Tensorflow神经网络之多层感知机_一个含有2个隐藏层的多层感知机

多层感知机简介

多层感知机模型

这里定义含有两个隐含层的模型，隐含层输出均为256个节点，输入784（MNIST数据集图片大小28*28），输出10。

激活函数

比较常用的是 ReLU：relu(x)=max(x,0)，本例中没有加激活函数。

softmax（同前面的logistic回归）

损失函数：交叉熵

Tensorflow实现多层感知机

from __future__ import print_function

import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
1
2
3
4
5

导入数据集

# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("./data/", one_hot=False)
1
2
3

Extracting ./data/train-images-idx3-ubyte.gz
Extracting ./data/train-labels-idx1-ubyte.gz
Extracting ./data/t10k-images-idx3-ubyte.gz
Extracting ./data/t10k-labels-idx1-ubyte.gz
1
2
3
4

设置参数

# Parameters
learning_rate = 0.1
num_steps = 1000
batch_size = 128
display_step = 100

# Network Parameters
n_hidden_1 = 256 # 1st layer number of neurons
n_hidden_2 = 256 # 2nd layer number of neurons
num_input = 784 # MNIST data input (img shape: 28*28)
num_classes = 10 # MNIST total classes (0-9 digits)
1
2
3
4
5
6
7
8
9
10
11

定义多层感知机模型

# Define the neural network
def neural_net(x_dict):
    # TF Estimator input is a dict, in case of multiple inputs
    x = x_dict['images']
    # Hidden fully connected layer with 256 neurons
    layer_1 = tf.layers.dense(x, n_hidden_1)
    # Hidden fully connected layer with 256 neurons
    layer_2 = tf.layers.dense(layer_1, n_hidden_2)
    # Output fully connected layer with a neuron for each class
    out_layer = tf.layers.dense(layer_2, num_classes)
    return out_layer
1
2
3
4
5
6
7
8
9
10
11

补充：dense [^2]

dense(
   inputs,
   units,
   activation=None,
   use_bias=True,
   kernel_initializer=None,
   bias_initializer=tf.zeros_initializer(),
   kernel_regularizer=None,
   bias_regularizer=None,
   activity_regularizer=None,
   kernel_constraint=None,
   bias_constraint=None,
   trainable=True,
   name=None,
   reuse=None
)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16

参数说明如下：

• inputs：必需，即需要进行操作的输入数据。
• units：必须，即神经元的数量。
• activation：可选，默认为 None，如果为 None 则是线性激>活。
• use_bias：可选，默认为 True，是否使用偏置。
• kernel_initializer：可选，默认为 None，即权重的初始化>方法，如果为 None，则使用默认的 Xavier 初始化方法。
• bias_initializer：可选，默认为零值初始化，即偏置的初始>化方法。
• kernel_regularizer：可选，默认为 None，施加在权重上的>正则项。
• bias_regularizer：可选，默认为 None，施加在偏置上的正>则项。
• activity_regularizer：可选，默认为 None，施加在输出上>的正则项。
• kernel_constraint，可选，默认为 None，施加在权重上的>约束项。
• bias_constraint，可选，默认为 None，施加在偏置上的约束>项。
• trainable：可选，默认为 True，布尔类型，如果为 True，>则将变量添加到 GraphKeys.TRAINABLE_VARIABLES 中。
• name：可选，默认为 None，卷积层的名称。
• reuse：可选，默认为 None，布尔类型，如果为 True，那么>如果 name 相同时，会重复利用。
• 返回值： 全连接网络处理后的 Tensor。

上面的代码中，第三个参数为空，所以这里采用线性激活

定义模型函数

# Define the model function (following TF Estimator Template)
def model_fn(features, labels, mode):

    # Build the neural network
    logits = neural_net(features)

    # Predictions
    pred_classes = tf.argmax(logits, axis=1)
    pred_probas = tf.nn.softmax(logits)

    # If prediction mode, early return
    if mode == tf.estimator.ModeKeys.PREDICT:
        return tf.estimator.EstimatorSpec(mode, predictions=pred_classes)

    # Define loss and optimizer
    loss_op = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(
        logits=logits, labels=tf.cast(labels, dtype=tf.int32)))
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
    train_op = optimizer.minimize(loss_op, global_step=tf.train.get_global_step())

    # Evaluate the accuracy of the model
    acc_op = tf.metrics.accuracy(labels=labels, predictions=pred_classes)

    # TF Estimators requires to return a EstimatorSpec, that specify
    # the different ops for training, evaluating, ...
    estim_specs = tf.estimator.EstimatorSpec(
      mode=mode,
      predictions=pred_classes,
      loss=loss_op,
      train_op=train_op,
      eval_metric_ops={'accuracy': acc_op})

    return estim_specs
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33

构建评估器

# Build the Estimator
model = tf.estimator.Estimator(model_fn)
1
2

INFO:tensorflow:Using default config.
WARNING:tensorflow:Using temporary folder as model directory: C:\Users\xywang\AppData\Local\Temp\tmp995gddib
INFO:tensorflow:Using config: {'_model_dir': 'C:\\Users\\xywang\\AppData\\Local\\Temp\\tmp995gddib', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': None, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_service': None, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x0000024BBEE7A1D0>, '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}
1
2
3

