大数据算法实验七

最新推荐文章于 2024-09-11 10:30:00 发布

m0_62936151

最新推荐文章于 2024-09-11 10:30:00 发布

阅读量104

点赞数 2

文章标签：大数据算法

本文链接：https://blog.csdn.net/m0_62936151/article/details/139753529

版权

# coding: utf-8
import sys, os
sys.path.append(os.pardir)  # 为了导入父目录的文件而进行的设定
import numpy as np
from collections import OrderedDict
from common.optimizer import *  #优化器
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.util import smooth_curve
from common.multi_layer_net import MultiLayerNet



# 0:读入MNIST数据==========
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)

train_size = x_train.shape[0]
batch_size = 128
max_iterations = 2000

# 1:进行实验的设置==========
# 1:设置权重初始值的方式
weight_init_types = {'std=0.01': 0.01, 'Xavier': 'sigmoid', 'He': 'relu'}
# optimizer = SGD(lr=0.01)
optimizer = AdaGrad(lr=0.05)

networks = {}
train_loss = {}
# 初始化网络
for key, weight_type in weight_init_types.items():
    networks[key] = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100],
                                  output_size=10, weight_init_std=weight_type)
    train_loss[key] = []

# 2:开始训练==========
# 2:训练2000次
for i in range(max_iterations):
    # 批处理
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    t_batch = t_train[batch_mask]
    # 梯度更新
    for key in weight_init_types.keys():
        grads = networks[key].gradient(x_batch, t_batch)
        optimizer.update(networks[key].params, grads)

        loss = networks[key].loss(x_batch, t_batch)
        train_loss[key].append(loss)

    if i % 100 == 0:
        print("===========" + "iteration:" + str(i) + "===========")
        for key in weight_init_types.keys():
            loss = networks[key].loss(x_batch, t_batch)
            print(key + ":" + str(loss))

# 3.绘制图形==========
markers = {'std=0.01': 'o', 'Xavier': 's', 'He': 'D'}
x = np.arange(max_iterations)
for key in weight_init_types.keys():
    plt.plot(x, smooth_curve(train_loss[key]), marker=markers[key], markevery=100, label=key)
plt.xlabel("iterations")
plt.ylabel("loss")
plt.ylim(0, 2.5)
plt.legend()
plt.show()