在TFLearn目录下新建CNN_MNIST.py，在PyCharm中编写代码。
使用TFLearn搭建一个两层的卷积神经网络，数据集是MNIST手写数字的数据集，TFLearn将卷积、池化、正则化等操作都封装成了类，所以需要先导入这些类。
from future import division, print_function, absolute_import
import tflearn
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.estimator import regression
导入类之后，需要构建一个拥有两个卷积层的神经网络。使用TFLearn的卷积、池化、正则化、全连接、Dropout等操作完成网络构建，TFLearn在卷积的时候，参数包含激活函数，所以不必单独构建激活函数。

MNIST数据集加载

import tflearn.datasets.mnist as mnist
X, Y, testX, testY = mnist.load_data(one_hot=True)
X = X.reshape([-1, 28, 28, 1])
testX = testX.reshape([-1, 28, 28, 1])

搭建卷积神经网络，两层卷积

network = input_data(shape=[None, 28, 28, 1], name='input')
network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = fully_connected(network, 128, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 10, activation='softmax')
network = regression(network, optimizer='adam', learning_rate=0.01,
loss='categorical_crossentropy', name='target')
regression()函数中需要规定优化器类型、学习率和损失函数类型。
完成网络构建后，开始训练模型，在训练过程中可以看到损失以及准确率。

训练

model = tflearn.DNN(network, tensorboard_verbose=0)
model.fit({'input': X}, {'target': Y}, n_epoch=20,
validation_set=({'input': testX}, {'target': testY}),
snapshot_step=100, show_metric=True, run_id='convnet_mnist')
使用TFLearn构建神经网络时，由于封装度更高，所以整体的代码非常简洁。