Description
Pretrained VIT model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.image_classifier_vit_base_beans_demo_v5 is a English model originally trained by mrgiraffe.
Predicted Entities
lion, tulip, keyboard, cra, bus, dolphin, plate, beaver, skyscraper, tiger, bear, trout, porcupine, sea, shrew, squirrel, snail, leopard, palm_tree, turtle, orchid, skunk, hamster, oak_tree, lizard, bridge, sunflower, pickup_truck, orange, man, mouse, cup, whale, seal, television, snake, crocodile, cockroach, bed, otter, caterpillar, woman, rocket, butterfly, bicycle, spider, motorcycle, lawn_mower, wolf, raccoon, can, cloud, clock, worm, tank, ray, house, girl, dinosaur, willow_tree, maple_tree, kangaroo, cattle, bee, chair, aquarium_fish, shark, baby, tractor, sweet_pepper, plain, lamp, boy, telephone, mushroom, couch, apple, wardrobe, train, pine_tree, pear, road, mountain, castle, bowl, lobster, elephant, beetle, possum, forest, flatfish, poppy, fox, streetcar, chimpanzee, bottle, rose, rabbit, table, camel
How to use
pipeline = PretrainedPipeline('pipeline_image_classifier_vit_base_beans_demo_v5', lang = 'en')
annotations = pipeline.transform(imageDF)
val pipeline = new PretrainedPipeline("pipeline_image_classifier_vit_base_beans_demo_v5", lang = "en")
val annotations = pipeline.transform(imageDF)
Model Information
| Model Name: | pipeline_image_classifier_vit_base_beans_demo_v5 |
| Type: | pipeline |
| Compatibility: | Spark NLP 4.2.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 322.2 MB |
Included Models
- ImageAssembler
- ViTForImageClassification