我正在尝试使用TensorFlow中的kNN算法计算给定地址的最佳匹配，效果很好，但是当我尝试导出模型并在Java环境中使用它时，我陷入了困境从Java提供稀疏的Placholder。
这是python部分的简化版本，它返回测试名称和最佳引用名称之间的最小距离。到目前为止，这项工作符合预期。当我导出模型并将其导入Java程序时，它总是返回相同的值（默认为占位符的距离）。我假设python函数sparse_from_word_vec(word_vec)不在模型中，这对我完全有意义，但是那我应该怎么做这个稀疏张量呢？我的输入是单个字符串，我需要创建一个合适的稀疏张量（值）来计算距离。我还寻找了一种在Java端生成稀疏张量的方法，但没有成功。
import tensorflow as tf
import pandas as pd
d = {'NAME': ['max mustermann',
'erika musterfrau',
'joseph haydn',
'johann sebastian bach',
'wolfgang amadeus mozart']}
df = pd.DataFrame(data=d)
input_name = tf.placeholder_with_default('max musterman',(), name='input_name')
output_dist = tf.placeholder(tf.float32, (), name='output_dist')
test_name = tf.sparse_placeholder(dtype=tf.string)
ref_names = tf.sparse_placeholder(dtype=tf.string)
output_dist = tf.edit_distance(test_name, ref_names, normalize=True)
def sparse_from_word_vec(word_vec):
num_words = len(word_vec)
indices = [[xi, 0, yi] for xi,x in enumerate(word_vec) for yi,y in enumerate(x)]
chars = list(''.join(word_vec))
return(tf.SparseTensorValue(indices, chars, [num_words,1,1]))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
t_data_names=tf.constant(df['NAME'])
reference_names = [el.decode('UTF-8') for el in (t_data_names.eval())]
sparse_ref_names = sparse_from_word_vec(reference_names)
sparse_test_name = sparse_from_word_vec([str(input_name.eval().decode('utf-8'))]*5)
feeddict={test_name: sparse_test_name,
ref_names: sparse_ref_names,
}
output_dist = sess.run(output_dist, feed_dict=feeddict)
output_dist = tf.reduce_min(output_dist, 0)
print(output_dist.eval())
tf.saved_model.simple_save(sess,
"model-simple",
inputs={"input_name": input_name},
outputs={"output_dist": output_dist})
这是我的Java方法：
public void run(ApplicationArguments args) throws Exception {
log.info("Loading model...");
SavedModelBundle savedModelBundle = SavedModelBundle.load("/model", "serve");
byte[] test_name = "Max Mustermann".toLowerCase().getBytes("UTF-8");
List<Tensor<?>> output = savedModelBundle.session().runner()
.feed("input_name", Tensor.<String>create(test_names))
.fetch("output_dist")
.run();
System.out.printl("Nearest distance: " + output.get(0).floatValue());
}
答案 0 :(得分：1)
我能够使您的示例正常工作。在深入之前，我对您的python代码有一些评论。
在整个代码中，变量output_dist用于3种不同的值类型。我不是python专家，但是我认为这是不好的做法。您实际上也永远不会使用input_name占位符，除非将其导出为输入。最后一个是tf.saved_model.simple_save已过时，您应该改用tf.saved_model.Builder。
现在解决。
使用命令libtensorflow查看jar tvf libtensorflow-x.x.x.jar jar文件（感谢this发布），您会发现没有用于创建稀疏张量的有用绑定（也许功能要求？）。因此，我们必须将输入更改为密集的张量，然后向图形添加操作以将其转换为稀疏。在您的原始代码中，稀疏转换位于python端，这意味着Java中加载的图形没有任何操作。
这是新的python代码：
import tensorflow as tf
import pandas as pd
def model():
#use dense tensors then convert to sparse for edit_distance
test_name = tf.placeholder(shape=(None, None), dtype=tf.string, name="test_name")
ref_names = tf.placeholder(shape=(None, None), dtype=tf.string, name="ref_names")
#Java Does not play well with the empty character so use "/" instead
test_name_sparse = tf.contrib.layers.dense_to_sparse(test_name, "/")
ref_names_sparse = tf.contrib.layers.dense_to_sparse(ref_names, "/")
output_dist = tf.edit_distance(test_name_sparse, ref_names_sparse, normalize=True)
#output the index to the closest ref name
min_idx = tf.argmin(output_dist)
