Tensorflow神经网络之多层感知机

多层感知机简介
多层感知机模型 Tensorflow神经网络之多层感知机
文章图片
image 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 【Tensorflow神经网络之多层感知机】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_functionimport tensorflow as tf import matplotlib.pyplot as plt import numpy as np

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)

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

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)

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

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 )

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

构建评估器
# Build the Estimator model = tf.estimator.Estimator(model_fn)

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': , '_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}

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)

  • 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)

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 =https://www.it610.com/article/[{"feature1": 2, "features2":6}, {"feature1": 1, "features2":5}, {"feature1": 4, "features2":8}] y_data = https://www.it610.com/article/[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。

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)

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

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)

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}

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])

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.

Tensorflow神经网络之多层感知机
文章图片
image
Model prediction: 7

参考
[1] 在tf.estimator中构建inpu_fn解读
[2] TensorFlow layers模块用法

    推荐阅读