Python 使用PyTorch手动指定权重
我使用Python3.8和PyTorch 1.7手动分配和更改神经网络的权重和偏差。作为一个例子,我定义了一个LeNet-300-100完全连接的神经网络来在MNIST数据集上进行训练。类定义的代码是:Python 使用PyTorch手动指定权重,python,neural-network,pytorch,Python,Neural Network,Pytorch,我使用Python3.8和PyTorch 1.7手动分配和更改神经网络的权重和偏差。作为一个例子,我定义了一个LeNet-300-100完全连接的神经网络来在MNIST数据集上进行训练。类定义的代码是: class LeNet300(nn.Module): def __init__(self): super(LeNet300, self).__init__() # Define layers- self.fc1 = nn.
class LeNet300(nn.Module):
def __init__(self):
super(LeNet300, self).__init__()
# Define layers-
self.fc1 = nn.Linear(in_features = input_size, out_features = 300)
self.fc2 = nn.Linear(in_features = 300, out_features = 100)
self.output = nn.Linear(in_features = 100, out_features = 10)
self.weights_initialization()
def forward(self, x):
out = F.relu(self.fc1(x))
out = F.relu(self.fc2(out))
return self.output(out)
def weights_initialization(self):
'''
When we define all the modules such as the layers in '__init__()'
method above, these are all stored in 'self.modules()'.
We go through each module one by one. This is the entire network,
basically.
'''
for m in self.modules():
if isinstance(m, nn.Linear):
nn.init.xavier_normal_(m.weight)
nn.init.constant_(m.bias, 0)
尝试更改此模型的权重的步骤-
# Instantiate model-
mask_model = LeNet300()
为了将每个层中的所有权重分配给一(1),我使用代码-
with torch.no_grad():
for layer in mask_model.state_dict():
mask_model.state_dict()[layer] = nn.parameter.Parameter(torch.ones_like(mask_model.state_dict()[layer]))
# Sanity check-
mask_model.state_dict()['fc1.weight']
for param in mask_model.parameters():
# print(param.shape)
param = nn.parameter.Parameter(torch.ones_like(param))
此输出显示权重不等于1
我也试过代码-
with torch.no_grad():
for layer in mask_model.state_dict():
mask_model.state_dict()[layer] = nn.parameter.Parameter(torch.ones_like(mask_model.state_dict()[layer]))
# Sanity check-
mask_model.state_dict()['fc1.weight']
for param in mask_model.parameters():
# print(param.shape)
param = nn.parameter.Parameter(torch.ones_like(param))
但这并不奏效
帮助?我用一种非常简单的方法(只使用了
fill()
)代码如下:
import torch
import torch.nn as nn
class LeNet300(nn.Module):
def __init__(self):
super(LeNet300, self).__init__()
# Define layers-
self.fc1 = nn.Linear(in_features = 28, out_features = 300)
self.fc2 = nn.Linear(in_features = 300, out_features = 100)
self.output = nn.Linear(in_features = 100, out_features = 10)
self.weights_initialization()
def forward(self, x):
out = F.relu(self.fc1(x))
out = F.relu(self.fc2(out))
return self.output(out)
def weights_initialization(self):
'''
When we define all the modules such as the layers in '__init__()'
method above, these are all stored in 'self.modules()'.
We go through each module one by one. This is the entire network,
basically.
'''
for m in self.modules():
if isinstance(m, nn.Linear):
nn.init.xavier_normal_(m.weight)
nn.init.constant_(m.bias, 0)
mask_model = LeNet300()
with torch.no_grad():
for layer in mask_model.state_dict():
print(layer)
#print(torch.ones_like(mask_model.state_dict()[layer].data))
mask_model.state_dict()[layer].data.fill_(1)
mask_model.state_dict()['fc1.weight']
# tensor([[1., 1., 1., ..., 1., 1., 1.],
# [1., 1., 1., ..., 1., 1., 1.],
# [1., 1., 1., ..., 1., 1., 1.],
# ...,
# [1., 1., 1., ..., 1., 1., 1.],
# [1., 1., 1., ..., 1., 1., 1.],
# [1., 1., 1., ..., 1., 1., 1.]])