return test_name, ref_names, min_idx
#Python code to be replicated in Java
def pad_string(s, max_len):
return s + ["/"] * (max_len - len(s))
d = {'NAME': ['joseph haydn',
'max mustermann',
'erika musterfrau',
'johann sebastian bach',
'wolfgang amadeus mozart']}
df = pd.DataFrame(data=d)
input_name = 'max musterman'
#pad dense tensor input
max_len = max([len(n) for n in df['NAME']])
test_input = [list(input_name)]*len(df['NAME'])
#no need to pad, all same length
ref_input = list(map(lambda x: pad_string(x, max_len), [list(n) for n in df['NAME']]))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
test_name, ref_names, min_idx = model()
#run a test to make sure the model works
feeddict = {test_name: test_input,
ref_names: ref_input,
}
out = sess.run(min_idx, feed_dict=feeddict)
print("test output:", out)
#save the model with the new Builder API
signature_def_map= {
"predict": tf.saved_model.signature_def_utils.predict_signature_def(
inputs= {"test_name": test_name, "ref_names": ref_names},
outputs= {"min_idx": min_idx})
}
builder = tf.saved_model.Builder("model")
builder.add_meta_graph_and_variables(sess, ["serve"], signature_def_map=signature_def_map)
builder.save()
这是要加载并运行它的Java。这里可能还有很多改进的余地（java不是我的主要语言），但这可以为您带来想法。
import org.tensorflow.Graph;
import org.tensorflow.Session;
import org.tensorflow.Tensor;
import org.tensorflow.TensorFlow;
import org.tensorflow.SavedModelBundle;
import java.util.ArrayList;
import java.util.List;
import java.util.Arrays;
public class Test {
public static byte[][] makeTensor(String s, int padding) throws Exception
{
int len = s.length();
int extra = padding - len;
byte[][] ret = new byte[len + extra][];
for (int i = 0; i < len; i++) {
String cur = "" + s.charAt(i);
byte[] cur_b = cur.getBytes("UTF-8");
ret[i] = cur_b;
}
for (int i = 0; i < extra; i++) {
byte[] cur = "/".getBytes("UTF-8");
ret[len + i] = cur;
}
return ret;
}
public static byte[][][] makeTensor(List<String> l, int padding) throws Exception
{
byte[][][] ret = new byte[l.size()][][];
for (int i = 0; i < l.size(); i++) {
ret[i] = makeTensor(l.get(i), padding);
}
return ret;
}
public static void main(String[] args) throws Exception {
System.out.println("Loading model...");
SavedModelBundle savedModelBundle = SavedModelBundle.load("model", "serve");
List<String> str_test_name = Arrays.asList("Max Mustermann",
"Max Mustermann",
"Max Mustermann",
"Max Mustermann",
"Max Mustermann");
List<String> names = Arrays.asList("joseph haydn",
"max mustermann",
"erika musterfrau",
"johann sebastian bach",
"wolfgang amadeus mozart");
//get the max length for each array
int pad1 = str_test_name.get(0).length();
int pad2 = 0;
for (String var : names) {
if(var.length() > pad2)
pad2 = var.length();
}
byte[][][] test_name = makeTensor(str_test_name, pad1);
byte[][][] ref_names = makeTensor(names, pad2);
//use a with block so the close method is called
try(Tensor t_test_name = Tensor.<String>create(test_name))
{
try (Tensor t_ref_names = Tensor.<String>create(ref_names))
{
List<Tensor<?>> output = savedModelBundle.session().runner()
.feed("test_name", t_test_name)
.feed("ref_names", t_ref_names)
.fetch("ArgMin")
.run();
System.out.println("Nearest distance: " + output.get(0).longValue());
}
}
}
}