-
Right now, there's some overhead in gradient computations: `deepcopy` needs to be called on every computation to make sure gradients aren't shared between workers. This about doubles the time for a gr…
-
As mentioned in [Source MiniGrid/BabyAI Dataset#14](https://github.com/ManifoldRG/NEKO/issues/14), once a dataset is sourced, it needs to be converted to Minari. GoToLocal expert trajectories have alr…
-
I have been using presidio_analyzer in my local host.
I used presidio-research to generate a dataset with Fake and then run the train/run/dev.
the output is 3 JSON files.
I used the same genera…
-
I wanted to speed up the training phase using `InMemoryDataSetCache` and `CachingDataSetIterator` but got weird results.
The following gist comparse four things using code from the [MNIST example](…
-
When I apply the FewX on custom dataset, I meet an error:
Traceback (most recent call last):
File "/root/FewX-master/fsod_train_net.py", line 323, in
launch(
File "/root/.local/lib/pyth…
-
**Bug report checklist**
- [X] I provided code that demonstrates a minimal reproducible example.
- [X] I confirmed bug exists on the latest mainline of Chronos via source install.
**Describ…
-
Nice library, thanks! Will it work to pass e.g. `dataset.rolling(...)` or `dataset.rolling(...).construct(...)` to `xarray_beam.DatasetToChunks`? (I'm assuming not, or that it would result in somethin…
-
Long form country name is not available for PCA generation (example: currently PCA will show Pakistan instead of Islamic Republic of Pakistan). The long form name is not available in VISION either.
…
-
A `Task` in Codabench is considered atomic. A discussion is needed for the following:
1. What is task validation and how it is done
2. Should a task be updated? When and how
Some discussion bel…
-
# Summary
The `save_all` command does not correctly restore sessions for grating PHA datasets. The current work around is to use the binary state commands (`save` and `restore`). For simple cases (…