-
**Describe the bug**
For some choices of parameters for the models, the scores are NaN values. This may not be a bug but something that just happens.
**To Reproduce**
Steps to reproduce the behav…
-
Hi, thanks for sharing the work. We have performed a rigorous evaluation for the framework on the cifar-10 setting with this code base, for each setting we run the experiments independently 8 times an…
-
Can you post a working example that uses Skorch and HyperbandSearchCV? I haven't been able to find an actual working example.
The biggest challenge I've faced so far is how to determine the batch s…
-
Currently, we follow the classic setup of having one long list of args to initialize the model.
On top, we have some functions to configure special modules later, like `add_lagged_regressor`.
e.g.…
-
NOTE: ISSUES ARE NOT FOR CODE HELP - Ask for Help at https://stackoverflow.com
Your issue may already be reported!
Also, please search on the [issue tracker](../) before creating one.
* **I'm s…
-
I have been trying to run distributed training using tensorflow for a case where worker nodes don't have the `training_graph` but the master node does. There is no success so far with tensorflow distr…
-
hello, I have 3 questions can't be found in papers.
1.How to decide number of pixels for translateX(Y), on cifar10 is 10 pixels(10/32) but 150 pixels for imagenet(150/331), for example, if image s…
-
## 🐛 Bug
The default `ModelCheckpoint()` callback is saving the checkpoint to a different directory than the directory for the `CSVLogger` logger I have set up. For example, when the first ever run…
-
You will see the problem in the text below, this is with using gpt-4o and version 0.5 of agent zero, but have similar issues with other models
User message ('e' to leave):
> Write a college level …
-
Thanks for your nice work! I am trying to reproduce results of multi-domain datasets.
However, the results i get are quite different from the reported results in the paper.
When I followed your guid…