Description
Pretrained ViTForImageClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.v2_vit_base_patch16_224_in21k_finetuned_gecko_pipeline is a English model originally trained by emaeon.
How to use
pipeline = PretrainedPipeline("v2_vit_base_patch16_224_in21k_finetuned_gecko_pipeline", lang = "en")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("v2_vit_base_patch16_224_in21k_finetuned_gecko_pipeline", lang = "en")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | v2_vit_base_patch16_224_in21k_finetuned_gecko_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 321.5 MB |
References
https://huggingface.co/emaeon/v2_vit-base-patch16-224-in21k-finetuned-gecko
Included Models
- ImageAssembler
- ViTForImageClassification