using pytorch for Gradient Descent

Question

my code:

import torch import torch.nn as nn import torch.nn.functional as F class MultivariateLinearRegressionModel(nn.Module): def __init__(self): super().__init__() self.linear = nn.Linear(3,1) def forward(self,x): # print(1) return self.linear(x) x_train = torch.FloatTensor([[73,80,75], [93,88,93], [89,91,90], [96,98,100], [73,66,70]]) y_train = torch.FloatTensor([[152],[185],[180],[196], [142]]) model = MultivariateLinearRegressionModel() optimizer = torch.optim.SGD(model.parameters(), lr = 1e-5) # print(222) ep = 2000 for epoch in range(ep+1): hypothesis = model(x_train) cost = F.mse_loss(hypothesis, y_train) if epoch % 100 == 0: print('Epoch {:4d}/{} Cost: {:.6f}'.format( epoch, 2000, cost.item() )) optimizer.zero_grad() cost.backward() optimizer.step()

my problem:

this code is my own MultivariateLinearRegressionModel.

But in the for loop hypothesis = model(x_train) why this code is same with hypothesis = model.forward(x_train) ??

i don't know why this 2 code statement is same. is this a python grammar??

Toan T · Accepted Answer · 2021-06-27 13:48:34Z

Because your model MultivariateLinearRegressionModel is inherited from nn.Module so when ever you call model(x_train), it will automatically execute the forward function which is defined in MultivariateLinearRegressionModel class.

That's why model(x_train) and model.forward(x_train) give the same result.

Collectives™ on Stack Overflow

using pytorch for Gradient Descent

1 Answer 1

Comments

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Related