Replies: 1 comment 1 reply
-
so, instead of constructing a dictionary directly from the dataframe, you should be using the point_predictions = []
for batch in progress_bar(inference_dataloader):
for k, v in batch.items():
if isinstance(v, list) and (len(v) == 0):
continue # Skipping empty list
batch[k] = v.to(model.device)
y_hat=F.softmax(model.predict(batch), dim=1)
point_predictions.append(y_hat.detach().cpu())
point_predictions = torch.cat(point_predictions, dim=0) |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
@manujosephv , Idk why I can't add a comment on this issue #396
here is my fixed code to activate softmax
But Idk how can I apply datamodule in this code, can you give me some advice please??
Beta Was this translation helpful? Give feedback.
All reactions