素材

from：

https://jalammar.github.io/Supercharging-android-apps-using-tensorflow/

1. On startup, the app launches an Android activity (CameraActivity.java) which then starts a fragment (CameraConnectionFragment.java)
2. The fragment does some setup to basically start the camera and feed the incoming stream of images to an object it instantiates (TensorflowImageListener.java)
3. The listener consults the classifier (TensorflowClassifier.java) about each image it gets, and receives the classification and confidence score for each image.

转载于:https://my.oschina.net/hounLeft/blog/728133