英文:
Python doesn't know the class attributes, while Jupyter does
问题
我有StatQuest频道的这段代码。这段代码在Jupyter中运行正常，但当我在一个.py文件中运行时，报告错误：
AttributeError: 'BasicNNTrain'对象没有'w00'属性。
这是代码：
import torchimport torch.nn as nnimport torch.nn.functional as Ffrom torch.optim import SGDimport matplotlib.pyplot as pltimport seaborn as snsclass BasicNNTrain(nn.Module):def __int__(self):super().__init__()self.w00 = nn.Parameter(torch.tensor(1.7), requires_grad=False)self.b00 = nn.Parameter(torch.tensor(-0.85), requires_grad=False)self.w01 = nn.Parameter(torch.tensor(-40.8), requires_grad=False)self.w10 = nn.Parameter(torch.tensor(12.6), requires_grad=False)self.b10 = nn.Parameter(torch.tensor(0.0), requires_grad=False)self.w11 = nn.Parameter(torch.tensor(2.7), requires_grad=False)self.final_bias = nn.Parameter(torch.tensor(0.0), requires_grad=True)def forward(self, input):input_to_top_relu = input * self.w00 + self.b00top_relu_output = F.relu(input_to_top_relu)scaled_top_relu_output = top_relu_output * self.w01input_to_bottom_relu = input * self.w10 + self.b10bottom_relu_output = F.relu(input_to_bottom_relu)scaled_bottom_relu_output = bottom_relu_output * this.w11input_to_final_relu = scaled_top_relu_output + scaled_bottom_relu_output + this.final_biasoutput = F.relu(input_to_final_relu)return outputmodel = BasicNNTrain()for name, param in model.named_parameters():print(name, param.data)input_doses = torch.linspace(start=0, end=1, steps=11)print(input_doses)model(input_doses)
注意：上述代码有一个拼写错误，将 "this" 替换为 "self"，以修复错误。
英文:
I have this code from StatQuest channel. This code works in Jupyter, however when I run this in a .py file, it reports the error
>AttributeError: 'BasicNNTrain' object has no attribute 'w00'
This is the code:
import torchimport torch.nn as nnimport torch.nn.functional as Ffrom torch.optim import SGDimport matplotlib.pyplot as pltimport seaborn as snsclass BasicNNTrain(nn.Module):def __int__(self):super().__init__()self.w00 = nn.Parameter(torch.tensor(1.7), requires_grad=False)self.b00 = nn.Parameter(torch.tensor(-0.85), requires_grad=False)self.w01 = nn.Parameter(torch.tensor(-40.8), requires_grad=False)self.w10 = nn.Parameter(torch.tensor(12.6), requires_grad=False)self.b10 = nn.Parameter(torch.tensor(0.0), requires_grad=False)self.w11 = nn.Parameter(torch.tensor(2.7), requires_grad=False)self.final_bias = nn.Parameter(torch.tensor(0.0), requires_grad=True)def forward(self, input):input_to_top_relu = input * self.w00 + self.b00top_relu_output = F.relu(input_to_top_relu)scaled_top_relu_output = top_relu_output * self.w01input_to_bottom_relu = input * self.w10 + self.b10bottom_relu_output = F.relu(input_to_bottom_relu)scaled_bottom_relu_output = bottom_relu_output * self.w11input_to_final_relu = scaled_top_relu_output + scaled_bottom_relu_output + self.final_biasoutput = F.relu(input_to_final_relu)return outputmodel = BasicNNTrain()for name, param in model.named_parameters():print(name, param.data)input_doses = torch.linspace(start=0, end=1, steps=11)print(input_doses)model(input_doses)
答案1
得分: 1
可能是因为def __int__ 中的拼写错误？
英文:
Probably because of the typo in def __int__ ?
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库，让每个人都能够通过互相帮助和分享经验来进步。
评论