Alara Dirik

Adding OWL-ViT to HuggingFace Transformers

20

Hi, I've implemented OWL-ViT as a fork of [🤗 HuggingFace Transformers](https://github.com/huggingface/transformers.git), and we are planning to add it to the library soon (see https://github.com/huggingface/transformers/pull/17938). Here's a notebook that illustrates inference...

Add semantic segmentation post-processing method to MobileViT

1

# What does this PR do? Adds post_process_semantic_segmentation method to `MobileViTFeatureExtractor`. I will open an issue and separate PRs to make sure that - Segmentation models (DETR, MaskFormer, SegFormer, etc.)...

Add AutoModelForZeroShotImageClassification

2

# What does this PR do? Adds `AutoModelForZeroShotImageClassification` and `TFAutoModelForZeroShotImageClassification` to transformers. CC @MKhalusova will be adding a task guide in a separate PR ## Before submitting - [ ]...

Fix DeiT Masked Image Modeling output

1

# What does this PR do? Fixes the output of `DeiTForMaskedImageModeling` and `TFDeiTForMaskedImageModeling` by replacing the inaccurate `MaskedLMOutput` with the `MaskedImageCompletionOutput` class. Follow-up PR on #22152 ## Before submitting -...

Add MaskedImageModelingOutput

3

# What does this PR do? - Adds `MaskedImageModelingOutput` and `TFMaskedImageModelingOutput` classes for masked image modeling / completion / in-painting models. - Replaces the inaccurate MaskedLMOutput used for ViT and...

Add Replicate demo

5

Hi @yl4579 , I accidentally discard the changes and closed the previous [pull request](https://github.com/yl4579/StyleTTS2/pull/71). The issue is now fixed and I updated the Replicate demo as well!