如何将输入数据传递到Java中现有的tensorflow 2.x模型?
我正在使用如何将输入数据传递到Java中现有的tensorflow 2.x模型?,java,python,tensorflow,Java,Python,Tensorflow,我正在使用tensorflow完成我的第一步。在用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并使用它进行分类。但是,我无法将输入数据传递给模型 以下是用于创建模型的Python代码: from tensorflow.keras.datasets import mnist from tensorflow.keras.utils import to_categorical. (train_images, train_labels), (test_im
tensorflow
完成我的第一步。在用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并使用它进行分类。但是,我无法将输入数据传递给模型
以下是用于创建模型的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
# 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')
对于Java
,我正在尝试调整发布的App.Java
代码
我正在努力替换这段代码:
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,一个特定的输入张量用于传递数据,在我的模型中,只有层,没有单独命名的张量。因此,以下方法不起作用:
Tensor<?> result = s.runner()
.feed("Input_Layer/kernel", inputTensor)
.fetch("Output_Layer/kernel")
.run().get(0);
Tensor result=s.runner()
.feed(“输入层/内核”,输入传感器)
.fetch(“输出层/内核”)
.run().get(0);
如何用Java将数据传递给我的模型并从中获得输出?我终于找到了一个解决方案。为了获得图形中的所有张量名称,我使用了以下代码:
for (Iterator it = smb.graph().operations(); it.hasNext();) {
Operation op = (Operation) it.next();
System.out.println("Operation name: " + op.name());
}
从这一点上,我发现以下方法是有效的:
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);
SavedModelBundle smb=SavedModelBundle.load(“./model”,“service”);
会话s=smb.Session();
Tensor InputSensor=Tensor.create(imagesArray,Float.class);
张量结果=s.runner()
.feed(“服务\默认\输入\层\输入”,输入传感器)
.fetch(“StatefulPartitionedCall”)
.run().get(0.expect(Float.class));
使用最新版本的,您无需从模型签名或图形中搜索输入/输出张量的名称。您可以简单地调用以下命令:
try(SavedModelBundle model=SavedModelBundle.load(“./model”,“service”);
Tensor image=TFloat32.tensorOf(…);//这里有很多方法可以传递图像字节
张量结果=model.call(image.expect(TFloat32.DTYPE)){
System.out.println(“结果是”+Result.data().getFloat());
}
}
TensorFlow Java将自动负责将输入/输出张量映射到正确的节点