Charles Tapley Hoyt
Charles Tapley Hoyt
Wrap either a `PipelineResult` or a `Model` such that it does the evaluation requested by a given OGB task (link prediction, node classification, etc.)
> What about adding a mode that moves all entities that won't get used in evaluation over to training? I suppose you mean the triples containing entities which are not...
Can we generalize this part? We should consider that we could also pass `experiment_id`, and `experiment_name` to the MLFlow tracker. _Originally posted by @mali-git in https://github.com/pykeen/pykeen/pull/69_
In the opposite scenario to #62/#83, we want to report several different sets of metrics based on each relation type. For example, for hetionet, you might want to specify edges...
Since #17 was merged before I got a chance to make a fuss about there not being documentation, it needs to be revisited. 1. Since you touched it last, you're...
Since each interaction model has a different range (e.g., the values of some interaction functions could be between [-inf,inf], some could be [0, inf], some could be [0, 1]), it...
This PR updates the pyproject.toml to tell build systems that torch needs to be available _before_ installation so there's no issues with the torch_scatter. It switches from setup.py to a...
I think it would be better to have the dataset download and processing happen client-side, then use `pystow` to store the results in a reliable place. This would also allow...
This PR closes #5 by putting the code in a directory structure that's required by python packages, by adding a minimal `setup.py`/`setup.cfg`. It also closes #6 by encapsulating the main...
As a follow-up to #5, it would be nice to have vanity CLI endpoints so users could directly use the code.