Ben Johnson
Ben Johnson
The paper mentions the malware datasets `TRAIN10K` and `TEST10K` -- are these datasets available for download somewhere? I downloaded the VM, but AFAIK it only contains that KDD datasets. Thanks!
I noticed that you can get substantial training speedups by adding eg. `num_workers=8` here: https://github.com/HazyResearch/hyperbolics/blob/master/pytorch/pytorch_hyperbolic.py#L279 I haven't had a chance to test whether this is valid on the other 3...
I'm trying to reproduce the results of Table 2 in [the paper](https://arxiv.org/pdf/1807.09856.pdf). I ran the code in the repo on the TRANCOS dataset and got the following results after 1000...
Hello -- Really enjoyed the paper. One clarifying question: you add the `target_embedding` to the query point embedding here: https://github.com/ZrrSkywalker/Personalize-SAM/blob/main/per_segment_anything/modeling/transformer.py#L94 but you don't fine-tune the model. Do you have an...
In this line: https://github.com/cfld/simple_tsp/blob/master/simple_tsp/lk.py#L141 we should only be checking the old edges up to the current depth. Otherwise, you could get something like this which is incorrect ``` pre filter...
Hi -- is anyone able to provide guidance on how to implement a custom popup? I only want to allow annotations from two different classes, and don't want the user...
This looks like a really great package. I'm trying to get the example running, but having some trouble. I adapted the code from here: https://www.eugene.zone/tarexp/example/ yielding ```python import ir_measures import...
Hello -- Are you able to release code that you used for the FRAMES benchmarking? Specifically, I'm interested in whether there are current best practices for the automatic grading --...