I'm doing my first steps with tensorflow. After having created a simple model for MNIST data in Python, I now want to import this model into Java and use it for classification. However, I don't manage to pass the input data to the model.
Here is the Python code for model creation:
from tensorflow.keras.datasets import mnist
from tensorflow.keras.utils import to_categorical.
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images.astype('float32')
train_images /= 255
test_images = test_images.reshape((10000, 28, 28, 1))
test_images = test_images.astype('float32')
test_images /= 255
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)
NrTrainimages = train_images.shape[0]
NrTestimages = test_images.shape[0]
import os
import numpy as np
from tensorflow.keras.callbacks import TensorBoard
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D
from tensorflow.keras import backend as K
# Network architecture
model = Sequential()
mnist_inputshape = train_images.shape[1:4]
# Convolutional block 1
model.add(Conv2D(32, kernel_size=(5,5),
activation = 'relu',
input_shape=mnist_inputshape,
name = 'Input_Layer'))
model.add(MaxPooling2D(pool_size=(2,2)))
# Convolutional block 2
model.add(Conv2D(64, kernel_size=(5,5),activation= 'relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.5))
# Prediction block
model.add(Flatten())
model.add(Dense(128, activation='relu', name='features'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dense(10, activation='softmax', name = 'Output_Layer'))
model.compile(loss='categorical_crossentropy',
optimizer='Adam',
metrics=['accuracy'])
LOGDIR = "logs"
my_tensorboard = TensorBoard(log_dir = LOGDIR,
histogram_freq=0,
write_graph=True,
write_images=True)
my_batch_size = 128
my_num_classes = 10
my_epochs = 5
history = model.fit(train_images, train_labels,
batch_size=my_batch_size,
callbacks=[my_tensorboard],
epochs=my_epochs,
use_multiprocessing=False,
verbose=1,
validation_data=(test_images, test_labels))
score = model.evaluate(test_images, test_labels)
modeldir = 'models'
model.save(modeldir, save_format = 'tf')
For Java, I am trying to adapt the App.java code published here.
I am struggling with replacing this snippet:
Tensor result = s.runner()
.feed("input_tensor", inputTensor)
.feed("dropout/keep_prob", keep_prob)
.fetch("output_tensor")
.run().get(0);
While in this code, a particular input tensor is used to pass the data, in my model, there are only layers and no individual named tensors. Thus, the following doesn't work:
Tensor<?> result = s.runner()
.feed("Input_Layer/kernel", inputTensor)
.fetch("Output_Layer/kernel")
.run().get(0);
How do I pass the data to and get the output from my model in Java?
With the newest version of TensorFlow Java, you don't need to search for yourself the name of the input/output tensors from the model signature or from the graph. You can simply call the following:
try (SavedModelBundle model = SavedModelBundle.load("./model", "serve");
Tensor<TFloat32> image = TFloat32.tensorOf(...); // There a many ways to pass you image bytes here
Tensor<TFloat32> result = model.call(image).expect(TFloat32.DTYPE)) {
System.out.println("Result is " + result.data().getFloat());
}
}
TensorFlow Java will automatically take care of mapping your input/output tensors to the right nodes.
