Pytorch菜鸟入门（5）——RNN入门【代码】

• 本系列文章为小白针对Morvan的课程中Pytorch学习过程中理解和记录，用于自己复习回顾，可参考。

数据

用的是下图数据，已知数据输入的sin值，来预测cos值

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()

搭建RNN

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

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
    print("loss:",step,":",loss)
    optimizer.zero_grad()  # clear gradients for this training step
    loss.backward()  # backpropagation, compute gradients
    optimizer.step()  # apply gradients

forward方法定义了模型的输入输出和数据在模型中的流动方向。过程如下：

• 模型输入参数【x】和【h_n】被输入到Rnn中，Rnn结果将返回2个Tensor：计算的结果【r_out】和新的隐藏层状态【h_n】
• for循环将Rnn的输出【r_out】按照step的顺序输入到Linear层中，每个step的Linear输出将追加到类型为tensor的列表【outs】中
• 将【outs】（通过torch.stack方法）中的内容堆叠到一个Tensor中，与新的隐藏层状态【h_n】一起作为forward的返回值被返回。

torch.nn.Rnn输入输出值格式

因为在创建Rnn时，batch_first参数被设置为true，所以Forward方法中Rnn的输入值【x】和输出值【r_out】的shape为[batch_size, time_step, feature]。这两个Tensor的第1维是训练的批次batch，第2维是rnn的输入序列，第3维是每次输入Rnn或Rnn输出的特征向量。举个例子：

实验结果

画图

plt.plot(steps, y_np.flatten(), 'r-')
plt.plot(steps, prediction.data.numpy().flatten(), 'b-')
plt.show()

代码

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
    print("loss:",step,":",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.show()
    # plt.draw();
#     plt.pause(0.05)
#
# plt.ioff()