我想在PyTorch中解决一个问题。我编写了以下代码，作为学习正弦函数的教程。
import torchfrom torch import nnfrom torch import optimfrom torch.autograd import Variable as Vfrom torch.utils.data import TensorDataset, DataLoaderimport numpy as np# y=sin(x1)numTrain = 512numTest = 128noiseScale = 0.01PI2 = 3.1415 * 2X_train = np.random.rand(numTrain,1) * PI2y_train = np.sin(X_train) + np.random.randn(numTrain,1) * noiseScale + 1.5X_test = np.random.rand(numTest,1) * PI2y_test = np.sin(X_test) + np.random.randn(numTest,1) * noiseScale# Construct DataSetX_trainT = torch.Tensor(X_train)y_trainT = torch.Tensor(y_train)X_testT = torch.Tensor(X_test)y_testT = torch.Tensor(y_test)ds_train = TensorDataset(X_trainT, y_trainT)ds_test = TensorDataset(X_testT, y_testT)# Construct DataLoaderloader_train = DataLoader(ds_train, batch_size=64, shuffle=True)loader_test = DataLoader(ds_test, batch_size=64, shuffle=False)# Construct networknet = nn.Sequential( nn.Linear(1,10), nn.ReLU(), nn.BatchNorm1d(10), nn.Linear(10,5), nn.ReLU(), nn.BatchNorm1d(5), nn.Linear(5,1),)optimizer = optim.Adam(net.parameters())loss_fn = nn.SmoothL1Loss()# Traininglosses = []net.train()for epoc in range(100): for data, target in loader_train: y_pred = net(data) loss = loss_fn(target,y_pred) optimizer.zero_grad() loss.backward() optimizer.step() losses.append(loss.data)# evaluation%matplotlib inlinefrom matplotlib import pyplot as plt#plt.plot(losses)plt.scatter(X_train, y_train)net.eval()sinsX = []sinsY = []for t in range(128): x = t/128 * PI2 output = net(V(torch.Tensor([x]))) sinsX.append(x) sinsY.append(output.detach().numpy())plt.scatter(sinsX,sinsY)训练过程没有错误，但接下来的这行代码引发了错误：“expected 2D or 3D input (got 1D input)”
output = net(V(torch.Tensor([x])))如果没有BatchNorm1d()，这个错误就不会发生。我觉得奇怪，因为输入是一维的。
如何修复这个问题呢？
谢谢。
更新：我是如何修复的
arr = np.array([x])output = net(V(torch.Tensor(arr[None,...])))回答：
在处理一维信号时，PyTorch实际上期望的是二维张量：第一个维度是“小批量”维度。因此，您应该在一个包含一个一维信号的批次上评估您的网络：
output = net(V(torch.Tensor([x[None, ...]]))在评估之前，请确保将您的网络设置为“评估”模式：
net.eval()