-
Notifications
You must be signed in to change notification settings - Fork 147
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Temporal sampling #202
Temporal sampling #202
Conversation
Codecov Report
@@ Coverage Diff @@
## master #202 +/- ##
=======================================
Coverage 72.32% 72.32%
=======================================
Files 28 28
Lines 1120 1120
=======================================
Hits 810 810
Misses 310 310 📣 Codecov can now indicate which changes are the most critical in Pull Requests. Learn more |
Since the random function has been changed to follow |
… into temporal_sampling
Is it because the pytorch 1.11 (on ubuntu) has made some modifications on |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks @RexYing. This looks great overall. One thing I think we need to fix is to add is_temporal
as part of the template
definition.
node_types, edge_types, colptr_dict, row_dict, input_node_dict, | ||
num_neighbors_dict, node_time_dict, num_hops, replace, directed); | ||
} | ||
|
||
static auto registry = | ||
torch::RegisterOperators() | ||
.op("torch_sparse::neighbor_sample", &neighbor_sample) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
How much work would it be to add the same for neighbor_sample
?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
should be easy. I'll create another PR for neighbor_sample
?
Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
* nni basic * nni basic trial * Ray tune now works * create separate kumo-train-auto * update * fix * fix * fix * Update and merge single/tune API * fix linting * Fix pl api change * Ready to merge with master * Add missing file * Refactor train_fn, improve test_trainer * fix * fix * Final change based on comments * Fix conflict Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
No description provided.