[英]What’s the difference between the two operations in back-propagation with pytorch?
[英]Why is it in Pytorch when I make a COPY of a network's weight it would be automatically updated after back-propagation?
我編寫了以下代碼作為測試,因為在我的原始網絡中,我使用ModuleDict,並且取決於我提供的索引將僅對該網絡的一部分進行切片和訓練。
我想確保只有切成薄片的圖層會更新其權重,所以我編寫了一些測試代碼來進行仔細檢查。 好吧,我得到一些奇怪的結果。 假設我的模型有2個層,第1層是FC,第2層是Conv2d,如果我對網絡進行切片並且僅使用第2層,則我希望第1層的權重保持不變,因為它們未使用,並且第1層后將更新第2層的權重。
因此,我的計划是使用for
循環從網絡中獲取所有權重,然后再進行訓練,然后在1 optimizer.step()
之后執行此操作。 兩次,我都將那些權重完全存儲在2個Python列表中,以便以后可以比較它們的結果。 好吧,出於某種原因,如果我將兩個列表與torch.equal()
進行比較,則它們是torch.equal()
我認為這是因為內存中可能仍然存在某種隱藏鏈接? 因此,當我從循環中獲取權重時,我嘗試在權重上使用.detach()
,結果仍然相同。 在這種情況下,第2層的權重應該有所不同,因為在訓練之前它應包含來自網絡的權重。
在下面的代碼中指出,我實際上是在使用layer1並忽略layer2。
完整代碼:
class mymodel(nn.Module):
def __init__(self):
super().__init__()
self.layer1 = nn.Linear(10, 5)
self.layer2 = nn.Conv2d(1, 5, 4, 2, 1)
self.act = nn.Sigmoid()
def forward(self, x):
x = self.layer1(x) #only layer1 and act are used layer 2 is ignored so only layer1 and act's weight should be updated
x = self.act(x)
return x
model = mymodel()
weights = []
for param in model.parameters(): # loop the weights in the model before updating and store them
print(param.size())
weights.append(param)
critertion = nn.BCELoss() #criterion and optimizer setup
optimizer = optim.Adam(model.parameters(), lr = 0.001)
foo = torch.randn(3, 10) #fake input
target = torch.randn(3, 5) #fake target
result = model(foo) #predictions and comparison and backprop
loss = criterion(result, target)
optimizer.zero_grad()
loss.backward()
optimizer.step()
weights_after_backprop = [] # weights after backprop
for param in model.parameters():
weights_after_backprop.append(param) # only layer1's weight should update, layer2 is not used
for i in zip(weights, weights_after_backprop):
print(torch.equal(i[0], i[1]))
# **prints all Trues when "layer1" and "act" should be different, I have also tried to call param.detach in the loop but I got the same result.
您必須clone
參數,否則只需復制引用即可。
weights = []
for param in model.parameters():
weights.append(param.clone())
criterion = nn.BCELoss() # criterion and optimizer setup
optimizer = optim.Adam(model.parameters(), lr=0.001)
foo = torch.randn(3, 10) # fake input
target = torch.randn(3, 5) # fake target
result = model(foo) # predictions and comparison and backprop
loss = criterion(result, target)
optimizer.zero_grad()
loss.backward()
optimizer.step()
weights_after_backprop = [] # weights after backprop
for param in model.parameters():
weights_after_backprop.append(param.clone()) # only layer1's weight should update, layer2 is not used
for i in zip(weights, weights_after_backprop):
print(torch.equal(i[0], i[1]))
這使
False
False
True
True
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.