import torch
import torch.nn as nn
import numpy as np
import matplotlib.pyplot as plt


# 超参数设置
# Hyper Parameters
BATCH_SIZE = 64
LR_G = 0.0001           # learning rate for generator
LR_D = 0.0001           # learning rate for discriminator
N_IDEAS = 5             # think of this as number of ideas for generating an art work (Generator)
ART_COMPONENTS = 15     # it could be total point G can draw in the canvas
PAINT_POINTS = np.vstack([np.linspace(-1, 1, ART_COMPONENTS) for _ in range(BATCH_SIZE)])

# show our beautiful painting range
# 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()

# 著名画家的画
# 这里生成一些著名画家的画 (batch 条不同的一元二次方程曲线).

def artist_works():     # painting from the famous artist (real target)
    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

# 神经网络
# Generator (新手画家), G 会拿着自己的一些灵感当做输入, 输出一元二次曲线上的点 (G 的画).
G = nn.Sequential(                      # Generator
    nn.Linear(N_IDEAS, 128),            # random ideas (could from normal distribution)
    nn.ReLU(),
    nn.Linear(128, ART_COMPONENTS),     # making a painting from these random ideas
)
# Discriminator(新手鉴赏家). D 会接收一幅画作 (一元二次曲线), 输出这幅画作到底是不是著名画家的画(是著名画家的画的概率).
D = nn.Sequential(                      # Discriminator
    nn.Linear(ART_COMPONENTS, 128),     # receive art work either from the famous artist or a newbie like G
    nn.ReLU(),
    nn.Linear(128, 1),
    nn.Sigmoid(),                       # tell the probability that the art work is made by artist
)

# 搭建完神经网络后,对 神经网路参数(net.parameters()) 进行优化
# 选择优化器 optimizer 是训练的工具
opt_D = torch.optim.Adam(D.parameters(), lr=LR_D)
opt_G = torch.optim.Adam(G.parameters(), lr=LR_G)

plt.ion()   # something about continuous plotting

# 训练
# G 首先会有些灵感, G_ideas 就会拿到这些随机灵感 (可以是正态分布的随机数),
# 然后 G 会根据这些灵感画画.接着我们拿着著名画家的画和 G 的画, 让 D 来判定这两批画作是著名画家画的概率.
# 然后计算有多少来之画家的画猜对了, 有多少来自 G 的画猜对了, 我们想最大化这些猜对的次数.这也就是 log(D(x)) + log(1-D(G(z))
# 因为 torch 中提升参数的形式是最小化误差, 那我们把最大化 score 转换成最小化 loss,
# 在两个 score 的合的地方加一个符号就好. 而 G 的提升就是要减小 D 猜测 G 生成数据的正确率, 也就是减小 D_score1.
for step in range(10000):
    artist_paintings = artist_works()           # real painting from artist
    G_ideas = torch.randn(BATCH_SIZE, N_IDEAS)  # random ideas
    G_paintings = G(G_ideas)                    # fake painting from G (random ideas)

    prob_artist0 = D(artist_paintings)          # D try to increase this prob
    prob_artist1 = D(G_paintings)               # D try to reduce this prob

    D_loss = - torch.mean(torch.log(prob_artist0) + torch.log(1. - prob_artist1))
    G_loss = torch.mean(torch.log(1. - prob_artist1))

    opt_D.zero_grad()
    D_loss.backward(retain_graph=True)      # reusing computational graph  保留参数
    opt_D.step()

    opt_G.zero_grad()
    G_loss.backward()
    opt_G.step()

    if step % 50 == 0:  # plotting
        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()