Closed terribilissimo closed 5 years ago
Based on the code you've provided, this doesn't seem to be an issue with code on this repo (we don't have anything called "stuff.csv". Please reopen if it is, and provide a link to the code on this repo which is not working correctly.
Hi Jeremy.
stuff.csv
is just my csv with labeling for my dataset. If you don't mind, I'll reopen it, proving a link to relevant code.
However, see also https://forums.fast.ai/t/error-pytorch-expected-object-of-scalar-type-long-but-got-scalar-type-float-for-argument-2-other/33778/5
This repo is for issues in the course materials. You should use the forum for your issue, since it isn't an issue in the course materials.
You are right, I did open this issue here by mistake. I was on the verge of opening a new issue on the main fastai repo (not course). Do you prefer that I stick with the forum post I already started and not to open an issue? Consider however that the post is two weeks old, but the problem still persists.
I'll wait for your reply before opening a new issue on the fastai repo.
Thanks.
On Sun, Jan 27, 2019 at 1:00 PM Jeremy Howard notifications@github.com wrote:
This repo is for issues in the course materials. You should use the forum for your issue, since it isn't an issue in the course materials.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/fastai/course-v3/issues/141#issuecomment-457911710, or mute the thread https://github.com/notifications/unsubscribe-auth/AhqNqlRW-Bcpw57Qn0gHu67f2AqtJaXZks5vHZTYgaJpZM4Z7b-1 .
Yes you should stick to the forum thread. The answer there seems to be the correct one.
Yes, the answer is correct and it solved my problems, indeed I write my custom metric before my trainings. But souldn't we patch the code in fastai? Consider that it happens as one acquires the data via csv or df. As you acquire the data from (for example) folders, the error does not manifest itself. I wonder if you (fastai team) encounter the same issue as you acquire data for your experiments from csv/df.
On Sun, Jan 27, 2019 at 2:51 PM Jeremy Howard notifications@github.com wrote:
Yes you should stick to the forum thread. The answer there seems to be the correct one.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/fastai/course-v3/issues/141#issuecomment-457919725, or mute the thread https://github.com/notifications/unsubscribe-auth/AhqNqhKqbZvY_pOi0Q4XFYfrC5CPqpXKks5vHa70gaJpZM4Z7b-1 .
This is somewhat related with:
https://github.com/fastai/fastai/issues/839
and:
https://forums.fast.ai/t/error-pytorch-expected-object-of-scalar-type-long-but-got-scalar-type-float-for-argument-2-other/33778/3
Complete debug message:
How I acquired the data, created my Learner:
The error pops up right after the first epoch, just as the first validation cycle starts. Note that I implemented the suggestion provided by S. Gugger in issue #839