Question

我正在尝试在Pytorch中创建一个基本的二元分类器，用于分类我的玩家是在游戏Pong中的右侧还是左侧进行游戏。输入是1x42x42图像，标签是我的播放器侧（右= 1或左= 2）。代码：

class Net(nn.Module):
    def __init__(self, input_size, hidden_size, num_classes):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(input_size, hidden_size)
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(hidden_size, num_classes)

    def forward(self, x):
        out = self.fc1(x)
        out = self.relu(out)
        out = self.fc2(out)
        return out

net = Net(42 * 42, 100, 2)

# Loss and Optimizer
criterion = nn.CrossEntropyLoss()
optimizer_net = torch.optim.Adam(net.parameters(), 0.001)
net.train()

while True:
    state = get_game_img()
    state = torch.from_numpy(state)

    # right = 1, left = 2
    current_side = get_player_side()
    target = torch.LongTensor(current_side)
    x = Variable(state.view(-1, 42 * 42))
    y = Variable(target)
    optimizer_net.zero_grad()
    y_pred = net(x)
    loss = criterion(y_pred, y)
    loss.backward()
    optimizer.step()

我得到的错误：

  File "train.py", line 109, in train
    loss = criterion(y_pred, y)
  File "/home/shani/anaconda2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 206, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/shani/anaconda2/lib/python2.7/site-packages/torch/nn/modules/loss.py", line 321, in forward
    self.weight, self.size_average)
  File "/home/shani/anaconda2/lib/python2.7/site-packages/torch/nn/functional.py", line 533, in cross_entropy
    return nll_loss(log_softmax(input), target, weight, size_average)
  File "/home/shani/anaconda2/lib/python2.7/site-packages/torch/nn/functional.py", line 501, in nll_loss
    return f(input, target)
  File "/home/shani/anaconda2/lib/python2.7/site-packages/torch/nn/_functions/thnn/auto.py", line 41, in forward
    output, *self.additional_args)
RuntimeError: Assertion `cur_target >= 0 && cur_target < n_classes' failed.  at /py/conda-bld/pytorch_1493676237139/work/torch/lib/THNN/generic/ClassNLLCriterion.c:57

Answer 1

对于大多数deeplearning库，目标（或标签）应从0开始。

这意味着您的目标应该在[0，n]范围内，具有n级。

Answer 2

看起来PyTorch希望得到零基标签（在你的情况下是0/1），你可能用一个基础的标签（1/2）来喂它

Answer 3

我的程序中存在相同的错误，我只是意识到问题出在我的神经网络中的输出节点数上

在我的程序中，模型的输出节点数不等于数据集中的标签数

输出数量为1，目标标签数量为10。然后我将输出数量更改为10，没有错误

PyTorch RuntimeError：断言`cur_target＆gt; = 0＆amp;＆amp; cur_target＆lt; n_classes＆＃39;失败

3 个答案: