作业截图:
中文释义代码如下:
import torch
import torch.nn as nn
import numpy as np
import matplotlib.pyplot as plt
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
# torch.manual_seed(1) # 可重复性
# np.random.seed(1)
# 超参数
BATCH_SIZE = 64
LR_G = 0.0001 # 生成器学习率
LR_D = 0.0001 # 判别器学习率
N_IDEAS = 5 # 生成艺术品所需的思路数(生成器)
ART_COMPONENTS = 15 # 画布上G能画的总点数
PAINT_POINTS = np.vstack([np.linspace(-1, 1, ART_COMPONENTS) for _ in range(BATCH_SIZE)])
# 展示我们美丽的绘画范围
# plt.plot(PAINT_POINTS[0], 2 * np.power(PAINT_POINTS[0], 2) + 1, c='#74BCFF', lw=3, label='upper bound')
# plt.plot(PAINT_POINTS[0], 1 * np.power(PAINT_POINTS[0], 2) + 0, c='#FF9359', lw=3, label='lower bound')
# plt.legend(loc='upper right')
# plt.show()
def artist_works(): # 画家的真实画作(真实目标)
a = np.random.uniform(1, 2, size=BATCH_SIZE)[:, np.newaxis]
paintings = a * np.power(PAINT_POINTS, 2) + (a - 1)
paintings = torch.from_numpy(paintings).float()
return paintings
G = nn.Sequential( # 生成器
nn.Linear(N_IDEAS, 128), # 随机的思路(可以从正态分布中得到)
nn.ReLU(),
nn.Linear(128, ART_COMPONENTS), # 利用这些随机思路制作一幅画
)
D = nn.Sequential( #判别器
nn.Linear(ART_COMPONENTS, 128), # 接收画作,可能是来自著名画家或像G这样的新手
nn.ReLU(),
nn.Linear(128, 1),
nn.Sigmoid(), # 表示画作由画家创作的概率
)
opt_D = torch.optim.Adam(D.parameters(), lr=LR_D)
opt_G = torch.optim.Adam(G.parameters(), lr=LR_G)
plt.ion() # 连续绘图的一些内容
for step in range(10000):
artist_paintings = artist_works() # 画家的真实画作
G_ideas = torch.randn(BATCH_SIZE, N_IDEAS, requires_grad=True) #随机思路\n
G_paintings = G(G_ideas) #G(随机思路)创作的假画作
prob_artist1 = D(G_paintings) # D尝试减少这个概率
G_loss = torch.mean(torch.log(1. - prob_artist1))
opt_G.zero_grad()
G_loss.backward()
opt_G.step()
prob_artist0 = D(artist_paintings) # D尝试增加这个概率的值。
prob_artist1 = D(G_paintings.detach()) # D尝试减少这个概率的值。
D_loss = - torch.mean(torch.log(prob_artist0) + torch.log(1. - prob_artist1))
opt_D.zero_grad()
D_loss.backward(retain_graph=True) # 重用计算图
opt_D.step()
if step % 50 == 0: # 绘制图表
plt.cla()
plt.plot(PAINT_POINTS[0], G_paintings.data.numpy()[0], c='#4AD631', lw=3, label='Generated painting', )
plt.plot(PAINT_POINTS[0], 2 * np.power(PAINT_POINTS[0], 2) + 1, c='#74BCFF', lw=3, label='upper bound')
plt.plot(PAINT_POINTS[0], 1 * np.power(PAINT_POINTS[0], 2) + 0, c='#FF9359', lw=3, label='lower bound')
plt.text(-.5, 2.3, 'D accuracy=%.2f (0.5 for D to converge)' % prob_artist0.data.numpy().mean(),
fontdict={'size': 13})
plt.text(-.5, 2, 'D score= %.2f (-1.38 for G to converge)' % -D_loss.data.numpy(), fontdict={'size': 13})
plt.ylim((0, 3));
plt.legend(loc='upper right', fontsize=10);
plt.draw();
plt.pause(0.01)
plt.ioff()
plt.show()
运行结果截图: