[尝试训练数据时使用pytorch大小不匹配

问题描述 投票:0回答:1

我真的是pytorch的新手,只是尝试使用自己的数据集来做一个简单的线性回归模型。我也只将数字值用作输入。

The CSV File I Imported

我已从CSV导入数据

dataset = pd.read_csv('mlb_games_overview.csv')

我将数据分为四个部分X_train,X_test,y_train,y_test

X = dataset.drop(['date', 'team', 'runs', 'win'], 1)
y = dataset['win']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=True)

我已将数据转换为pytorch张量

X_train = torch.from_numpy(np.array(X_train))
X_test = torch.from_numpy(np.array(X_test))
y_train = torch.from_numpy(np.array(y_train))
y_test = torch.from_numpy(np.array(y_test))

我已经创建了LinearRegressionModel

class LinearRegressionModel(torch.nn.Module):
    def __init__(self):
        super(LinearRegressionModel, self).__init__()
        self.linear = torch.nn.Linear(1, 1)
    def forward(self, x):
        y_pred = self.linear(x)
        return y_pred

我已经初始化了优化器和损失函数

criterion = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

现在,当我开始训练数据时,我得到运行时错误不匹配

EPOCHS = 500
for epoch in range(EPOCHS):
    pred_y = model(X_train) # RUNTIME ERROR HERE
    loss = criterion(pred_y, y_train)
    optimizer.zero_grad() # zero out gradients to update parameters correctly
    loss.backward() # backpropagation
    optimizer.step() # update weights
    print('epoch {}, loss {}'. format(epoch, loss.data[0]))

错误日志:

RuntimeError                              Traceback (most recent call last)
<ipython-input-40-c0474231d515> in <module>
  1 EPOCHS = 500
  2 for epoch in range(EPOCHS):
----> 3     pred_y = model(X_train)
  4     loss = criterion(pred_y, y_train)
  5     optimizer.zero_grad() # zero out gradients to update parameters correctly
RuntimeError: size mismatch, m1: [3540 x 8], m2: [1 x 1] at 
C:\w\1\s\windows\pytorch\aten\src\TH/generic/THTensorMath.cpp:752
machine-learning pytorch linear-regression tensor
1个回答
1
投票

在线性回归模型中,您具有:

self.linear = torch.nn.Linear(1, 1)

但是您的训练数据(X_train)形状为3540 x 8,这意味着您有8个代表每个输入示例的特征。因此,您应该按如下所示定义线性层。

self.linear = torch.nn.Linear(8, 1)

PyTorch中的linear layer具有参数Wb。如果将in_features设置为8,将out_features设置为1,则W矩阵的形状将为1 x 8b向量的长度将为1。

由于您的训练数据形状为3540 x 8,因此您可以执行以下操作。

linear_out = X_train W_T + b

我希望它能澄清您的困惑。

© www.soinside.com 2019 - 2024. All rights reserved.