I finally managed to find a solution. To get all the tensor names in the graph, I used the following code:
for (Iterator it = smb.graph().operations(); it.hasNext();) {
Operation op = (Operation) it.next();
System.out.println("Operation name: " + op.name());
}
From this, I figured out that the following works:
SavedModelBundle smb = SavedModelBundle.load("./model", "serve");
Session s = smb.session();
Tensor<Float> inputTensor = Tensor.<Float>create(imagesArray, Float.class);
Tensor<Float> result = s.runner()
.feed("serving_default_Input_Layer_input", inputTensor)
.fetch("StatefulPartitionedCall")
.run().get(0).expect(Float.class);
I have been trying to build a CNN model using dl4j, but it is giving me an error. The code:
RecordReader rr;
rr = new CSVRecordReader();
rr.initialize(new FileSplit(new File(dataLocalPath, nameTrain)));
DataSetIterator trainIter = new RecordReaderDataSetIterator(rr, batchSize, 0, 2);
MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().seed(123).updater(new Adam(0.1))
.list()
.layer(0,new Convolution1DLayer.Builder().kernelSize(3).padding(1).nIn(371).nOut(64).build())
.layer(1,new Subsampling1DLayer.Builder().kernelSize(3).padding(1).build())
.layer(2,new Convolution1DLayer.Builder().kernelSize(3).activation(Activation.RELU).padding(1).nIn(64)
.nOut(32).build())
.layer(3,new Subsampling1DLayer.Builder().kernelSize(3).padding(1).build())
.layer(4,new DenseLayer.Builder().activation(Activation.RELU).nIn(32).nOut(16).build())
.layer(5,new OutputLayer.Builder(LossFunction.RECONSTRUCTION_CROSSENTROPY).activation(Activation.SIGMOID)
.nIn(16).nOut(2).build())
.build();
MultiLayerNetwork model = new MultiLayerNetwork(conf);
model.init();
model.setListeners(new ScoreIterationListener(10));
final DataSet trainData = trainIter.next();
INDArray a = trainData.getFeatures();
final INDArray b = trainData.getLabels();
a = a.reshape(new int[] { (int) a.size(0), (int) a.size(1), 1 });
model.fit(a, b);
Added the error below,
Exception in thread "main" org.deeplearning4j.exception.DL4JInvalidInputException: Input that is not a matrix; expected matrix (rank 2), got rank 3 array with shape [128, 32, 1]. Missing preprocessor or wrong input type? (layer name: layer4, layer index: 4, layer type: DenseLayer)
at org.deeplearning4j.nn.layers.BaseLayer.preOutputWithPreNorm(BaseLayer.java:306)
at org.deeplearning4j.nn.layers.BaseLayer.preOutput(BaseLayer.java:289)
at org.deeplearning4j.nn.layers.BaseLayer.activate(BaseLayer.java:337)
at org.deeplearning4j.nn.layers.AbstractLayer.activate(AbstractLayer.java:257)
at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.ffToLayerActivationsInWs(MultiLayerNetwork.java:1129)
at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.computeGradientAndScore(MultiLayerNetwork.java:2741)
at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.computeGradientAndScore(MultiLayerNetwork.java:2699)
at org.deeplearning4j.optimize.solvers.BaseOptimizer.gradientAndScore(BaseOptimizer.java:170)
at org.deeplearning4j.optimize.solvers.StochasticGradientDescent.optimize(StochasticGradientDescent.java:63)
at org.deeplearning4j.optimize.Solver.optimize(Solver.java:52)
at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.fitHelper(MultiLayerNetwork.java:2303)
at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.fit(MultiLayerNetwork.java:2261)
at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.fit(MultiLayerNetwork.java:2248)
at com.rssoftware.efrm.AnnModelFromKeras.trainModel(AnnModelFromKeras.java:73)
at com.rssoftware.efrm.AnnModelFromKeras.main(AnnModelFromKeras.java:89)
I have tried using input pre-processor, CNN to feed forward pre processor, but it is not working.
The expected input shape into a conv1d layer is [minibatchSize, convNIn, length] or [minibatchSize, featuresSize, sequenceLength] in terms of a time series. The reshape in your code sets your length to 1. Maybe you intended to set featuresize/convNIn to 1?
I want to predict on my trained Model from Python Tensorflow API with the Java API, but have problems to feed in the features to predict in Java.
My Python Code is like this:
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
from six.moves.urllib.request import urlopen
import numpy as np
import tensorflow as tf
feature_names = [
'Attribute1',
'Attribute2',
'Attribute3',
'Attribute4',
'Attribute5',
'Attribute6',
'Attribute7',
'Attribute8',
'Attribute9',
'Attribute10',
'Attribute11',
'Attribute12',
'Attribute13',
'Attribute14',
'Attribute15',
'Attribute16',
'Attribute17',
'Attribute18',
'Attribute19',
'Attribute20']
#prediction_input = np.array([['A11', 6, 'A34', 'A43', 1169, 'A65', 'A75', 4, 'A93', 'A101', 4, 'A121', 67, 'A143', 'A152', 2, 'A173', 1, 'A192', 'A201'],
# ['A12', 18, 'A34', 'A43', 1795, 'A61', 'A75', 3, 'A92', 'A103', 4, 'A121', 48, 'A141', 'A151', 2, 'A173', 1, 'A192', 'A201']])
prediction_input = [["A12 12 A32 A40 7472 A65 A71 1 A92 A101 2 A121 24 A143 A151 1 A171 1 A191 A201"],
