Pytorch使用過程錯誤與解決

• error1：關鍵詞 copy tensor
• error2：關鍵詞 張量相加
• error3：關鍵詞 nn.Linear()的使用
• • 報錯1：
  • • 報錯代碼：
    • 錯誤原因：
  • 報錯2：
  • • 報錯代碼：
    • 錯誤原因：
  • 解決辦法
  • • 錯誤原因：
    • 正確代碼

error1：關鍵詞 copy tensor

報錯信息：

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).

解決辦法1：
*** 當轉換某個變量為tensor時，盡量使用torch.as_tensor()***

原錯誤代碼： state_tensor_list = [torch.tensor(i) for i in batch.state]修改為： state_tensor_list = [torch.as_tensor(i) for i in batch.state]

解決辦法2：
*** 當轉換某個變量x為tensor時，盡量使用x.clone().detach() or x.clone().detach().requires_grad_(True) ***

原錯誤代碼： state_tensor_list = [torch.tensor(i) for i in batch.state]修改為： state_tensor_list = [i.clone().detach() for i in batch.state]

error2：關鍵詞 張量相加

參考鏈接:

報錯信息：
RuntimeError: The size of tensor a (3) must match the size of tensor b (4) at non-singleton dimension 1
解決辦法：
檢查張量維度！！！

錯誤代碼 next_state_values = torch.tensor([0.7056, 0.7165, 0.6326]) state_action_values=torch.tensor([[ 0.1139, 0.1139, 0.1139, 0.1139],[ 0.0884, 0.0884, 0.0884, 0.0884],[ 0.0019, 0.0019, 0.0019, 0.0019]]) print(next_state_values.shape) print(state_action_values.shape) print(next_state_values.size()) print(state_action_values.size()) next_state_values + state_action_values結果： torch.Size([3]) torch.Size([3, 4]) torch.Size([3]) torch.Size([3, 4]) 修改代碼： next_state_values = torch.tensor([0.7056, 0.7165, 0.6326]) state_action_values=torch.tensor([[ 0.1139, 0.1139, 0.1139, 0.1139],[ 0.0884, 0.0884, 0.0884, 0.0884],[ 0.0019, 0.0019, 0.0019, 0.0019]]).max(1)[0] print(next_state_values.shape) print(state_action_values.shape) print(next_state_values.size()) print(state_action_values.size()) next_state_values + state_action_values結果： torch.Size([3]) torch.Size([3]) torch.Size([3]) torch.Size([3]) tensor([0.8195, 0.8049, 0.6345])

error3：關鍵詞 nn.Linear()的使用

參考鏈接:

報錯1：

報錯：RuntimeError: expected scalar type Long but found Float

報錯代碼：

import torch import torch.nn as nn class Net(nn.Module):def __init__(self,state_dim,mid_dim,action_dim):super().__init__()self.net = nn.Sequential(nn.Linear(state_dim, mid_dim))def forward(self,state):res = self.net(state)return res net = Net(9,5,4) print(net) current_state = torch.tensor([0,0,0,0,0,0,0,0,0]) print(current_state.shape) action = net(current_state) print(action)結果： Net((net): Sequential((0): Linear(in_features=9, out_features=5, bias=True)) ) torch.Size([9]) torch.Size([9])

錯誤原因：

將一維張量轉換成二維張量后才能輸入

報錯2：

報錯：RuntimeError: expected scalar type Float but found Long

報錯代碼：

import torch import torch.nn as nn class Net(nn.Module):def __init__(self,state_dim,mid_dim,action_dim):super().__init__()self.net = nn.Sequential(nn.Linear(state_dim, mid_dim))def forward(self,state):res = self.net(state)return res net = Net(9,5,4) print(net) current_state = torch.tensor([0,0,0,0,0,0,0,0,0]) print(current_state.shape) current_state = current_state.view(1,9) print(current_state.shape) action = net(current_state) print(action) 結果： Net((net): Sequential((0): Linear(in_features=9, out_features=5, bias=True)) ) torch.Size([9]) torch.Size([1, 9])

錯誤原因：

傳入的張量數據類型應該為float32

解決辦法

錯誤原因：

1、將張量轉為二維使用.view(1,shape)
2、指定張量數據類型 dtype=torch.float32

正確代碼

import torch import torch.nn as nn class Net(nn.Module):def __init__(self,state_dim,mid_dim,action_dim):super().__init__()self.net = nn.Sequential(nn.Linear(state_dim, mid_dim))def forward(self,state):res = self.net(state)return res net = Net(9,5,4) print(net) current_state = torch.tensor([0,0,0,0,0,0,0,0,0],**dtype=torch.float32**) print(current_state.shape) **current_state = current_state.view(1,9)** print(current_state.shape) action = net(current_state) print(action)

總結

以上是生活随笔為你收集整理的Pytorch使用过程错误与解决 -汇总~的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。