英文:
How to pass input data to an existing tensorflow 2.x model in Java?
问题
以下是翻译好的部分：
我正在使用`tensorflow`迈出我的第一步。在使用Python为MNIST数据创建了一个简单的模型之后，我现在想将这个模型导入Java，并在分类中使用它。然而，我无法将输入数据传递给模型。
这是用于模型创建的Python代码：
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
# 网络结构
model = Sequential()
mnist_inputshape = train_images.shape[1:4]
# 卷积块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)))
# 卷积块2
model.add(Conv2D(64, kernel_size=(5,5),activation= 'relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.5))
# 预测块
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')
对于Java，我试图调整在此处发布的App.java代码。
我正在努力替换这个片段：
Tensor result = s.runner()
.feed("input_tensor", inputTensor)
.feed("dropout/keep_prob", keep_prob)
.fetch("output_tensor")
.run().get(0);
在这段代码中，使用了特定的输入张量来传递数据，而在我的模型中，只有层，没有单独的命名张量。因此，以下代码无法工作：
Tensor<?> result = s.runner()
.feed("Input_Layer/kernel", inputTensor)
.fetch("Output_Layer/kernel")
.run().get(0);
我应该如何在Java中传递数据并获取模型的输出？
<details>
<summary>英文:</summary>
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][1].
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?
[1]: https://github.com/kalaspuffar/tensorflow-mnist-test/tree/master/src/main/java/org/ea/tensorflow
</details>
# 答案1
**得分**: 1
我终于成功找到了解决方法。为了获取图中的所有张量名称，我使用了以下代码：
```java
for (Iterator it = smb.graph().operations(); it.hasNext();) {
Operation op = (Operation) it.next();
System.out.println("Operation name: " + op.name());
}
通过这个，我找到了以下有效的方法：
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);
英文:
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);
答案2
得分: 1
使用最新版本的TensorFlow Java，您无需自行查找模型签名或图形中输入/输出张量的名称。您只需调用以下方法：
try (SavedModelBundle model = SavedModelBundle.load("./model", "serve");
Tensor<TFloat32> image = TFloat32.tensorOf(...); // 有许多方法可以传递图像字节
Tensor<TFloat32> result = model.call(image).expect(TFloat32.DTYPE)) {
System.out.println("Result is " + result.data().getFloat());
}
TensorFlow Java将自动处理将您的输入/输出张量映射到正确的节点。
英文:
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.
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库，让每个人都能够通过互相帮助和分享经验来进步。
评论