["A11 36 A32 A40 9271 A61 A74 2 A93 A101 1 A123 24 A143 A152 1 A173 1 A192 A201"],
["A12 15 A30 A40 1778 A61 A72 2 A92 A101 1 A121 26 A143 A151 2 A171 1 A191 A201"]]
def predict_input_fn():
def decode(zeile):
parsed_line = tf.decode_csv(zeile, [[''], [0], [''], [''], [0], [''], [''], [0], [''], [''], [0], [''], [0], [''], [''], [0], [''], [0], [''], ['']], field_delim=' ')
#x = tf.split(x, 20) # Need to split into our 20 features
# When predicting, we don't need (or have) any labels
return dict(zip(feature_names, parsed_line)) # Then build a dict from them
# The from_tensor_slices function will use a memory structure as input
dataset = tf.data.Dataset.from_tensor_slices(prediction_input)
dataset = dataset.map(decode)
dataset = dataset.batch(1)
iterator = dataset.make_one_shot_iterator()
next_feature_batch = iterator.get_next()
return next_feature_batch, None # In prediction, we have no labels
# Data sets
def train_test_input_fn(dateipfad, mit_shuffle=False, anzahl_wiederholungen=1):
def parser(zeile):
parsed_line = tf.decode_csv(zeile, [[''], [0], [''], [''], [0], [''], [''], [0], [''], [''], [0], [''], [0], [''], [''], [0], [''], [0], [''], [''], [0]], field_delim=' ')
label = parsed_line[-1:] # Last element is the label
del parsed_line[-1] # Delete last element
features = parsed_line # Everything (but last element) are the features
d = dict(zip(feature_names, features)), label
return d
dataset = tf.data.TextLineDataset(dateipfad)
dataset = dataset.map(parser)
if mit_shuffle:
dataset = dataset.shuffle(buffer_size=100)
dataset = dataset.batch(1)
dataset = dataset.repeat(anzahl_wiederholungen)
iterator = dataset.make_one_shot_iterator()
# `features` is a dictionary in which each value is a batch of values for
# that feature; `labels` is a batch of labels.
batch_features, batch_labels = iterator.get_next()
return batch_features, batch_labels
def main():
feature_columns = [tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute1', ['A11', 'A12', 'A13', 'A14'])),
tf.feature_column.numeric_column('Attribute2', shape=[1]),
tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute3', ['A30', 'A31', 'A32', 'A33'])),
tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute4', ['A40', 'A41', 'A42', 'A43', 'A44', 'A45', 'A46', 'A47', 'A48', 'A49', 'A410'])),
tf.feature_column.numeric_column('Attribute5', shape=[1]),
tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute6', ['A61', 'A62', 'A63', 'A64', 'A65'])),
tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute7', ['A71', 'A72', 'A73', 'A74', 'A75'])),
tf.feature_column.numeric_column('Attribute8', shape=[1]),
tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute9', ['A91', 'A92', 'A93', 'A94', 'A95'])),
tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute10', ['A101', 'A102', 'A103'])),
tf.feature_column.numeric_column('Attribute11', shape=[1]),
tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute12', ['A121', 'A122', 'A123', 'A124'])),
tf.feature_column.numeric_column('Attribute13', shape=[1]),
tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute14', ['A141', 'A142', 'A143'])),
tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute15', ['A151', 'A152', 'A153'])),
tf.feature_column.numeric_column('Attribute16', shape=[1]),
tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute17', ['A171', 'A172', 'A173', 'A174'])),
tf.feature_column.numeric_column('Attribute18', shape=[1]),
tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute19', ['A191', 'A192'])),
tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('Attribute20', ['A201', 'A202']))]
classifier = tf.estimator.DNNClassifier(feature_columns=feature_columns,
hidden_units=[100],
n_classes=2,
model_dir="./summaries")
# Trainieren des Models
classifier.train(input_fn=lambda: train_test_input_fn("german.data.train.txt", True, 10))
# Errechne die Genauigkeit ("accuracy").
accuracy_score = classifier.evaluate(input_fn=lambda: train_test_input_fn("german.data.test.txt", False, 4))["accuracy"]
print("\nTest Genauigkeit: {0:f}\n".format(accuracy_score))
feature_spec = tf.feature_column.make_parse_example_spec(feature_columns)
serving_input_receiver_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(feature_spec)
classifier.export_savedmodel("./export" , serving_input_receiver_fn, as_text=True)
predict_results = classifier.predict(input_fn=predict_input_fn)
for idx, prediction in enumerate(predict_results):
type = prediction["class_ids"][0] # Get the predicted class (index)
if type == 0:
print("Ich denke: {}, ist nicht kreditwürdig".format(prediction_input[idx]))
elif type == 1:
print("Ich denke: {}, ist kreditwürdig".format(prediction_input[idx]))
if __name__ == "__main__":
main()
But I found nothing, how I can feed such categorical columns in Java Clients? Can you please provide a sample how I can make this?
