-
#### Describe the workflow you want to enable
Currently, `RFECV` searches for the optimal number of features to provide the best score. It then fits an `RFE` on the whole training set: [L566](htt…
-
Hello,
Thanks for a great paper.
When you compute top-5%/top-64 score (Tables 4, 11), how many architectures are there in total?
Is it 3000 architectures (only warmup) or the size of the entire…
-
Hello, I was trying to reproduce the experiment of VGG-16 and CAE Classification (Which are corresponding to the Table 1 & 3 Results), and I ran into two problems as follows:
1. VGG-16's score jus…
-
### Bug Description
When `max_model_size` is set below 63812570, ImageClassifier will repeatedly try to build a model with an EfficientNet-B7 backbone, then throw a RuntimeError. EfficientNet-B7 i…
-
您好，很抱歉再次打扰您，您是否方便提供arxiv和products这两个数据集的参数，我是一名知识蒸馏领域的初学者，目前在尝试复现您的实验。已经在前六个均取得了不错的效果，但是在arxiv数据集上效果与论文内的不太一样，我是直接通过修改传入的data超参数来调用best_parameter.json中的arxiv参数，通过观察csv文件参数传入均正确，接下来复现products时发现json文件里…
-
AutoML toolkit for hyperparameter tuning, NAS and model compression: https://github.com/Microsoft/nni
-
### Description
This is my second attempt at running Optuna and this time I am getting strange behaviour.
First time in another project worked like a treat.
The dashboard is not updating, I need …
-
**What I would you like to be added**:
It would be great if NNI had an *extension/framework for model selection*.
**Why is this needed**:
Model selection is a very relevant decision for…
-
Hi, thats a cool thesis idea. You probably want to look at LightGBM with linear weak learner and KTBoost, SnapBoost, [PolyBoost](https://github.com/SaremS/polynomial_boosting) as well.
Just lookin…
-
I tried this example and i change the scoring metrics to kappa score instead of ROC-AUC score in the example.
```
metric = dc.metrics.Metric(dc.metrics.kappa_score, np.mean)
optimizer = dc.hyper.…