-
Currently the remote sensing featurizer is running out of RAM when dealing with larger datasets. It seem that the issue is due to the fact that featurizer is loading all of the remote sensing data fr…
-
- d3m-interface 0.1.5
- PyPi `pip install d3m-interface`
- Information on gitlab
- [Projects · VIDA-NYU / d3m / d3m_interface · GitLab](https://gitlab.com/ViDA-NYU/d3m/d3m_interface)
- [exa…
-
It would be great to have all of `d3m-experimenter`'s rich data inside the D3M MtL DB. The D3M deps will need to be updated (i.e. the D3M docker image that's used by the repo), and any breaking change…
-
This is making them fail to load in my TA2 system. It is too generic. So you should name your python module similar to your package. I suggest `kf_d3m_primitives` or something (and not `primitives`). …
mitar updated
4 years ago
-
Requires #48 to be completed first.
Now that we have the D3M version updated, and once #48 is completed, we'll have everything we need to rerun the current experiment setup (straight pipelines and …
-
- [x] Update NYU urls
- [ ] Test with seeds on DM
- [x] Integrate a TA2 (NYU?)
- [ ] follow submission checklist
- Submission form: https://wiki.datadrivendiscovery.org/pages/viewpage.action?pag…
-
Originally, pyprob was installed with `1.2.0`, but now it is installing with `1.2.1` has requirement `torch>=1.5.1`, but we have torch `1.4.0` in the D3M Docker image.
Please fix the upper versions…
mitar updated
4 years ago
-
- The TA2 check is right at start-up
- Move check only when the D3M solvers are invoked
-
Now that we have the random experiments fully implemented, it makes sense to run them at the same time as the straight and ensemble experiments as requested in #49.
-
When we tested with the latest version, I found some timeout errors that the previous version did not have. And I found that the `0.9.9.RELEASE` version had no timeout error, and `0.9.10.RELEASE` st…