访问由多层感知器构建的神经网络模型的权重的火炬错误

Posted 2023-03-29

【中文标题】访问由多层感知器构建的神经网络模型的权重的火炬错误

【英文标题】：torch error of accessing weights of a neural network model built by multiple layer perceptrons

【发布时间】：2021-03-04 21:57:47

【问题描述】：

我正在尝试访问由torch 在databricks 上构建的神经网络模型的权重。

代码：

 import torch
 import torch.nn as nn
 import numpy 

 class Feedforward(nn.Module):

     def __init__(self, input_size, hidden_size):
         super(Feedforward, self).__init__()
         self.input_size = input_size
         self.hidden_size  = hidden_size
         self.fc1 = nn.Linear(self.input_size, self.hidden_size)
         self.relu = nn.ReLU()
         self.fc2 = nn.Linear(self.hidden_size, 1)
         self.sigmoid = nn.Sigmoid()

     def forward(self, x):
         hidden = self.fc1(x)
         relu = self.relu(hidden)
         output = self.fc2(relu)
         output = self.sigmoid(output)
         return output

from sklearn.datasets import make_blobs
def blob_label(y, label, loc): # assign labels
    target = numpy.copy(y)
    for l in loc:
        target[y == l] = label
    return target

x_train, y_train = make_blobs(n_samples=40, n_features=2, cluster_std=1.5, shuffle=True)
x_train = torch.FloatTensor(x_train)
y_train = torch.FloatTensor(blob_label(y_train, 0, [0]))
y_train = torch.FloatTensor(blob_label(y_train, 1, [1,2,3]))

x_test, y_test = make_blobs(n_samples=10, n_features=2, cluster_std=1.5, shuffle=True)
x_test = torch.FloatTensor(x_test)
y_test = torch.FloatTensor(blob_label(y_test, 0, [0]))
y_test = torch.FloatTensor(blob_label(y_test, 1, [1,2,3]))

model = Feedforward(2, 10)
criterion = torch.nn.BCELoss()
optimizer = torch.optim.SGD(model.parameters(), lr = 0.01)

y_pred = model(x_test)
before_train = criterion(y_pred.squeeze(), y_test)
print('Test loss before training' , before_train.item())

model.train()
epoch = 20
for epoch in range(epoch):
    optimizer.zero_grad()
    # Forward pass
    y_pred = model(x_train)
    # Compute Loss
    loss = criterion(y_pred.squeeze(), y_train)

print('Epoch : train loss: '.format(epoch, loss.item()))
# Backward pass
loss.backward()
optimizer.step()

model.eval()
y_pred = model(x_test)
after_train = criterion(y_pred.squeeze(), y_test) 
print('Test loss after Training' , after_train.item())

代码运行良好。但是，当我尝试访问模型的权重时，我得到了错误：

 model.weight # ModuleAttributeError: 'Feedforward' object has no attribute 'weight'

但是，如果我尝试过

model.fc1.weight

效果很好..

如何获取由多层感知器构建的模型的权重？

此帖Can't init the weights of my neural network PyTorch 对我不起作用。

谢谢

【参考方案1】：

因为有属性的是nn.Linear()，而不是Feedforward，试试改

class Feedforward(nn.Module):

     def __init__(self, input_size, hidden_size):
         super(Feedforward, self).__init__()
         self.input_size = input_size
         self.hidden_size  = hidden_size
         self.fc1 = nn.Linear(self.input_size, self.hidden_size)
         self.relu = nn.ReLU()
         self.fc2 = nn.Linear(self.hidden_size, 1)
         self.sigmoid = nn.Sigmoid()

到

class Feedforward(nn.Module):

     def __init__(self, input_size, hidden_size):
         super(nn.Linear, self).__init__()
         self.input_size = input_size
         self.hidden_size  = hidden_size
         self.fc1 = nn.Linear(self.input_size, self.hidden_size)
         self.relu = nn.ReLU()
         self.fc2 = nn.Linear(self.hidden_size, 1)
         self.sigmoid = nn.Sigmoid()

【讨论】：

您好，我已经尝试了您的建议。我收到错误“TypeError: super(type, obj): obj must be an instance or subtype of type”。谢谢