This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 210
RuntimeError of 'T_out = y.size(1) if y is not None else None' #17
Comments
change seq2seq model line 173 to |
that worked for me thanks manoja328 |
Hi,
Its in the file
https://github.com/facebookresearch/clevr-iep/blob/master/scripts/run_model.py
in line 276 .. The preds variable is the answers.
_, preds = scores.data.cpu().max(1)
all_programs.append(programs_pred.data.cpu().clone())
all_scores.append(scores.data.cpu().clone())
all_probs.append(probs.data.cpu().clone())
.........
Best,
Manoj
…On Fri, Oct 20, 2017 at 10:05 AM, Victoria2333 ***@***.***> wrote:
@manoja328 <https://github.com/manoja328>,do you know how to compute test
accuracy?coz there is no test answer in dataset,i don't know how to do
it,and thanks very much~~~
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#17 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AE7OR2S26SDfsNY4q0CrenhcP_ww9CmKks5suKiRgaJpZM4PDrfq>
.
|
Hi,
Its in the file https://github.com/facebookresearch/clevr-iep/
blob/master/scripts/run_model.py in line 276 .. The preds variable is the
answers.
_, preds = scores.data.cpu().max(1)
all_programs.append(programs_pred.data.cpu().clone())
all_scores.append(scores.data.cpu().clone())
all_probs.append(probs.data.cpu().clone())
.........
Best,
Manoj
…On Fri, Oct 20, 2017 at 10:05 AM, Victoria2333 ***@***.***> wrote:
@manoja328 <https://github.com/manoja328>,do you know how to compute test
accuracy?coz there is no test answer in dataset,i don't know how to do
it,and thanks very much~~~
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#17 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AE7OR2S26SDfsNY4q0CrenhcP_ww9CmKks5suKiRgaJpZM4PDrfq>
.
|
Hi |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Hi there, when I ran the scripts as instructed, I got the RuntimeError. Below are the details:
My python is of version 3.6, and the latest pytorch is installed.
I have printed the content of y, and it can be None, 1-by-1 torch.cuda.LongTensor, and 1 torch.cuda.LongTensor. So, when the size is 1, T_out = y.size(1) will lead to the RuntimeError.
The text was updated successfully, but these errors were encountered: