标签的时间片长度似乎不对

[KBDDEY]

data.shape:[23991,207]

x_train.shape:[23976, 1, 12, 207] y_train.shape:[23976, 207]

def data_transform(data, n_his, n_pred, device):
# produce data slices for x_data and y_data

n_vertex = data.shape[1]  # 207
len_record = len(data)  # 23991
num = len_record - n_his - n_pred # 23991-12-3 = 23976

x = np.zeros([num, 1, n_his, n_vertex])
y = np.zeros([num, n_vertex])

for i in range(num):
    head = i
    tail = i + n_his
    x[i, :, :, :] = data[head: tail].reshape(1, n_his, n_vertex)
    y[i] = data[tail + n_pred - 1]

return torch.Tensor(x).to(device), torch.Tensor(y).to(device)

这段代码生成的标签的时间片长度总为1
位置在script.dataloader.data_transform