Colin White

Hi, with the release of nas-bench-301, there is no place in this repository where a GPU is needed. All of the experiments were run on single CPUs, and I would...

Hi Simon, Thanks for the interest. We used the code straight from the D-VAE repo. Specifically we set the "predictor" flag [here](https://github.com/muhanzhang/D-VAE/blob/3569a4a3bf5ecf8e12ae548e0d22e72062d29e26/train.py#L64) to true. If I remember correctly, I needed...

Hi, thank you for your interest. Many of the search spaces in NASLib have a `sample_random_architecture()` method, for example, the one for darts is [here](https://github.com/automl/NASLib/blob/047b0e66f034c5fb91df8e93efc30a12c6bc2259/naslib/search_spaces/darts/graph.py#L476), and an example on how...

Currently NASLib focuses on queryable benchmarks such as NAS-Bench-101/201/301/NLP/ASR, to make NAS research easier. You are free to write your own customized search space. For each search space, the architectures...

Hi Andreas, below are the 98 datasets from Table 1 and the 57 datasets from Table 2. Please let us know if you have more questions. ```python datasets_table_1 = ['openml__visualizing_environmental__3602',...