TensorFlow - Keras

Keras易于学习的高级Python库，可在TensorFlow框架上运行，它的重点是理解深度学习技术，如为神经网络创建层，以维护形状和数学细节的概念。框架的创建可以分为以下两种类型-

• 顺序API
• 功能API

无涯教程将使用Jupyter Notebook执行和显示输出，如下所示-

步骤1   -  首先执行数据加载和预处理加载的数据以执行深度学习模型。

import warnings
warnings.filterwarnings('ignore')

import numpy as np
np.random.seed(123) # for reproducibility

from keras.models import Sequential
from keras.layers import Flatten, MaxPool2D, Conv2D, Dense, Reshape, Dropout
from keras.utils import np_utils
Using TensorFlow backend.
from keras.datasets import mnist

# 将预混洗的 MNIST 数据加载到训练和测试集中
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = X_train.reshape(X_train.shape[0], 28, 28, 1)
X_test = X_test.reshape(X_test.shape[0], 28, 28, 1)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
Y_train = np_utils.to_categorical(y_train, 10)
Y_test = np_utils.to_categorical(y_test, 10)

可以将该步骤定义为"Import libraries and Modules"，这意味着所有库和模块都将作为初始步骤导入。

步骤2    -  在这一步中，无涯教程将定义模型架构-

model = Sequential()
model.add(Conv2D(32, 3, 3, activation = 'relu', input_shape = (28,28,1)))
model.add(Conv2D(32, 3, 3, activation = 'relu'))
model.add(MaxPool2D(pool_size = (2,2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation = 'relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation = 'softmax'))

步骤3    -  现在让编译指定的模型-

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

步骤4    -  现在，将使用训练数据拟合模型-

model.fit(X_train, Y_train, batch_size=32, epochs=10, verbose=1)

创建的迭代的输出如下-

Epoch 1/10 60000/60000 [==============================] - 65s - 
loss: 0.2124 - 
acc: 0.9345 
Epoch 2/10 60000/60000 [==============================] - 62s - 
loss: 0.0893 - 
acc: 0.9740 
Epoch 3/10 60000/60000 [==============================] - 58s - 
loss: 0.0665 - 
acc: 0.9802 
Epoch 4/10 60000/60000 [==============================] - 62s - 
loss: 0.0571 - 
acc: 0.9830 
Epoch 5/10 60000/60000 [==============================] - 62s - 
loss: 0.0474 - 
acc: 0.9855 
Epoch 6/10 60000/60000 [==============================] - 59s -
loss: 0.0416 - 
acc: 0.9871 
Epoch 7/10 60000/60000 [==============================] - 61s - 
loss: 0.0380 - 
acc: 0.9877 
Epoch 8/10 60000/60000 [==============================] - 63s - 
loss: 0.0333 - 
acc: 0.9895 
Epoch 9/10 60000/60000 [==============================] - 64s - 
loss: 0.0325 - 
acc: 0.9898 
Epoch 10/10 60000/60000 [==============================] - 60s - 
loss: 0.0284 - 
acc: 0.9910