My current state is something like this, but without any idea which Tensor I have to create, to predict on the trained model in Java:
public static void main(String[] args) throws Exception {
String pfad = System.getProperty("user.dir") + "\\1511523781";
Session session = SavedModelBundle.load(pfad, "serve").session();
String example = "A12 12 A32 A40 7472 A65 A71 1 A92 A101 2 A121 24 A143 A151 1 A171 1 A191 A201";
final String xName = "input_example_tensor";
final String scoresName = "dnn/head/predictions/probabilities:0";
List<Tensor<?>> outputs = session.runner()
.feed(xName, example)
.fetch(scoresName)
.run();
// Outer dimension is batch size; inner dimension is number of classes
float[][] scores = new float[2][3];
outputs.get(0).copyTo(scores);
System.out.println(Arrays.deepToString(scores));
}
Thanks!
Since you're using tf.estimator.export.build_parsing_serving_input_receiver_fn, the exported saved model you've created expects a serialized tf.Example protocol buffer as input.
You can use the tf.Example protocol buffer in Java (maven, javadoc), using something like this:
import com.google.protobuf.ByteString;
import java.util.Arrays;
import org.tensorflow.*;
import org.tensorflow.example.*;
public class Main {
// Returns a Feature containing a BytesList, where each element of the list
// is the UTF-8 encoded bytes of the Java string.
public static Feature feature(String... strings) {
BytesList.Builder b = BytesList.newBuilder();
for (String s : strings) {
b.addValue(ByteString.copyFromUtf8(s));
}
return Feature.newBuilder().setBytesList(b).build();
}
public static Feature feature(float... values) {
FloatList.Builder b = FloatList.newBuilder();
for (float v : values) {
b.addValue(v);
}
return Feature.newBuilder().setFloatList(b).build();
}
public static void main(String[] args) throws Exception {
Features features =
Features.newBuilder()
.putFeature("Attribute1", feature("A12"))
.putFeature("Attribute2", feature(12))
.putFeature("Attribute3", feature("A32"))
.putFeature("Attribute4", feature("A40"))
.putFeature("Attribute5", feature(7472))
.putFeature("Attribute6", feature("A65"))
.putFeature("Attribute7", feature("A71"))
.putFeature("Attribute8", feature(1))
.putFeature("Attribute9", feature("A92"))
.putFeature("Attribute10", feature("A101"))
.putFeature("Attribute11", feature(2))
.putFeature("Attribute12", feature("A121"))
.putFeature("Attribute13", feature(24))
.putFeature("Attribute14", feature("A143"))
.putFeature("Attribute15", feature("A151"))
.putFeature("Attribute16", feature(1))
.putFeature("Attribute17", feature("A171"))
.putFeature("Attribute18", feature(1))
.putFeature("Attribute19", feature("A191"))
.putFeature("Attribute20", feature("A201"))
.build();
Example example = Example.newBuilder().setFeatures(features).build();
String pfad = System.getProperty("user.dir") + "\\1511523781";
try (SavedModelBundle model = SavedModelBundle.load(pfad, "serve")) {
Session session = model.session();
final String xName = "input_example_tensor";
final String scoresName = "dnn/head/predictions/probabilities:0";
try (Tensor<String> inputBatch = Tensors.create(new byte[][] {example.toByteArray()});
Tensor<Float> output =
session
.runner()
.feed(xName, inputBatch)
.fetch(scoresName)
.run()
.get(0)
.expect(Float.class)) {
System.out.println(Arrays.deepToString(output.copyTo(new float[1][2])));
}
}
}
}
Much of the boilerplate here is to construct the protocol buffer example. Alternatively, you could use something other than build_arsing_serving_input_receiver_fn to setup the exported model to accept input in a different format.
