Tensflow：tf.contrib.learn.DNNClassifier（）模型的保存与复用以iris为例
python版本：3.5
tensorflow版本：1.4.0
在学习tensorflow深度学习应用时，很多资料以iris为例，并列举了很简单的例子，如本文下述代码。但是我们在搜集，将训练好的深度神经网络保存后，如何复用做测试时，就会搜到很多关于session相关的内容，但是又与自己好不容易学习的这个简单示例不匹配。本人也遇到同样的问题，查阅了很多博客都大同小异，并不是自己所需要的。接下来我将介绍使用tf.contrib.learn.DNNClassifier（）训练保存的模型如何重新的复用。方法真的是非常非常简单。
第一步： 训练深度神经网络，并将模型进行保存。
import os
import urllib
import numpy as np
import tensorflow as tf
import time
# Data sets
IRIS_TRAINING = "iris_training.csv"
IRIS_TRAINING_URL = "http://download.tensorflow.org/data/iris_training.csv"
IRIS_TEST = "iris_test.csv"
IRIS_TEST_URL = "http://download.tensorflow.org/data/iris_test.csv"
def main():
# If the training and test sets aren't stored locally, download them.
if not os.path.exists(IRIS_TRAINING):
raw = urllib.urlopen(IRIS_TRAINING_URL).read()
with open(IRIS_TRAINING, "w") as f:
f.write(raw)
if not os.path.exists(IRIS_TEST):
raw = urllib.urlopen(IRIS_TEST_URL).read()
with open(IRIS_TEST, "w") as f:
f.write(raw)
# Load datasets.
training_set = tf.contrib.learn.datasets.base.load_csv_with_header(
filename=IRIS_TRAINING,
target_dtype=np.int,
features_dtype=np.float32)
test_set = tf.contrib.learn.datasets.base.load_csv_with_header(
filename=IRIS_TEST,
target_dtype=np.int,
features_dtype=np.float32)
print(training_set)
# print(test_set)
# Specify that all features have real-value data
feature_columns = [tf.contrib.layers.real_valued_column("", dimension=4)]
print(feature_columns)
# Build 3 layer DNN with 10, 20, 10 units respectively.
classifier = tf.contrib.learn.DNNClassifier(feature_columns=feature_columns,hidden_units=[10, 20, 20, 10],n_classes=3,model_dir="D:\PycharmProject\Deep_Learning\Tensorflow_learning\model_iris")
# Define the training inputs
def get_train_inputs():
x = tf.constant(training_set.data)
y = tf.constant(training_set.target)
return x, y
# Fit model.
classifier.fit(input_fn=get_train_inputs, steps=2000)
# Define the test inputs
def get_test_inputs():
x = tf.constant(test_set.data)
y = tf.constant(test_set.target)
return x, y
# Evaluate accuracy.
accuracy_score = classifier.evaluate(input_fn=get_test_inputs,steps=1)["accuracy"]
print("\nTest Accuracy: {0:f}\n".format(accuracy_score))
print(classifier.evaluate(input_fn=get_test_inputs,steps=1))
print(list(classifier.predict(input_fn=get_test_inputs)))
# Classify two new flower samples.
def new_samples():
return np.array(
[[6.4, 3.2, 4.5, 1.5],
[5.8, 3.1, 5.0, 1.7]], dtype=np.float32)
predictions = list(classifier.predict(input_fn=new_samples))
print(
"New Samples, Class Predictions: {}\n"
.format(predictions))
if __name__ == "__main__":
start = time.time()
main()
end = time.time()
print('运行时间：',end-start)
运行部分结果如下：
Test Accuracy: 0.966667
运行时间： 5.970066785812378
生成的文件内容如下：
第二步：恢复模型利用，得出测试结果。
import os
import urllib
import numpy as np
import tensorflow as tf
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
import time
IRIS_TEST = "D:\PycharmProject\Deep_Learning\Tensorflow_learning\iris_test.csv"
IRIS_TEST_URL = "http://download.tensorflow.org/data/iris_test.csv"
def main():
test_set = tf.contrib.learn.datasets.base.load_csv_with_header(
filename=IRIS_TEST,
target_dtype=np.int,
features_dtype=np.float32)
# Specify that all features have real-value data
feature_columns = [tf.contrib.layers.real_valued_column("", dimension=4)]
print(feature_columns)
# Build 3 layer DNN with 10, 20, 10 units respectively.
classifier = tf.contrib.learn.DNNClassifier(feature_columns=feature_columns,hidden_units=[10, 20, 20, 10],n_classes=3,model_dir="D:\PycharmProject\Deep_Learning\Tensorflow_learning\model_iris")
# Define the test inputs
def get_test_inputs():
x = tf.constant(test_set.data)
y = tf.constant(test_set.target)
return x, y
# Evaluate accuracy.
accuracy_score = classifier.evaluate(input_fn=get_test_inputs,steps=1)["accuracy"]
print("\nTest Accuracy: {0:f}\n".format(accuracy_score))
print(classifier.evaluate(input_fn=get_test_inputs,steps=1))
print(list(classifier.predict(input_fn=get_test_inputs)))
# Classify two new flower samples.
def new_samples():
return np.array(
[[6.4, 3.2, 4.5, 1.5],
[5.8, 3.1, 5.0, 1.7]], dtype=np.float32)
predictions = list(classifier.predict(input_fn=new_samples))
print(
"New Samples, Class Predictions: {}\n"
.format(predictions))
# conf_mat = confusion_matrix(testlabel,predictions)
# report = classification_report(testlabel,predictions)
if __name__ == "__main__":
start = time.time()
main()
end = time.time()
print('运行时间：',end-start)
运行部分结果如下：
Test Accuracy: 0.966667
运行时间： 2.1934993267059326
完成，是不是很简单，通过测试集得出的accuracy和运行的时间就可以得知，第二步并没有重新的训练模型，而是直接使用已经训练好的深度神经网络，但是需要注意的问题是模型的结构要统一，如下代码所示：
tf.contrib.learn.DNNClassifier(feature_columns=feature_columns,hidden_units=[10, 20, 20,10],n_classes=3,model_dir="D:\PycharmProject\Deep_Learning\Tensorflow_learning\model_iris")