在java中提供TensorFlow - 在一个会话中运行多个预测

Question

我有一个保存的模型，我设法加载，运行和预测1行9个功能。 （输入）现在我试图预测这样的100行，但是当试图将结果从Tensor.copyTo（）读取到结果数组时，我得到了不兼容的形状

java.lang.IllegalArgumentException: cannot copy Tensor with shape [1, 1] into object with shape [100, 1]

显然我设法在循环中运行这一个预测 - 但这比一次运行中100的等效python执行慢20倍。

这是/saved_model_cli.py报告的已保存模型信息

MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:

signature_def['serving_default']:
  The given SavedModel SignatureDef contains the following input(s):
    inputs['input'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 9)
        name: dense_1_input:0
  The given SavedModel SignatureDef contains the following output(s):
    outputs['output'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 1)
        name: dense_4/BiasAdd:0
  Method name is: tensorflow/serving/predict

问题是 - 我需要运行（）我想要预测的每一行，如问题here

Answer 1

好的，所以我发现问题我不能为我想要的所有行（预测）运行一次。可能是一个张量流新手问题，我搞砸了输入和输出矩阵。当报表工具（python）说你有一个输入Tensor with shape（-1,9）映射到java long [] {1,9}时，它并不意味着你不能传递输入为long [] {1000,9 - 这意味着1000行用于预测。在此输入之后，定义为[1,1]的输出张量可以是[1000,1]。

这段代码实际运行速度比python快（1.2秒vs 7秒）这里是代码（可能会解释得更好）

public Tensor prepareData(){
    Random r = new Random();
    float[]inputArr = new float[NUMBER_OF_KEWORDS*NUMBER_OF_FIELDS];
    for (int i=0;i<NUMBER_OF_KEWORDS * NUMBER_OF_FIELDS;i++){
        inputArr[i] = r.nextFloat();
    }

    FloatBuffer inputBuff = FloatBuffer.wrap(inputArr, 0, NUMBER_OF_KEWORDS*NUMBER_OF_FIELDS);
    return Tensor.create(new long[]{NUMBER_OF_KEWORDS,NUMBER_OF_FIELDS}, inputBuff);
}

public void predict (Tensor inputTensor){
    try ( Session s = savedModelBundle.session()) {
        Tensor result;
        long globalStart = System.nanoTime();
            result = s.runner().feed("dense_1_input", inputTensor).fetch("dense_4/BiasAdd").run().get(0);

            final long[] rshape = result.shape();
            if (result.numDimensions() != 2 || rshape[0] <= NUMBER_OF_KEWORDS) {
                throw new RuntimeException(
                        String.format(
                                "Expected model to produce a [N,1] shaped tensor where N is the number of labels, instead it produced one with shape %s",
                                Arrays.toString(rshape)));
            }


        float[][] resultArray = (float[][]) result.copyTo(new float[NUMBER_OF_KEWORDS][1]);
        System.out.println(String.format("Total of %d,  took : %.4f ms", NUMBER_OF_KEWORDS, ((double) System.nanoTime() - globalStart) / 1000000));
        for (int i=0;i<10;i++){
            System.out.println(resultArray[i][0]);
        }
    }
}