swift-models icon indicating copy to clipboard operation
swift-models copied to clipboard

Models and examples built with Swift for TensorFlow

Results 46 swift-models issues
Sort by recently updated
recently updated
newest added

After importing the initial BERT model into the repository, there are a few remaining to-do items to expand upon this work (extracted from [Dan's comment](https://github.com/tensorflow/swift-models/pull/231#issuecomment-586036174)): - [ ] Rewrite utilities...

help wanted

Refactor the GPT-2 and BERT models to make it clear which concepts are shared and which are distinct. For example, transformers and multi-head attention are shared concepts, but naming collisions...

help wanted

The BERT-CoLA example only covers classification. Add SQuAD to Datasets with a corresponding task and example.

PR #418 replaced the core usage of TensorFlow.Dataset with the new Batcher mechanism. This is a step forward, but there was one small piece of old functionality missing in the...

I'd love to contribute an example of using UNet for image segmentation - would this be useful?

help wanted
good first issue

In Vocabulary, the attributes [tokensToIds and idsToTokens](https://github.com/tensorflow/swift-models/blob/master/Support/Text/Tokenization.swift#L41-L42) are a good candidate for replacement with [BijectiveDictionary](https://github.com/tensorflow/swift-models/blob/master/Support/BijectiveDictionary.swift). BERT and GPT2 both use Vocabulary, so ensure that functionality remains after the switch.

Since CMake has been added to Kokoro and blocks PR merges, the contributor guide needs documentation on local setup and usage. README.md contains basic information labeled as experimental, but this...

It'd be great to have an example speech to text model incorporated into our example models.

help wanted
good first issue

In order for inference tests in #201 to be possible, we should consider adding support for the imagenet dataset since most pretrained weights for models are released after having been...

Most UCI datasets are comma seperated classification datasets, much like the IRIS dataset. The first tutorial in the S4TF docs is one where we train a model for classification based...

help wanted