一、线性回归模型使用Pytorch的简洁实现
生成数据集
num_inputs = 2
num_examples = 1000
true_w = [2, -3.4]
true_b = 4.2
features = torch.tensor(np.random.normal(0, 1, (num_examples, num_inputs)), dtype=torch.float)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)
读取数据集
import torch.utils.data as Data
batch_size = 10
# combine featues and labels of dataset
dataset = Data.TensorDataset(features, labels)
# put dataset into DataLoader
data_iter = Data.DataLoader(
dataset=dataset, # torch TensorDataset format
batch_size=batch_size, # mini batch size
shuffle=True, # whether shuffle the data or not
num_workers=2, # read data in multithreading
)
定义模型
class LinearNet(nn.Module):
def __init__(self, n_feature):
super(LinearNet, self).__init__() # call father function to init
self.linear = nn.Linear(n_feature, 1) # function prototype: `torch.nn.Linear(in_features, out_features, bias=True)`
def forward(self, x):
y = self.linear(x)
return y
net = LinearNet(num_inputs)
初始化模型参数
from torch.nn import init
init.normal_(net[0].weight, mean=0.0, std=0.01)
init.constant_(net[0].bias, val=0.0)
定义损失函数和优化函数
loss=nn.MSELoss()
import torch.optim as optim
optimizer = optim.SGD(net.parameters(), lr=0.03) # built-in random gradient descent function
print(optimizer)
训练
num_epochs = 3
for epoch in range(1, num_epochs + 1):
for X, y in data_iter:
output = net(X)
l = loss(output, y.view(-1, 1))
optimizer.zero_grad() # reset gradient, equal to net.zero_grad()
l.backward()
optimizer.step()
print('epoch %d, loss: %f' % (epoch, l.item()))
dense = net[0]
二、循环神经网络的pytorch简洁实现
nn.RNN
我们使用Pytorch中的nn.RNN来构造循环神经网络。
重点关注nn.RNN的以下几个构造函数参数：
input_size - The number of expected features in the input x
hidden_size – The number of features in the hidden state h
nonlinearity – The non-linearity to use. Can be either 'tanh' or 'relu'. Default: 'tanh'
batch_first – If True, then the input and output tensors are provided as (batch_size, num_steps, input_size). Default: False
这里的batch_first决定了输入的形状，我们使用默认的参数False，对应的输入形状是 (num_steps, batch_size, input_size)。
forward函数的参数为：
input of shape (num_steps, batch_size, input_size): tensor containing the features of the input sequence.
h_0 of shape (num_layers * num_directions, batch_size, hidden_size): tensor containing the initial hidden state for each element in the batch. Defaults to zero if not provided. If the RNN is bidirectional, num_directions should be 2, else it should be 1.
forward函数的返回值是：
output of shape (num_steps, batch_size, num_directions * hidden_size): tensor containing the output features (h_t) from the last layer of the RNN, for each t.
h_n of shape (num_layers * num_directions, batch_size, hidden_size): tensor containing the hidden state for t = num_steps.
定义模型
RNN模型的构造
class RNNModel(nn.Module):
def __init__(self, rnn_layer, vocab_size):
super(RNNModel, self).__init__()
self.rnn = rnn_layer
self.hidden_size = rnn_layer.hidden_size * (2 if rnn_layer.bidirectional else 1)
self.vocab_size = vocab_size
self.dense = nn.Linear(self.hidden_size, vocab_size)
def forward(self, inputs, state):
# inputs.shape: (batch_size, num_steps)
X = to_onehot(inputs, vocab_size)
X = torch.stack(X) # X.shape: (num_steps, batch_size, vocab_size)
hiddens, state = self.rnn(X, state)
hiddens = hiddens.view(-1, hiddens.shape[-1]) # hiddens.shape: (num_steps * batch_size, hidden_size)
output = self.dense(hiddens)
return output, state
预测函数的构造
def predict_rnn_pytorch(prefix, num_chars, model, vocab_size, device, idx_to_char,
char_to_idx):
state = None
output = [char_to_idx[prefix[0]]] # output记录prefix加上预测的num_chars个字符
for t in range(num_chars + len(prefix) - 1):
X = torch.tensor([output[-1]], device=device).view(1, 1)
(Y, state) = model(X, state) # 前向计算不需要传入模型参数
if t < len(prefix) - 1:
output.append(char_to_idx[prefix[t + 1]])
else:
output.append(Y.argmax(dim=1).item())
return ''.join([idx_to_char[i] for i in output])
训练函数的构造
def train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
corpus_indices, idx_to_char, char_to_idx,
num_epochs, num_steps, lr, clipping_theta,
batch_size, pred_period, pred_len, prefixes):
loss = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=lr)
model.to(device)
for epoch in range(num_epochs):
l_sum, n, start = 0.0, 0, time.time()
data_iter = d2l.data_iter_consecutive(corpus_indices, batch_size, num_steps, device) # 相邻采样
state = None
for X, Y in data_iter:
if state is not None:
# 使用detach函数从计算图分离隐藏状态
if isinstance (state, tuple): # LSTM, state:(h, c)
state[0].detach_()
state[1].detach_()
else:
state.detach_()
(output, state) = model(X, state) # output.shape: (num_steps * batch_size, vocab_size)
y = torch.flatten(Y.T)
l = loss(output, y.long())
optimizer.zero_grad()
l.backward()
grad_clipping(model.parameters(), clipping_theta, device)
optimizer.step()
l_sum += l.item() * y.shape[0]
n += y.shape[0]
if (epoch + 1) % pred_period == 0:
print('epoch %d, perplexity %f, time %.2f sec' % (
epoch + 1, math.exp(l_sum / n), time.time() - start))
for prefix in prefixes:
print(' -', predict_rnn_pytorch(
prefix, pred_len, model, vocab_size, device, idx_to_char,
char_to_idx))
训练函数
num_epochs, batch_size, lr, clipping_theta = 250, 32, 1e-3, 1e-2
pred_period, pred_len, prefixes = 50, 50, ['分开', '不分开']
train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
corpus_indices, idx_to_char, char_to_idx,
num_epochs, num_steps, lr, clipping_theta,
batch_size, pred_period, pred_len, prefixes)
