李宏毅机器学习笔记二

8 Keras使用

adam高级优化方法不需要自己设置学习速率

如果有100个batch，1个epoch就更新参数100次

可以看出，batch_size 为1 和为10，参数更新速度是一样的(相同时间下，都用166s),这是由于vectorization带来的加速，并行运算。但随着batch_size 增大，速度会减慢。

mini-batch，参数更新有较大随机性，帮助跳出local minimum。如果不使用mini=batch,计算机可能会卡（内存不足），或则容易陷入local minimum。


上面的时间是下面的两倍，所以，当有GPU计算资源时，应该使用mini-batch,否则不会带来加速。

手写数字识别

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.datasets import mnist
from keras.utils import np_utils
from  keras.optimizers import SGD,Adam
import keras.callbacks
import time

a = time.time()
def load_data():
    (x_train,y_train),(x_test,y_test)=mnist.load_data()
    # print(x_train.shape,y_train.shape)  #(60000, 28, 28)   (60000,)
    # print(x_test.shape, y_test.shape)  # (10000, 28, 28) (10000,)

    number = 10000
    x_train = x_train[:number]
    y_train = y_train[:number]
    x_train = x_train.reshape(number,28*28)
    # print(y_train.shape) # (10000,)
    x_test = x_test.reshape(x_test.shape[0],28*28)
    x_train = x_train.astype(np.float32)

    x_test = x_test.astype(np.float32)

    y_train = np_utils.to_categorical(y_train,10)
    y_test = np_utils.to_categorical(y_test, 10)
    # print(y_train.shape)  # (10000, 10)
    x_train /= 255
    x_test /= 255

    # print(x_train.shape,y_train.shape,x_test.shape,y_test.shape) # (10000, 784) (10000, 10) (10000, 784) (10000, 10)
    return (x_train,y_train),(x_test,y_test)

(x_train,y_train),(x_test,y_test) = load_data()
model = Sequential()
# 全连接层
model.add(Dense(input_dim=28*28,units=500,activation='relu'))  # 'relu' 'sigmoid'

model.add(Dense(units=500,activation='relu'))

model.add(Dense(units=10,activation='softmax'))

# model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
# model.compile(loss='mse',optimizer='sgd',metrics=['accuracy'])
# model.compile(loss='categorical_crossentropy',optimizer=SGD(lr=0.01, momentum=0.9, nesterov=True),metrics=['accuracy'])
model.compile(loss='categorical_crossentropy',optimizer=Adam(),metrics=['accuracy'])
#
#可视化
log_filepath = 'E:\AAA\PYTHON\conda_test\keras_log'

tb_cb = keras.callbacks.TensorBoard(log_dir=log_filepath, write_images=1)
# 设置log的存储位置，将网络权值以图片格式保持在tensorboard中显示，设置每一个周期计算一次网络的权值，每层输出值的分布直方图

cbks = [tb_cb]

model.fit(x_train,y_t