-
**Summary:**
It is not currently possible to provide propagated delays for dynamically blocked services where the `vehicle.id` is provided for subsequent trips without triggering E047.
For exam…
-
## Prelude
* Could you find answer in below documents? No
* Have you searched your problem in [issues](https://github.com/brookhong/Surfingkeys/issues)? Yes
## Context
**Please replace this …
-
Hi Keren,
I've run your Cap2Det training code with the coco17_extend_match.pbtxt config on the COCO Captions dataset, but couldn't reproduce the results reported in your paper.
Specifically, I ha…
-
## 🚀 Feature
Support iterating over node pairs in DataLoader.
## Motivation
Currently there are two ways to perform link prediction evaluation with given positive and negative samples:
One is …
-
Hello,
As i can see we have c-iou metric which show us the complexity of our predictions. But im not sure how to control the number of vertex predictions. is it handled at the nms phase with topk p…
-
We currently only have PV data for the UK. We will at some point want to get PV data for elsewhere but, in the meantime, we'll need nowcasting_dataset to optionally output examples from outside the UK…
-
Currently regenerating the HMD creates a fresh storage table which never gets cleaned up. Older tables for same version of the HMD should be removed via a manually trigger clean up function; only thos…
-
When predicting, we are just loading all the predictions into memory. This will run OOM fast on smaller machines.
-
Thank you very much for this great package.
A colleague of mine seems to be running into problems with the predict() function and I am not sure whether this may hint at a bug or whether it is down…
-
### Why the lexer is slower than it needs to be
Many of the simpler byte handlers in the lexer perform multiple branches.
e.g. The handler for `=` which needs to figure out "is the whole token `…