-
Notifications
You must be signed in to change notification settings - Fork 154
Open
Description
Besides the toy examples listed in the docs and tests, are there actual examples of this library available anywhere?
I'm interested in using this library for a sequence labeling project, but I'm curious to know if I'm using this library correctly. What I have is something like this:
class MyModel(nn.Module):
def __init__(self, num_features, num_classes):
super(MyModel, self).__init__()
self.num_features = num_features
self.num_classes = num_classes
self.lstm = nn.LSTM(num_features, 128)
self.fc = nn.Linear(128, num_classes)
self.crf = CRF(num_classes)
# ----------------------------------------------------------
model = MyModel(...)
# Training loop:
y_hat = model(batch) # The network's forward returns fc(lstm(batch))
loss = -model.crf(y_hat, y)
loss.backward()
optimizer.step()
Although this seems to work and the loss is decreasing, I have a feeling that I might be missing something.
Any help is appreciated. Thanks!
Metadata
Metadata
Assignees
Labels
No labels