pytorch深度学习

RNN循环神经网络pytorch

RNN

后面的神经网络会基于前面神经网络的贡献

可以接受更广泛的时间序列结构输入

LSTM RNN

long short-term memory（长短期记忆）

普通rnn会出现最初始的信息被忽略，在反向传播的时候减小最开始时候的信息。

而造成梯度消失，也叫做梯度弥散

也有可能造成一开始的梯度改变之后无穷大，称为梯度爆炸

因此，普通rnn无法解决轴点记忆的问题

lstm rnn中多了输入，输出，忘记控制器

根据输入输出程度的重要性，加入循环神经网络中

pytorch实现

分类问题

import torch
from torch import nn
import torchvision.datasets as dsets
import torchvision.transforms as transforms
import matplotlib.pyplot as plt


# torch.manual_seed(1)    # reproducible

# Hyper Parameters
EPOCH = 1               # train the training data n times, to save time, we just train 1 epoch
BATCH_SIZE = 64
TIME_STEP = 28          # rnn time step / image height
INPUT_SIZE = 28         # rnn input size / image width
LR = 0.01               # learning rate
DOWNLOAD_MNIST = True   # set to True if haven't download the data


# Mnist digital dataset
train_data = dsets.MNIST(
    root='./mnist/',
    train=True,                         # this is training data
    transform=transforms.ToTensor(),    # Converts a PIL.Image or numpy.ndarray to
                                        # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
    download=DOWNLOAD_MNIST,            # download it if you don't have it
)

# plot one example
print(train_data.train_data.size())     # (60000, 28, 28)
print(train_data.train_labels.size())   # (60000)
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[0])
plt.show()

# Data Loader for easy mini-batch return in training
train_loader = torch.utils.data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

# convert test data into Variable, pick 2000 samples to speed up testing
test_data = dsets.MNIST(root='./mnist/', train=False, transform=transforms.ToTensor())
test_x = test_data.test_data.type(torch.FloatTensor)[:2000]/255.   # shape (2000, 28, 28) value in range(0,1)
test_y = test_data.test_labels.numpy()[:2000]    # covert to numpy array


class RNN(nn.Module):
    def __init__(self):
        super(RNN, self).__init__()

        self.rnn = nn.LSTM(         # if use nn.RNN(), it hardly learns
            input_size=INPUT_SIZE,
            hidden_size=64,         # rnn hidden unit
            num_layers=1,           # number of rnn layer
            batch_first=True,       # input & output will has batch size as 1s dimension. e.g. (batch, time_step, input_size)
        )

        self.out = nn.Linear(64, 10)

    def forward(self, x):
        # x shape (batch, time_step, input_size)
        # r_out shape (batch, time_step, output_size)
        # h_n shape (n_layers, batch, hidden_size)
        # h_c shape (n_layers, batch, hidden_size)
        r_out, (h_n, h_c) = self.rnn(x, None)   # None represents zero initial hidden state

        # choose r_out at the last time step
        out = self.out(r_out[:, -1, :])
        return out


rnn = RNN()
print(rnn)

out

RNN(
  (rnn): LSTM(28, 64, batch_first=True)
  (out): Linear(in_features=64, out_features=10, bias=True)
)

实现优化、训练

optimizer = torch.optim.Adam(rnn.parameters(), lr=LR)   # optimize all cnn parameters
loss_func = nn.CrossEntropyLoss()                       # the target label is not one-hotted

# training and testing
for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):        # gives batch data
        b_x = b_x.view(-1, 28, 28)              # reshape x to (batch, time_step, input_size)

        output = rnn(b_x)                               # rnn output
        loss = loss_func(output, b_y)                   # cross entropy loss
        optimizer.zero_grad()                           # clear gradients for this training step
        loss.backward()                                 # backpropagation, compute gradients
        optimizer.step()                                # apply gradients

        if step % 50 == 0:
            test_output = rnn(test_x)                   # (samples, time_step, input_size)
            pred_y = torch.max(test_output, 1)[1].data.numpy()
            accuracy = float((pred_y == test_y).astype(int).sum()) / float(test_y.size)
            print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy(), '| test accuracy: %.2f' % accuracy)

# print 10 predictions from test data
test_output = rnn(test_x[:10].view(-1, 28, 28))
pred_y = torch.max(test_output, 1)[1].data.numpy()
print(pred_y, 'prediction number')
print(test_y[:10], 'real number')

out

Epoch:  0 | train loss: 2.2896 | test accuracy: 0.12
Epoch:  0 | train loss: 0.8098 | test accuracy: 0.60
Epoch:  0 | train loss: 0.6983 | test accuracy: 0.73
Epoch:  0 | train loss: 0.5486 | test accuracy: 0.81
Epoch:  0 | train loss: 0.7209 | test accuracy: 0.85
Epoch:  0 | train loss: 0.2399 | test accuracy: 0.87
Epoch:  0 | train loss: 0.4179 | test accuracy: 0.90
Epoch:  0 | train loss: 0.5278 | test accuracy: 0.88
Epoch:  0 | train loss: 0.3201 | test accuracy: 0.90
Epoch:  0 | train loss: 0.1950 | test accuracy: 0.92
Epoch:  0 | train loss: 0.2301 | test accuracy: 0.92
Epoch:  0 | train loss: 0.1683 | test accuracy: 0.94
Epoch:  0 | train loss: 0.1188 | test accuracy: 0.93
Epoch:  0 | train loss: 0.0566 | test accuracy: 0.95
Epoch:  0 | train loss: 0.0941 | test accuracy: 0.94
Epoch:  0 | train loss: 0.3501 | test accuracy: 0.95
Epoch:  0 | train loss: 0.0342 | test accuracy: 0.93
Epoch:  0 | train loss: 0.0753 | test accuracy: 0.96
Epoch:  0 | train loss: 0.1507 | test accuracy: 0.96
[7 2 1 0 4 1 4 9 6 9] prediction number
[7 2 1 0 4 1 4 9 5 9] real number

