Edit on GitHub
  • John Snow Labs
  • Dec 16, 2024

English deit_tiny_patch16_224_facebook_pipeline pipeline ViTForImageClassification from facebook

  • en
  • open_source
  • pipeline
  • onnx

Description

Pretrained ViTForImageClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.deit_tiny_patch16_224_facebook_pipeline is a English model originally trained by facebook.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("deit_tiny_patch16_224_facebook_pipeline", lang = "en")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("deit_tiny_patch16_224_facebook_pipeline", lang = "en")
val annotations = pipeline.transform(df)

Model Information

Model Name: deit_tiny_patch16_224_facebook_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: en
Size: 21.5 MB

References

https://huggingface.co/facebook/deit-tiny-patch16-224

Included Models

  • ImageAssembler
  • ViTForImageClassification