[英]what is the pytorch equivalent of a tensorflow linear regression?
我正在学习 pytorch,要对这里以这种方式创建的数据进行基本的线性回归:
from sklearn.datasets import make_regression
x, y = make_regression(n_samples=100, n_features=1, noise=15, random_state=42)
y = y.reshape(-1, 1)
print(x.shape, y.shape)
plt.scatter(x, y)
我知道使用 tensorflow 这段代码可以解决:
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Dense(units=1, activation='linear', input_shape=(x.shape[1], )))
model.compile(optimizer=tf.keras.optimizers.SGD(lr=0.05), loss='mse')
hist = model.fit(x, y, epochs=15, verbose=0)
但我需要知道 pytorch 等价物会是什么样子,我试图做的是:
# Model Class
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.linear = nn.Linear(1,1)
def forward(self, x):
x = self.linear(x)
return x
def predict(self, x):
return self.forward(x)
model = Net()
loss_fn = F.mse_loss
opt = torch.optim.SGD(modelo.parameters(), lr=0.05)
# Funcao para treinar
def fit(num_epochs, model, loss_fn, opt, train_dl):
# Repeat for given number of epochs
for epoch in range(num_epochs):
# Train with batches of data
for xb, yb in train_dl:
# 1. Generate predictions
pred = model(xb)
# 2. Calculate Loss
loss = loss_fn(pred, yb)
# 3. Campute gradients
loss.backward()
# 4. Update parameters using gradients
opt.step()
# 5. Reset the gradients to zero
opt.zero_grad()
# Print the progress
if (epoch+1) % 10 == 0:
print('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, loss.item()))
# Training
fit(200, model, loss_fn, opt, data_loader)
但是模型没有学到任何东西,我不知道我还能做什么。
输入/输出尺寸为 (1/1)
首先,你应该定义torch.utils.data.Dataset
import torch
from sklearn.datasets import make_regression
class RegressionDataset(torch.utils.data.Dataset):
def __init__(self):
data = make_regression(n_samples=100, n_features=1, noise=0.1, random_state=42)
self.x = torch.from_numpy(data[0]).float()
self.y = torch.from_numpy(data[1]).float()
def __len__(self):
return len(self.x)
def __getitem__(self, index):
return self.x[index], self.y[index]
它可以转换numpy
数据PyTorch的tensor
内__init__
和将数据转换为float
( numpy
具有double
默认而PyTorch的默认值是float
,以使用更少的内存)。
除此之外,它将简单地返回特征tuple
和各自的回归目标。
差不多了,但是您必须使模型的输出变平(如下所述)。 torch.nn.Linear
将返回形状为(batch, 1)
张量,而您的目标的形状为(batch,)
。 flatten()
将删除不必要的1
维。
# 2. Calculate Loss
loss = criterion(pred.flatten(), yb)
这就是你真正需要的:
model = torch.nn.Linear(1, 1)
任何层都可以直接调用,简单模型不需要forward
和继承。
剩下的几乎没问题,你只需要创建torch.utils.data.DataLoader
并传递我们数据集的实例。 DataLoader
作用是多次发出dataset
__getitem__
并创建一批指定大小的(还有一些其他有趣的事情,但这就是想法):
dataset = RegressionDataset()
dataloader = torch.utils.data.DataLoader(dataset, batch_size=32)
model = torch.nn.Linear(1, 1)
criterion = torch.nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=3e-4)
fit(5000, model, criterion, optimizer, dataloader)
另请注意,我使用了torch.nn.MSELoss()
,因为我们正在传递对象,在这种情况下它看起来比函数更好。
为了使它更容易:
import torch
from sklearn.datasets import make_regression
class RegressionDataset(torch.utils.data.Dataset):
def __init__(self):
data = make_regression(n_samples=100, n_features=1, noise=0.1, random_state=42)
self.x = torch.from_numpy(data[0]).float()
self.y = torch.from_numpy(data[1]).float()
def __len__(self):
return len(self.x)
def __getitem__(self, index):
return self.x[index], self.y[index]
# Funcao para treinar
def fit(num_epochs, model, criterion, optimizer, train_dl):
# Repeat for given number of epochs
for epoch in range(num_epochs):
# Train with batches of data
for xb, yb in train_dl:
# 1. Generate predictions
pred = model(xb)
# 2. Calculate Loss
loss = criterion(pred.flatten(), yb)
# 3. Compute gradients
loss.backward()
# 4. Update parameters using gradients
optimizer.step()
# 5. Reset the gradients to zero
optimizer.zero_grad()
# Print the progress
if (epoch + 1) % 10 == 0:
print(
"Epoch [{}/{}], Loss: {:.4f}".format(epoch + 1, num_epochs, loss.item())
)
dataset = RegressionDataset()
dataloader = torch.utils.data.DataLoader(dataset, batch_size=32)
model = torch.nn.Linear(1, 1)
criterion = torch.nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=3e-4)
fit(5000, model, criterion, optimizer, dataloader)
你应该得到大约0.053
损失,改变noise
或其他参数以实现更难/更容易的回归任务。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.