Srikumar Sastry

Check for empty input array

5

Added assertion for checking empty input array in Model.fit function. Closes: #16202

Better error message for Unexpected result of `train_function` (Empty logs). Please use `Model.compile(..., run_eagerly=True)`, or `tf.config.run_functions_eagerly(True)` for more information of where went wrong, or file a issue/bug to `tf.keras`

6

Hi! This error message pops up when empty arrays are passed to `Model.fit` or `Model.predict`. The solution suggested in the error message does not work and in some sense is...

[Feature Proposal] Implementation of State of the Art Active Learning Algorithms

1

Lately, a lot of active learning methods have been developed for deep neural networks. Some of these state of the art methods are considered as a standard benchmark when comparing...

Can FFCV work on the fly with a PyTorch Dataset?

1

My general understanding of how FFCV works is that it serializes a dataset of a `fixed` size and shape into a .beton file. Now, in my workflow, I want to...

Access datapoints through indexing from `.beton` file without creating a DataLoader

1

Is it possible to access some datapoints from the `.beton` file without having to load them into a DataLoader?

Fixed `np.float` to `np.float32`

Fixes issue #38709 for CLIP and XCLIP

2

# What does this PR do? Fixes #38709 (at least for CLIP and XCLIP for now and is fully backward compatible and existing functionality remains unaffected). Previously, `get__features` function in...