回归问题

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

# torch.manual_seed(1)    # reproducible

# Hyper Parameters
TIME_STEP = 10  # rnn time step
INPUT_SIZE = 1  # rnn input size
LR = 0.02  # learning rate

# show data
steps = np.linspace(0, np.pi * 2, 100, dtype=np.float32)  # float32 for converting torch FloatTensor
x_np = np.sin(steps)
y_np = np.cos(steps)
plt.plot(steps, y_np, 'r-', label='target (cos)')
plt.plot(steps, x_np, 'b-', label='input (sin)')
plt.legend(loc='best')
plt.show()


class RNN(nn.Module):
    def __init__(self):
        super(RNN, self).__init__()

        self.rnn = nn.RNN(
            input_size=INPUT_SIZE,
            hidden_size=32,  # rnn hidden unit
            num_layers=1,  # number of rnn layer
            batch_first=True,  # input & output will has batch size as 1s dimension. e.g. (batch, time_step, input_size)
        )
        self.out = nn.Linear(32, 1)

    def forward(self, x, h_state):
        # x (batch, time_step, input_size)
        # h_state (n_layers, batch, hidden_size)
        # r_out (batch, time_step, hidden_size)
        r_out, h_state = self.rnn(x, h_state)

        outs = []  # save all predictions
        for time_step in range(r_out.size(1)):  # calculate output for each time step
            outs.append(self.out(r_out[:, time_step, :]))
        return torch.stack(outs, dim=1), h_state

        # instead, for simplicity, you can replace above codes by follows
        # r_out = r_out.view(-1, 32)
        # outs = self.out(r_out)
        # outs = outs.view(-1, TIME_STEP, 1)
        # return outs, h_state

        # or even simpler, since nn.Linear can accept inputs of any dimension
        # and returns outputs with same dimension except for the last
        # outs = self.out(r_out)
        # return outs


rnn = RNN()
print(rnn)

optimizer = torch.optim.Adam(rnn.parameters(), lr=LR)  # optimize all cnn parameters
loss_func = nn.MSELoss()

h_state = None  # for initial hidden state

plt.figure(1, figsize=(12, 5))
plt.ion()  # continuously plot

for step in range(100):
    start, end = step * np.pi, (step + 1) * np.pi  # time range
    # use sin predicts cos
    steps = np.linspace(start, end, TIME_STEP, dtype=np.float32,
                        endpoint=False)  # float32 for converting torch FloatTensor
    x_np = np.sin(steps)
    y_np = np.cos(steps)

    x = torch.from_numpy(x_np[np.newaxis, :, np.newaxis])  # shape (batch, time_step, input_size)
    y = torch.from_numpy(y_np[np.newaxis, :, np.newaxis])

    prediction, h_state = rnn(x, h_state)  # rnn output
    # !! next step is important !!
    h_state = h_state.data  # repack the hidden state, break the connection from last iteration

    loss = loss_func(prediction, y)  # calculate loss
    optimizer.zero_grad()  # clear gradients for this training step
    loss.backward()  # backpropagation, compute gradients
    optimizer.step()  # apply gradients

    # plotting
    plt.plot(steps, y_np.flatten(), 'r-')
    plt.plot(steps, prediction.data.numpy().flatten(), 'b-')
    plt.draw();
    plt.pause(0.05)

plt.ioff()
plt.show()

out

RNN(
  (rnn): RNN(1, 32, batch_first=True)
  (out): Linear(in_features=32, out_features=1, bias=True)
)

AutoEncoder（自编码）

先将原数据压缩，在进行解压得到输出

再将输出进行反向传递进行优化

是一种非监督学习，超过了PCA

压缩后得到的是编码器，掌握着原数据的精髓

强化学习

• Deep Q Network（DQN）
• GAN（无意义的随机数生成，互相提升）
• • generator生成数据，discriminator进行判别

torch是动态的

可以采用GPU加速

缓解过拟合（Over fitting）

增加一个drop层

net_dropped = torch.nn.Sequential(
	torch.nn.Linear(1, N_HIDDEN),
    torch.nn.Dropout(0.5), # 随即屏蔽掉一半的点，实现缓解过拟合
    torch.nn.ReLU(),
)

批标准化（Batch Normalization）

激励函数对较大数不敏感

这不仅仅在输入层，也在隐藏层中发生

批标准化在激励函数与下一层之间

分为标准化工序，反标准化工序

def __init__(self, batch_normalization=False):
    super(Net, self).__init__()
    self.do_bn = batch_normalization
    self.fns = []
    self.bns = []
    self.bn_input = nn.BatchNormal1d(1, momentum=0.5)
    
    for i in range(N_HIDDEN):
        input_size = 1 if i == 0 else 10
        fc = nn.Linear(input_size, 10)
        setattr(self, 'fc%i' % i, fc) # important
        self._set_init()
        
    self.predict = nn.Linear(10, 1)
    self._set_init(self.predict)