class pu_fc(nn.Module):
def __init__(self, input_dim):
super(pu_fc, self).__init__()
self.input_dim = input_dim
self.fc1 = nn.Linear(input_dim, 50)
self.fc2 = nn.Linear(50, 2)
self.loss_fn = custom_NLL()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
self.bias = torch.autograd.Variable(torch.rand(1,1), requires_grad=True).to(device)
def forward(self, x):
out = self.fc1(x)
out = F.relu(out, inplace=True)
out = self.fc2(out)
out[..., 1] = out[..., 1] + self.bias
print('bias: ', self.bias)
return out正如您从代码中看到的,我想向第二个输出通道添加一个偏置项。但是,我的实现不起作用。偏置项根本不会更新。它在训练过程中保持不变,我认为它在训练过程中是不可学习的。所以问题是,我如何才能让偏置术语变得可学?有可能做到这一点吗?下面是训练过程中偏差的一些输出。任何提示都将不胜感激,提前谢谢!
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
Current Epoch: 1
Epoch loss: 0.4424589276313782
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
Current Epoch: 2
Epoch loss: 0.3476297199726105
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)
bias: tensor([[0.0930]], device='cuda:0', grad_fn=<CopyBackwards>)发布于 2020-06-20 22:30:28
bias应为nn.Parameter。作为参数意味着它将在model.parameters()中显示,并在调用model.to(device)时自动传输到指定的设备。
self.bias = nn.Parameter(torch.rand(1,1))注意:不要使用Variable,它在2年前发布的PyTorch 0.4.0中已被弃用,它的所有功能都已合并到张量中。
https://stackoverflow.com/questions/62487029
复制相似问题