Skip to content

Instantly share code, notes, and snippets.

@nodamu

nodamu/ImageClassifier.java

Last active April 2, 2019 11:12
Show Gist options
  • Save nodamu/3dac072ae3336e14c59997c745cb60f8 to your computer and use it in GitHub Desktop.
Save nodamu/3dac072ae3336e14c59997c745cb60f8 to your computer and use it in GitHub Desktop.
Download ZIP
This is where the classification happens. The image has to converted to bytebuffer before passing to the model
Raw
ImageClassifier.java
/** Writes Image data into a {@code ByteBuffer}. */
private void convertBitmapToByteBuffer(Bitmap bitmap) {
if (imgData == null) {
return;
}
imgData.rewind();
bitmap.getPixels(intValues, 0, bitmap.getWidth(), 0, 0, bitmap.getWidth(), bitmap.getHeight());
// Convert the image to floating point.
int pixel = 0;
long startTime = SystemClock.uptimeMillis();
for (int i = 0; i < getImageSizeX(); ++i) {
for (int j = 0; j < getImageSizeY(); ++j) {
final int val = intValues[pixel++];
addPixelValue(val);
}
}
long endTime = SystemClock.uptimeMillis();
Log.d(TAG, "Timecost to put values into ByteBuffer: " + Long.toString(endTime - startTime));
}
void classifyFrame(Bitmap bitmap, SpannableStringBuilder builder) {
if (tflite == null) {
Log.e(TAG, "Image classifier has not been initialized; Skipped.");
builder.append(new SpannableString("Uninitialized Classifier."));
}
convertBitmapToByteBuffer(bitmap);
// Here's where the magic happens!!!
long startTime = SystemClock.uptimeMillis();
runInference();
long endTime = SystemClock.uptimeMillis();
Log.d(TAG, "Timecost to run model inference: " + Long.toString(endTime - startTime));
// Smooth the results across frames.
applyFilter();
// Print the results.
printTopKLabels(builder);
long duration = endTime - startTime;
SpannableString span = new SpannableString(duration + " ms");
span.setSpan(new ForegroundColorSpan(android.graphics.Color.LTGRAY), 0, span.length(), 0);
builder.append(span);
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment