- 根据mnist_cnn_to_student.py代码的提示,编写卷积神经网络代码,并尝试设计AlexNet框架(包含5个卷积层的神经网络),用于手写数字识别。
2.完成情感分析代码(基于循环神经网络)的运行与调试。
1.卷积神经网络
'''Trains a simple convnet on the MNIST dataset.
Gets to 99.25% test accuracy after 12 epochs
(there is still a lot of margin for parameter tuning).
16 seconds per epoch on a GRID K520 GPU.
'''
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
batch_size = 128 # 一次训练所选取的样本数
num_classes = 10 # 分类的类别数
epochs = 12 # 完整的数据集所训练的次数
# 训练集有1000个样本,batchsize=10,那么:训练完整个样本集需要: 100次iteration,1次epoch。
# input image dimensions 数据的维数
img_rows, img_cols = 28, 28
# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
x_train = x_train.astype('float32') # 将uint8型数据转成float32
x_test = x_test.astype('float32')
x_train /= 255 # 归一化处理
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices 将类别向量转换为二进制类矩阵
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
model = Sequential() # 接下来定义顺序模型,输入 28*28大小的图像
# 卷积层1,首先加入2D卷积层,卷积核大小3*3,通道数32,激活函数为relu