-
From: https://github.com/fairlearn/fairlearn/pull/906#discussion_r673118210
Some of our algorithms require the output to be 0/1. However, they only need the output to be categorical, and in case of…
-
I would suggest to expose the tuners as `sklearn` compatible tuning wrappers, e.g.,
`HyperactiveCV(sklearn_estimator, config)`,
or
`HyperactiveCV(sklearn_estimator, hyperopt_tuning_algo, conf…
-
Hi,
When I run my code, the links provided to access the dashboard are invalid. I tried using the key disable_dashboard = True in sherpa.Study and then after running all my code, sherpa.Study.load_…
-
| | |
|--------------------|----|
| Bugzilla Link | [PR31917](https://bugs.llvm.org/show_bug.cgi?id=31917) |
| Status | NEW |
| Importance | P normal |
|…
-
Hi all,
I have a question regarding data scaling - my dataset is almost the same as CIFAR-10, only grayscale: 32x32, 1 channel, 4 classes, 3000 training and 800 test images. I'm using the CIFAR-10 …
-
The idea is to allow for more than the generic gradient descent algorithm when it comes to network weight optimization. When building a network the user should be allowed to specify which optimization…
-
### 🐛 Describe the bug
### Code
```python
import os
import argparse
import functools
import torch
from itertools import chain
import torch.nn as nn
import torch.optim as optim
from transfo…
-
**Is your feature request related to a problem? Please describe.**
Locality-optimized scan internally creates a UNION ALL expression to handle reading from local and remote regions in separate scans.…
-
Currently both `Vec`s and `VecDeque`s `truncate` implementations just call `pop_back()` in a loop. When `std::mem::needs_drop::()` is `false` this is pretty inefficient.
Now LLVM *does* [optimize a…
-
How can I train models in multiple GPUs on the same machine. Current generic tf solution for keras API is using `tf.distribute.MirroredStrategy()` like below:
```
strategy = tf.distribute.Mirror…