Pytorch training loss function throws: "TypeError: 'Tensor' object is not callable"

Question

我使用 Python 3.x 和带有 GPU 的 pytorch 1.5.0。我正在尝试使用 mnist 数据编写一个简单的多项逻辑回归。

我的问题是 loss() 函数在遍历训练批次时抛出 TypeError: 'Tensor' object is not callable。令我困惑的是 错误没有出现在循环的第一次迭代中，但对于第二批，我得到以下完整错误：

Traceback (most recent call last):
  File "/snap/pycharm-community/207/plugins/python-ce/helpers/pydev/pydevd.py", line 1448, in _exec
    pydev_imports.execfile(file, globals, locals)  # execute the script
  File "/snap/pycharm-community/207/plugins/python-ce/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "/home/pytorch_tutorial/Pytorch_feed_fwd_310720.py", line 78, in <module>
    loss = loss(preds,ys)
TypeError: 'Tensor' object is not callable

这里的loss()函数就是loss = nn.CrossEntropyLoss()。完整代码如下。非常欢迎任何指点。

    for epoch in range(5):

        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            xs, ys = data
            opt.zero_grad()
            preds = net(xs)
            loss = loss(preds,ys)
            loss.backward()
            opt.step()

            # print statistics
            running_loss += loss.item()
            if i % 1000 == 999:  # print every 1000 mini-batches
                print('[%d, %5d] loss: %.3f' %
                      (epoch + 1, i + 1, running_loss / 2000))
                running_loss = 0.0

        print('epoch {}, loss {}'.format(epoch, loss.item()))

    a=1

Answer 1

因为你在本地循环设置loss

将loss = loss(preds, ys)更改为_loss = loss(preds, ys)

Pytorch training loss function throws: "TypeError: 'Tensor' object is not callable"

Pytorch training loss function throws: "TypeError: 'Tensor' object is not callable"

pytorch

tensor