维度不匹配，求助大佬们！

在尝试写一个简单的神经网络训练代码，出现了这个报错信息。孩子被困住好几天了，有没有好心的大佬帮帮忙，在此先感谢了555

代码如下：

import pandas as pd
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim

file_path = 'test_file\\excel.xlsx'

train_day=7
pred_day=3
# train_num = train_day*24*60
# pre_num = pre_day*24*60

# 使用pandas的read_excel函数读取Excel文件
df = pd.read_excel(file_path,sheet_name='Sheet2')

x = df.iloc[:, 1].values
#x = x.reshape(-1, 1)
flow_data = torch.tensor(x, dtype=torch.float32)
print(len(flow_data))

class SimpleNN(nn.Module):
    def __init__(self):
        super(SimpleNN, self).__init__()
        # 第一层：输入层到第一个隐藏层
        self.layer1 = nn.Linear(train_day, 10)
        # 第二层：第一个隐藏层到第二个隐藏层
        self.layer2 = nn.Linear(10, 5)
        # 第三层：第二个隐藏层到输出层
        self.output_layer = nn.Linear(5, pred_day)
        # 激活函数
        self.relu = nn.ReLU()

    def forward(self, x):
        # 前向传播
        x = self.layer1(x)
        x = self.relu(x)
        x = self.layer2(x)
        x = self.relu(x)
        y_pred = self.output_layer(x)
        return y_pred

# 创建模型实例
flow_pre_model = SimpleNN()
# 定义损失函数和优化器
criterion = nn.MSELoss()
optimizer = optim.Adam(flow_pre_model.parameters())


# 初始化存储预测结果的列表
predictions = []

x_trains = []
y_trains = []

for i in range(0, len(flow_data) - pred_day, train_day):  # 每次迭代移动7个索引
    a = len(flow_data) - pred_day
    # 获取当前训练集和目标集
    x_train = torch.tensor(flow_data[i:i+train_day]).float()
    #y_train = torch.tensor(flow_data[i+train_day:i+train_day+pred_day]).float()
    y_train = torch.tensor(flow_data[i + train_day:i + train_day + pred_day]).float()


    #x_trains.append(x_train)
    #y_trains.append(y_train)

    # 训练模型
    for _ in range(100):  # 假设我们训练100个迭代
        optimizer.zero_grad()
        output = flow_pre_model(x_train)

        loss = criterion(output, y_train)
        loss.backward()
        optimizer.step()

    predictions.append(output.data.numpy())

print(predictions)

 报错信息：

C:\Users\hhl\.conda\envs\hhlpytorch\python.exe F:\Nonnetta\05code\flow_pre_hhl\flow_pre_hhl\data_loader.py 
100
F:\Nonnetta\05code\flow_pre_hhl\flow_pre_hhl\data_loader.py:59: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
  x_train = torch.tensor(flow_data[i:i+train_day]).float()
F:\Nonnetta\05code\flow_pre_hhl\flow_pre_hhl\data_loader.py:61: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
  y_train = torch.tensor(flow_data[i + train_day:i + train_day + pred_day]).float()
C:\Users\Raye\.conda\envs\hhlpytorch\Lib\site-packages\torch\nn\modules\loss.py:535: UserWarning: Using a target size (torch.Size([2])) that is different to the input size (torch.Size([3])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.
  return F.mse_loss(input, target, reduction=self.reduction)
Traceback (most recent call last):
  File "F:\Nonnetta\05code\flow_pre_hhl\flow_pre_hhl\data_loader.py", line 72, in <module>
    loss = criterion(output, y_train)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\hhl\.conda\envs\hhlpytorch\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\hhl\.conda\envs\hhlpytorch\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\hhl\.conda\envs\hhlpytorch\Lib\site-packages\torch\nn\modules\loss.py", line 535, in forward
    return F.mse_loss(input, target, reduction=self.reduction)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\hhl\.conda\envs\hhlpytorch\Lib\site-packages\torch\nn\functional.py", line 3338, in mse_loss
    expanded_input, expanded_target = torch.broadcast_tensors(input, target)
                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\hhl\.conda\envs\hhlpytorch\Lib\site-packages\torch\functional.py", line 76, in broadcast_tensors
    return _VF.broadcast_tensors(tensors)  # type: ignore[attr-defined]
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: The size of tensor a (3) must match the size of tensor b (2) at non-singleton dimension 0

进程已结束，退出代码为 1