pytorch 在网络中添加可训练参数,修改预训练权重文件的方法

# -*- coding: utf-8 -*-
import torch
from torch.autograd import Variable
import torch.optim as optim
 
x = Variable(torch.FloatTensor([1, 2, 3])).cuda()
y = Variable(torch.FloatTensor([4, 5])).cuda()
 
class MLP(torch.nn.Module):
  def __init__(self):
    super(MLP, self).__init__()
    self.linear1 = torch.nn.Linear(3, 5)
    self.relu = torch.nn.ReLU()
    self.linear2 = torch.nn.Linear(5, 2)
 
  def forward(self, x):
    x = self.linear1(x)
    x = self.relu(x)
    x = self.linear2(x)
 
    return x
 
model = MLP().cuda()
 
loss_fn = torch.nn.MSELoss(size_average=False)
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)
 
for t in range(500):
  y_pred = model(x)
  loss = loss_fn(y_pred, y)
  print(t, loss.data[0])
  model.zero_grad()
  loss.backward()
  optimizer.step()
 
print(model(x))

class MLP(torch.nn.Module):
  def __init__(self):
    super(MLP, self).__init__()
    self.linear1 = torch.nn.Linear(3, 5)
    self.relu = torch.nn.ReLU()
    self.linear2 = torch.nn.Linear(5, 2)
    # the para to be added and updated in train phase, note that NO cuda() at last
    self.coefficient = torch.nn.Parameter(torch.Tensor([1.55]))
 
  def forward(self, x):
    x = self.linear1(x)
    x = self.relu(x)
    x = self.coefficient * x
    x = self.linear2(x)
 
    return x

print(model.state_dict().keys())
for i, j in model.named_parameters():
  print(i)
  print(j)

odict_keys(['linear1.weight', 'linear1.bias', 'linear2.weight', 'linear2.bias'])
linear1.weight
Parameter containing:
-0.3582 -0.0283 0.2607
 0.5190 -0.2221 0.0665
-0.2586 -0.3311 0.1927
-0.2765 0.5590 -0.2598
 0.4679 -0.2923 -0.3379
[torch.cuda.FloatTensor of size 5x3 (GPU 0)]
 
linear1.bias
Parameter containing:
-0.2549
-0.5246
-0.1109
 0.5237
-0.1362
[torch.cuda.FloatTensor of size 5 (GPU 0)]
 
linear2.weight
Parameter containing:
-0.0286 -0.3045 0.1928 -0.2323 0.2966
 0.2601 0.1441 -0.2159 0.2484 0.0544
[torch.cuda.FloatTensor of size 2x5 (GPU 0)]
 
linear2.bias
Parameter containing:
-0.4038
 0.3129
[torch.cuda.FloatTensor of size 2 (GPU 0)]

a = torch.load("OldWeights.pth")
 
a["layer1.0.coefficient"] = torch.FloatTensor([1.2])
a["layer1.1.coefficient"] = torch.FloatTensor([1.5])
 
torch.save(a, "Weights.pth")