""" Neural Network.
A 2-Hidden Layers Fully Connected Neural Network (a.k.a Multilayer Perceptron)
implementation with TensorFlow. This example is using the MNIST database
of handwritten digits (http://yann.lecun.com/exdb/mnist/).
This example is using TensorFlow layers, see 'neural_network_raw' example for
a raw implementation with variables.
Links:
[MNIST Dataset](http://yann.lecun.com/exdb/mnist/).
Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
"""
from __future__ import print_function
# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=False)
import tensorflow as tf
# 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)
# 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
# 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
# Build the Estimator
model = tf.estimator.Estimator(model_fn)
# 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)
# 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
e = model.evaluate(input_fn)
print("Testing Accuracy:", e['accuracy'])
# Predict single images
n_images = 4
# 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])
以上示例代码使用TensorFlow框架和手写数字识别数据集MNIST训练网络,运行环境为Python3.6、TensorFlow1.7。其神经网络搭建过程总结如下:
step1.超参数设定。如学习率、训练步数、小批量大小、打印输出训练结果间隔步长。
神经网络参数设定。如输入层、隐藏层、输出层的神经单元个数。
step2.定义神经网络前向传播过程函数。
step3.定义model_fn函数。该函数返回一个特定了一些参数的estimator。函数定义详见TensorFlow API。
step4.定义模型。该模型由tf.estimator.Estimator(model_fn)建立。
step5.定义input_fn函数。函数定义详见TensorFlow API。
step6.训练模型。
step7.定义input_fn函数。
step8.评估模型。