-
release: december 2022
Wanted:
- Infrastructure:
- cPython-3.11.1,
- Spyder with ipython-8 support,
- more pyodide examples that work in dot
- Experimental:
- coudn't resist; …
-
## Overview
Refer to hpo design in nano pytroch in issue #3925
Enable hyper param tuning in nano tensorflow. Make it as transparent as possible to users. General principals include:
- provide …
-
See https://blog.floydhub.com/guide-to-hyperparameters-search-for-deep-learning-models/ and
https://rpubs.com/Argaadya/bayesian-optimization
-
Hi,
I am working on this notebook, to use detectron2's Retinanet on our custom dataset, instead of SKU110k dataset. Our dataset has 140 labels, so while running the training job this error is comi…
-
Thank you for sharing your code which is of high quality.
Do you have a link to download all the datasets used in your experiments?
-
## Documentation ##
A full-size upgrade of the documentation, with the following significant improvements in the reading experience, practical tutorials, and examples:
- Reorganized the document st…
-
Currently, the `KnowledgeGraph` class accept a data frame containing three columns (`['from', 'rel', 'to']`) and I feel like it would be nice to provide some facts that are known to be false, with a f…
-
- Release manager: @ultmaster
- Release start date: 6.22
- Feature freeze date (at most 30 days): ~7.22~ 8.1
- First test package (1 week since feature freeze): ~7.29~ ~8.12~ 8.16
- Release date (…
-
I set up a pipeline. Within the same `PythonScriptStep` I have a _Pytorch-lightning_ training loop and an _Optuna_ hyperparameter tuning loop. If I do not use Optuna, I can log without any issues the …
-
Hi,
thanks for sharing your implementation. I have some questions about it:
1. Does it also work on tabular data?
2. Is the code tailored to the datasets used in the paper or can one apply it to …