如何在java中读取tensorflow模型的输出

Question

    interpreter.run(input, output);

Answer 1

>>> import tensorflow as tf
>>> interpreter = tf.contrib.lite.Interpreter("detect.tflite")

>>> interpreter.allocate_tensors()
>>> input_details = interpreter.get_input_details()
>>> output_details = interpreter.get_output_details()

>>> input_details
[{'name': 'normalized_input_image_tensor', 'index': 308, 'shape': array([  1, 300, 300,   3], dtype=int32), 'dtype': <class 'numpy.float32'>, 'quantization': (0.0, 0)}]

>>> output_details
[{'name': 'TFLite_Detection_PostProcess', 'index': 300, 'shape': array([ 1, 10,  4], dtype=int32), 'dtype': <class 'numpy.float32'>, 'quantization': (0.0, 0)}, {'name': 'TFLite_Detection_PostProcess:1', 'index': 301, 'shape': array([ 1, 10], dtype=int32), 'dtype': <class 'numpy.float32'>, 'quantization': (0.0, 0)}, {'name': 'TFLite_Detection_PostProcess:2', 'index': 302, 'shape': array([ 1, 10], dtype=int32), 'dtype': <class 'numpy.float32'>, 'quantization': (0.0, 0)}, {'name': 'TFLite_Detection_PostProcess:3', 'index': 303, 'shape': array([1], dtype=int32), 'dtype': <class 'numpy.float32'>, 'quantization': (0.0, 0)}]

interpreter.run(input, output) 

interpreter.runForMultipleInputsOutputs(inputs, map_of_indices_to_outputs);

private Object[1] inputs;
inputs[0] = imgData; //imgData - image converted to bytebuffer 

private Map<Integer, Object> output_map = new TreeMap<>();
private float[1][10][4] boxes;
private float[1][10] scores;
private float[1][10] classes;
output_map.put(0, boxes);
output_map.put(1, classes);
output_map.put(2, scores);