-
Hi
I recently trained an InductiveNodePieceGNN model and now want to generate embeddings for unseen nodes. To do this, I added a few new triples to the existing data and used the code below to retr…
-
The Open Article Gauge updates the results for a given POST request asynchronously. The immediately returned JSON will only include objects for which a license is already cached by OAG. The delay for …
-
Reproduction:
* Delete a message from INBOX
Actual result:
* The message disappears from the INBOX and appears in Trash (correct)
* After a few seconds (maybe 10 seconds), all new messages from …
-
Hi, I have found that the ground truth of unseen classes in COCO have been used in trainning, I wonder if I'm misunderstood.
ids of unseen classes in COCO
 reported this on 2016-12-18T18:19:08Z
### Transfered from https://issues.dlang.org/show_bug.cgi?id=16982
### CC List
* ag0aep6g
* greeenify
* johannespfau (@jpf91)
### Descr…
-
Hello, I think adding a keyword extractor with [KeyBERT](https://github.com/MaartenGr/KeyBERT) would be quite useful. The keywords extracted could be used for paraphrasing or summarizing with `logit_b…
-
Thanks for sharing the great work.
I wonder how does the model works for novel objects that are not seen during training phase. Have you ever conducted similar experiments？