'org.tensorflow:tensorflow-android:1.2.0'
 }

app/libs/libandroid_tensorflow_inference_java.jar

@@ -16,13 +16,6 @@
 
 package com.mindorks.tensorflowexample;
 
-import android.content.res.AssetManager;
-import android.os.Trace;
-import android.support.v4.os.TraceCompat;
-import android.util.Log;
-
-import org.tensorflow.contrib.android.TensorFlowInferenceInterface;
-
 import java.io.BufferedReader;
 import java.io.IOException;
 import java.io.InputStreamReader;
@@ -32,6 +25,12 @@
 import java.util.PriorityQueue;
 import java.util.Vector;
 
+import org.tensorflow.contrib.android.TensorFlowInferenceInterface;
+
+import android.content.res.AssetManager;
+import android.support.v4.os.TraceCompat;
+import android.util.Log;
+
 /**
  * Created by amitshekhar on 16/03/17.
  */
@@ -59,6 +58,8 @@ public class TensorFlowImageClassifier implements Classifier {
 
     private TensorFlowInferenceInterface inferenceInterface;
 
+    private boolean runStats = false;
+
     private TensorFlowImageClassifier() {
     }
 
@@ -97,10 +98,8 @@ public static Classifier create(
         }
         br.close();
 
-        c.inferenceInterface = new TensorFlowInferenceInterface();
-        if (c.inferenceInterface.initializeTensorFlow(assetManager, modelFilename) != 0) {
-            throw new RuntimeException("TF initialization failed");
-        }
+        c.inferenceInterface = new TensorFlowInferenceInterface(assetManager, modelFilename);
+
         // The shape of the output is [N, NUM_CLASSES], where N is the batch size.
         int numClasses =
                 (int) c.inferenceInterface.graph().operation(outputName).output(0).shape().size(1);
@@ -124,19 +123,18 @@ public List<Recognition> recognizeImage(final float[] pixels) {
         TraceCompat.beginSection("recognizeImage");
 
         // Copy the input data into TensorFlow.
-        TraceCompat.beginSection("fillNodeFloat");
-        inferenceInterface.fillNodeFloat(
-                inputName, new int[]{inputSize * inputSize}, pixels);
+        TraceCompat.beginSection("feed");
+        inferenceInterface.feed(inputName, pixels, new long[]{inputSize * inputSize});
         TraceCompat.endSection();
 
         // Run the inference call.
-        TraceCompat.beginSection("runInference");
-        inferenceInterface.runInference(outputNames);
+        TraceCompat.beginSection("run");
+        inferenceInterface.run(outputNames, runStats);
         TraceCompat.endSection();
 
         // Copy the output Tensor back into the output array.
-        TraceCompat.beginSection("readNodeFloat");
-        inferenceInterface.readNodeFloat(outputName, outputs);
+        TraceCompat.beginSection("fetch");
+        inferenceInterface.fetch(outputName, outputs);
         TraceCompat.endSection();
 
         // Find the best classifications.
@@ -168,7 +166,7 @@ public int compare(Recognition lhs, Recognition rhs) {
 
     @Override
     public void enableStatLogging(boolean debug) {
-        inferenceInterface.enableStatLogging(debug);
+        runStats = debug;
     }
 
     @Override