我有一個(gè)保存的模型，我設(shè)法加載，運(yùn)行并獲得1行9個(gè)特征的預(yù)測(cè)。（輸入）現(xiàn)在我試圖預(yù)測(cè)100行這樣的行，但是當(dāng)嘗試從Tensor.copyTo（）讀取結(jié)果數(shù)組時(shí)，我得到了不兼容的形狀java.lang.IllegalArgumentException: cannot copy Tensor with shape [1, 1] into object with shape [100, 1]顯然，我設(shè)法在循環(huán)中運(yùn)行了這個(gè)預(yù)測(cè) - 但這比一次運(yùn)行100的等效python執(zhí)行慢20倍。這里是 /saved_model_cli.py 報(bào)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問題是 - 我是否需要為我想預(yù)測(cè)的每一行運(yùn)行（），就像這里的問題一樣
1 回答
catspeake
TA貢獻(xiàn)1111條經(jīng)驗(yàn) 獲得超0個(gè)贊
好吧，所以我發(fā)現(xiàn)了一個(gè)問題，我無法為我想要的所有行（預(yù)測(cè)）運(yùn)行一次。可能是一個(gè)張量流新手問題，我搞砸了輸入和輸出矩陣。當(dāng)報(bào)告工具（python）說你有一個(gè)形狀（-1，9）的輸入張量映射到j(luò)ava long[]{1，9}時(shí)，這并不意味著你不能傳遞long[]{1000，9}的輸入張量 - 這意味著1000行用于預(yù)測(cè)。在此輸入之后，定義為 [1，1] 的輸出張量可以是 [1000，1]。
這個(gè)代碼實(shí)際上比python運(yùn)行得快得多（1.2秒對(duì)7秒），這是代碼（也許會(huì)解釋得更好）
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]);
}
}
}
添加回答
舉報(bào)
0/150
提交
取消