补充：tf.estimator
tf.estimator就是已经预定义好的模型，自带train，evaluate，predict。
其编程范式为：

• 定义算法模型，比如多层感知机，CNN；
• 定义模型函数（model_fn），包括构建graph，定义损失函数、优化器，估计准确率等，返回结果分训练和测试两种情况；
• 构建评估器；

model = tf.estimator.Estimator(model_fn)
1

• 用 tf.estimator.inputs.numpy_input_fn 把 input_fn 传入 model，就可调用 model.train, model.evaluate, model.predict 了。

input_fn = tf.estimator.inputs.numpy_input_fn()
model.train(input_fn)
model.evaluate(input_fn)
model.predict(input_fn)
1
2
3
4

Estimator 是一种更高层次的封装，它把一些基本算法的算法>模型和模型函数预定义好，你只需要传入参数即可。

input_fn [^1]

一般来讲，input_fn方法做两件事：

1.数据预处理，如洗脏数据，归整数据等。没有就空着。

2.返回feature_cols, labels。

• feature_cols：一个dict，key为feature名，value>为feature值。
• lables: 对应的分类标签。

可以将多种对象转换为tensorflow对象，常见的为将Numpy>转tensorflow对象。比如：

import tensorflow as tf
import numpy as np
#numpy input_fn.
x_data =[{"feature1": 2, "features2":6},
         {"feature1": 1, "features2":5},
         {"feature1": 4, "features2":8}]
y_data = [2,3,4]
my_input_fn = tf.estimator.inputs.numpy_input_fn(
    x={"x": np.array(x_data)},
    y=np.array(y_data),
    shuffle = True)
#得到的是一个名为my_input_fn的function对象。
1
2
3
4
5
6
7
8
9
10
11
12

训练模型

# Define the input function for training
input_fn = tf.estimator.inputs.numpy_input_fn(
    x={'images': mnist.train.images}, y=mnist.train.labels,
    batch_size=batch_size, num_epochs=None, shuffle=True)

#Train the Model
model.train(input_fn, steps=num_steps)
1
2
3
4
5
6
7

INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Saving checkpoints for 1 into C:\Users\xywang\AppData\Local\Temp\tmp995gddib\model.ckpt.
INFO:tensorflow:loss = 2.4631722, step = 1
INFO:tensorflow:global_step/sec: 248.501
INFO:tensorflow:loss = 0.42414927, step = 101 (0.388 sec)
INFO:tensorflow:global_step/sec: 301.862
INFO:tensorflow:loss = 0.48539022, step = 201 (0.331 sec)
INFO:tensorflow:global_step/sec: 310.3
INFO:tensorflow:loss = 0.2779913, step = 301 (0.323 sec)
INFO:tensorflow:global_step/sec: 303.697
INFO:tensorflow:loss = 0.20052063, step = 401 (0.329 sec)
INFO:tensorflow:global_step/sec: 322.311
INFO:tensorflow:loss = 0.5092098, step = 501 (0.309 sec)
INFO:tensorflow:global_step/sec: 337.555
INFO:tensorflow:loss = 0.28386787, step = 601 (0.297 sec)
INFO:tensorflow:global_step/sec: 322.309
INFO:tensorflow:loss = 0.36957514, step = 701 (0.309 sec)
INFO:tensorflow:global_step/sec: 334.17
INFO:tensorflow:loss = 0.28504127, step = 801 (0.300 sec)
INFO:tensorflow:global_step/sec: 319.222
INFO:tensorflow:loss = 0.37339848, step = 901 (0.312 sec)
INFO:tensorflow:Saving checkpoints for 1000 into C:\Users\xywang\AppData\Local\Temp\tmp995gddib\model.ckpt.
INFO:tensorflow:Loss for final step: 0.2043538.

tensorflow.python.estimator.estimator.Estimator at 0x24bbee72160
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30

模型评估

# Evaluate the Model
# Define the input function for evaluating
input_fn = tf.estimator.inputs.numpy_input_fn(
    x={'images': mnist.test.images}, y=mnist.test.labels,
    batch_size=batch_size, shuffle=False)
# Use the Estimator 'evaluate' method
model.evaluate(input_fn)
1
2
3
4
5
6
7

INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Starting evaluation at 2018-04-11-08:04:38
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Restoring parameters from C:\Users\xywang\AppData\Local\Temp\tmp995gddib\model.ckpt-1000
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Finished evaluation at 2018-04-11-08:04:38
INFO:tensorflow:Saving dict for global step 1000: accuracy = 0.9149, global_step = 1000, loss = 0.29386005

{'accuracy': 0.9149, 'global_step': 1000, 'loss': 0.29386005}
1
2
3
4
5
6
7
8
9
10
11

测试

# Predict single images
n_images = 1
# Get images from test set
test_images = mnist.test.images[:n_images]
# Prepare the input data
input_fn = tf.estimator.inputs.numpy_input_fn(
    x={'images': test_images}, shuffle=False)
# Use the model to predict the images class
preds = list(model.predict(input_fn))

# Display
for i in range(n_images):
    plt.imshow(np.reshape(test_images[i], [28, 28]), cmap='gray')
    plt.show()
    print("Model prediction:", preds[i])
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15

INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Restoring parameters from C:\Users\xywang\AppData\Local\Temp\tmp995gddib\model.ckpt-1000
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
1
2
3
4
5
6

Model prediction: 7
1

参考

[1] 在tf.estimator中构建inpu_fn解读

[2] TensorFlow layers模块用法

---