pip install pixeltable fiftyone transformers

import pixeltable as pxt
from pixeltable.functions.huggingface import (
    vit_for_image_classification,
    detr_for_object_detection
)

# Initialize app structure
pxt.drop_dir('vision', force=True)
pxt.create_dir('vision')

# Create base table
images = pxt.create_table(
    'vision.images', 
    {'image': pxt.Image},
    if_exists="ignore"
)

# Add model inference columns
images.add_computed_column(
    classifications=vit_for_image_classification(
        images.image, 
        model_id='google/vit-base-patch16-224'
    )
)

images.add_computed_column(
    detections=detr_for_object_detection(
        images.image, 
        model_id='facebook/detr-resnet-50'
    )
)

# Optional: Add additional model for comparison
images.add_computed_column(
    detections_101=detr_for_object_detection(
        images.image, 
        model_id='facebook/detr-resnet-101'
    )
)

# Define label conversion functions
@pxt.udf
def vit_to_fo(vit_labels: list) -> list:
    """Convert ViT classification output to Voxel51 format"""
    return [
        {'label': label, 'confidence': score}
        for label, score in zip(
            vit_labels.label_text, 
            vit_labels.scores
        )
    ]

@pxt.udf
def detr_to_fo(img: pxt.Image, detr_labels: dict) -> list:
    """Convert DETR detection output to Voxel51 format"""
    result = []
    for label, box, score in zip(
        detr_labels.label_text, 
        detr_labels.boxes, 
        detr_labels.scores
    ):
        # Convert DETR (x1,y1,x2,y2) to Voxel51 (x,y,w,h) format
        fo_box = [
            box[0] / img.width,
            box[1] / img.height,
            (box[2] - box[0]) / img.width,
            (box[3] - box[1]) / img.height,
        ]
        result.append({
            'label': label, 
            'bounding_box': fo_box, 
            'confidence': score
        })
    return result

import pixeltable as pxt
import fiftyone as fo

# Connect to your table
images = pxt.get_table("vision.images")

# Insert some images
url_prefix = 'https://raw.githubusercontent.com/pixeltable/pixeltable/main/docs/source/data/images'
urls = [
    f'{url_prefix}/000000000019.jpg',
    f'{url_prefix}/000000000025.jpg',
    f'{url_prefix}/000000000030.jpg',
    f'{url_prefix}/000000000034.jpg',
]

images.insert({'image': url} for url in urls)

# Export to Voxel51 with multiple label sets
fo_dataset = pxt.io.export_images_as_fo_dataset(
    images,
    images.image,
    classifications=vit_to_fo(images.classifications),
    detections={
        'detections_50': detr_to_fo(images.image, images.detections),
        'detections_101': detr_to_fo(images.image, images.detections_101)
    }
)

# Launch Voxel51 visualization
session = fo.launch_app(fo_dataset)