Description
Pretrained SwinForImageClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.swin_base_patch4_window12_384_in22k_pipeline is a English model originally trained by microsoft.
How to use
pipeline = PretrainedPipeline("swin_base_patch4_window12_384_in22k_pipeline", lang = "en")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("swin_base_patch4_window12_384_in22k_pipeline", lang = "en")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | swin_base_patch4_window12_384_in22k_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 820.3 MB |
References
https://huggingface.co/microsoft/swin-base-patch4-window12-384-in22k
Included Models
- ImageAssembler
- SwinForImageClassification