[英]what is the pytorch equivalent of a tensorflow linear regression?
我正在學習 pytorch,要對這里以這種方式創建的數據進行基本的線性回歸:
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 這段代碼可以解決:
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 等價物會是什么樣子,我試圖做的是:
# 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)
但是模型沒有學到任何東西,我不知道我還能做什么。
輸入/輸出尺寸為 (1/1)
首先,你應該定義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]
它可以轉換numpy
數據PyTorch的tensor
內__init__
和將數據轉換為float
( numpy
具有double
默認而PyTorch的默認值是float
,以使用更少的內存)。
除此之外,它將簡單地返回特征tuple
和各自的回歸目標。
差不多了,但是您必須使模型的輸出變平(如下所述)。 torch.nn.Linear
將返回形狀為(batch, 1)
張量,而您的目標的形狀為(batch,)
。 flatten()
將刪除不必要的1
維。
# 2. Calculate Loss
loss = criterion(pred.flatten(), yb)
這就是你真正需要的:
model = torch.nn.Linear(1, 1)
任何層都可以直接調用,簡單模型不需要forward
和繼承。
剩下的幾乎沒問題,你只需要創建torch.utils.data.DataLoader
並傳遞我們數據集的實例。 DataLoader
作用是多次發出dataset
__getitem__
並創建一批指定大小的(還有一些其他有趣的事情,但這就是想法):
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)
另請注意,我使用了torch.nn.MSELoss()
,因為我們正在傳遞對象,在這種情況下它看起來比函數更好。
為了使它更容易:
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)
你應該得到大約0.053
損失,改變noise
或其他參數以實現更難/更容易的回歸任務。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.