Side note: You can use the saved_model_cli command-line tool that is included with TensorFlow Python installation to inspect the saved model. For example, something like:
saved_model_cli show \
--dir ./export/1511523781 \
--tag_set serve \
--signature_def predict
will show something like:
The given SavedModel SignatureDef contains the following input(s):
inputs['examples'] tensor_info:
dtype: DT_STRING
shape: (-1)
name: input_example_tensor:0
The given SavedModel SignatureDef contains the following output(s):
...
outputs['probabilities'] tensor_info:
dtype: DT_FLOAT
shape: (-1, 2)
name: dnn/head/predictions/probabilities:0
Suggesting that the saved model takes a single input - a batch of DT_STRING elements and the output probabilities are a batch of 2-dimensional float vectors.
Hope that helps.
I am working on a Uninformed search assignment but I am stuck.
http://i.stack.imgur.com/d4n18.png
I have 90% of it working, however I am trying to:
1) Load the data (cities and miles) from a .txt file instead of from the within the code.
2) Allow the program to take three command line input arguments: the input file name, origin city, and destination city
Example: findroute inputFilename originCity DestinationCity
Command line example: findroute input1.txt Munich Berlin
This is part of the code I have right now:
package graph;
import java.util.Formatter;
import java.util.List;
import bisearch.UniformCostSearch;
import search.Action;
public class findRoute {
/**
* finds the shortest path
*/
public static void main(final String[] args) {
Graph graph = findRoute.Map();
GraphStateSpaceSearchProblem sssp = new GraphStateSpaceSearchProblem(
graph, " Zerind ", " Oradea ");
bisearch.Search bisearch = new UniformCostSearch();
List<Action> actions = bisearch.search(sssp);
findRoute.printOutput(bisearch.nodesExplored(), actions);
}
/**
* prints the path found
*/
private static void printOutput(final int nodesExplored,
final List<Action> actions) {
double cost = 0;
for (final Action action : actions)
cost += action.cost();
System.out.println("Distance: " + new Formatter().format("%.2f", cost)+" m");
System.out.println ("Route: ");
for (final Action action : actions)
System.out.println(action);
}
/**
* creates a map of as a Graph
*/
private static Graph Map() {
final Graph graph = new Graph();
graph.addUndirectedEdge("Oradea", "Zerind", 71);
graph.addUndirectedEdge("Zerind", "Arad", 75);
graph.addUndirectedEdge("Arad", "Sibiu", 140);
graph.addUndirectedEdge("Sibiu", "Oradea", 151);
graph.addUndirectedEdge("Timisoara", "Arad", 118);
graph.addUndirectedEdge("Timisoara", "Lugoj", 111);
graph.addUndirectedEdge("Lugoj", "Mehadia", 70);
graph.addUndirectedEdge("Mehadia", "Dobreta", 75);
graph.addUndirectedEdge("Dobreta", "Craiova", 120);
graph.addUndirectedEdge("Sibiu", "Fagaras", 99);
graph.addUndirectedEdge("Fagaras", "Bucharest", 211);
graph.addUndirectedEdge("Sibiu", "Rimnicu Vilcea", 80);
graph.addUndirectedEdge("Pitesti", "Rimnicu Vilcea", 97);
graph.addUndirectedEdge("Craiova", "Rimnicu Vilcea", 146);
graph.addUndirectedEdge("Craiova", "Pitesti", 136);
graph.addUndirectedEdge("Pitesti", "Bucharest", 101);
graph.addUndirectedEdge("Bucharest", "Giurgiu", 90);
graph.addUndirectedEdge("Bucharest", "Urziceni", 85);
graph.addUndirectedEdge("Urziceni", "Hirsova", 98);
graph.addUndirectedEdge("Hirsova", "Eforie", 86);
graph.addUndirectedEdge("Urziceni", "Vaslui", 142);
graph.addUndirectedEdge("Vaslui", "Iasi", 92);
graph.addUndirectedEdge("Neamt", "Iasi", 87);
return graph;
}
}
I just can’t figure out how to do this. Any help would be greatly appreciated. Thanks in advance
You need to use args[]. Command line parameters are passed as an array to java program through args[] variable.
args[0] = inputFilename
args[1] = originCity
args[2] = DestinationCity
Fill the map by parsing the file. Rest of the code should work as it is.
For part 1 you want to use the File object that Java provides OOB for you. You will then need to read in the values from that file I would recommend the FileReader object. When you instantiate the File object you will need to use the index lookup from the args String array.
For the second part, the program already does that. If you want to limit the number of arguments you need to check the args.length variable against what your desired input parameters will be.
1) Read the file line by line, split the lines by your seperator and you should be good to go (google how to do that)
2) The program already accepts parameters. They are in your args array. You just have to use them (args[0], args[1]...)