Description
Pretrained VIT model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.image_classifier_vit_mit_indoor_scenes is a English model originally trained by vincentclaes.
Predicted Entities
airport_inside, bowling, buffet, movietheater, clothingstore, inside_bus, fastfood_restaurant, operating_room, corridor, cloister, stairscase, auditorium, meeting_room, livingroom, videostore, bathroom, inside_subway, bedroom, casino, tv_studio, classroom, laboratorywet, nursery, office, deli, prisoncell, dentaloffice, restaurant_kitchen, studiomusic, locker_room, restaurant, laundromat, dining_room, subway, gameroom, museum, mall, garage, elevator, jewelleryshop, kindergarden, toystore, concert_hall, artstudio, kitchen, florist, waitingroom, grocerystore, library, bar, computerroom, trainstation, lobby, church_inside, pantry, closet, children_room, hairsalon, shoeshop, greenhouse, bookstore, bakery, poolinside, warehouse, winecellar, hospitalroom, gym
How to use
pipeline = PretrainedPipeline('pipeline_image_classifier_vit_mit_indoor_scenes', lang = 'en')
annotations = pipeline.transform(imageDF)
val pipeline = new PretrainedPipeline("pipeline_image_classifier_vit_mit_indoor_scenes", lang = "en")
val annotations = pipeline.transform(imageDF)
Model Information
| Model Name: | pipeline_image_classifier_vit_mit_indoor_scenes |
| Type: | pipeline |
| Compatibility: | Spark NLP 4.2.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 322.1 MB |
Included Models
- ImageAssembler
- ViTForImageClassification