Add Reuters-21578 dataset #147
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
The dataset path in args.py was made to point at the dataset folder rather than dataset/SST folder. Hence SST folder was added to paths in the SST dataset class
daemon
requested review from
daemon and
Impavidity
and removed request for
daemon
Impavidity
reviewed
Sep 27, 2018
| # Using binary accuracy | ||
| for tensor1, tensor2 in zip(scores.round().long().data, batch.label.data): | ||
| print(tensor1, tensor2) | ||
| if np.array_equal(tensor1, tensor2): |
There was a problem hiding this comment.
So your evaluation criteria is that: give full credit when it is exact match otherwise, it get zero ?
There was a problem hiding this comment.
Yup. Since only one or two in 90 classes would be the positive label, I'm not sure if something like hamming score would work. The fraction of labels that are incorrectly predicted would still be too small in that case,
Impavidity
reviewed
Sep 27, 2018
| scores = self.model(batch.text) | ||
| # Using binary accuracy | ||
| for tensor1, tensor2 in zip(scores.round().long().data, batch.label.data): | ||
| print(tensor1, tensor2) |
There was a problem hiding this comment.
My bad. I made the change, forgot to push it.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I hope the commit messages are descriptive enough of the changes made. This PR is complementary to https://git.uwaterloo.ca/jimmylin/Castor-data/merge_requests/7#note_71256 in the data repository.