Skip to content

selecting negatives from present item_idxes #117

Merged
merged 3 commits into from
Apr 12, 2022

Conversation

monkey0head
Copy link
Contributor

  • before: sampling negatives from [0, max_item_idx]
  • now: sampling negatives from items, presented in fit

discuss: protected attribute creation and deletion inside fit, sampling with numpy instead of pytorch.

@monkey0head
Copy link
Contributor Author

closes #99

@@ -336,7 +335,7 @@ def _fit(
hidden_mlp_dims=self.hidden_mlp_dims,
).to(self.device)

self.logger.debug("Create batch")
self.logger.debug("Create DataLoaders")
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

it is the only one

@AleXXL1986 AleXXL1986 merged commit 83ef810 into main Apr 12, 2022
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants