English image_classifier_vit_modelversion01 ViTForImageClassification from sudo-s

Description

Pretrained VIT model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.image_classifier_vit_modelversion01 is a English model originally trained by sudo-s.

Predicted Entities

45, 98, 113, 34, 67, 120, 93, 142, 147, 12, 66, 89, 51, 124, 84, 8, 73, 78, 19, 100, 23, 62, 135, 128, 4, 121, 88, 77, 40, 110, 15, 11, 104, 90, 9, 141, 139, 132, 44, 33, 117, 22, 56, 55, 26, 134, 50, 123, 37, 68, 61, 107, 13, 46, 99, 24, 94, 83, 35, 16, 79, 5, 103, 112, 72, 10, 59, 144, 87, 48, 21, 116, 76, 138, 54, 43, 148, 127, 65, 71, 57, 108, 32, 80, 106, 137, 82, 49, 6, 126, 36, 1, 39, 140, 17, 25, 60, 14, 133, 47, 122, 111, 102, 31, 96, 69, 95, 58, 145, 64, 53, 42, 75, 115, 109, 0, 20, 27, 70, 2, 86, 38, 81, 118, 92, 125, 18, 101, 30, 7, 143, 97, 130, 114, 129, 29, 41, 105, 63, 3, 74, 91, 52, 85, 131, 28, 119, 136, 146

Live Demo Open in Colab Download Copy S3 URI

How to use

image_assembler = ImageAssembler() \
    .setInputCol("image") \
    .setOutputCol("image_assembler")

imageClassifier = ViTForImageClassification \
    .pretrained("image_classifier_vit_modelversion01", "en")\
    .setInputCols("image_assembler") \
    .setOutputCol("class")

pipeline = Pipeline(stages=[
    image_assembler,
    imageClassifier,
])

pipelineModel = pipeline.fit(imageDF)

pipelineDF = pipelineModel.transform(imageDF)

val imageAssembler = new ImageAssembler()
.setInputCol("image")
.setOutputCol("image_assembler")

val imageClassifier = ViTForImageClassification
.pretrained("image_classifier_vit_modelversion01", "en")
.setInputCols("image_assembler")
.setOutputCol("class")

val pipeline = new Pipeline().setStages(Array(imageAssembler, imageClassifier))

val pipelineModel = pipeline.fit(imageDF)

val pipelineDF = pipelineModel.transform(imageDF)

import nlu
import requests
response = requests.get('https://raw.githubusercontent.com/JohnSnowLabs/spark-nlp/master/docs/assets/images/hen.JPEG')
with open('hen.JPEG', 'wb') as f:
    f.write(response.content)
nlu.load("en.classify_image.modelversion01").predict("hen.JPEG")