import comet_ml
comet_ml.init(anonymous=True, project_name="3: OWL-ViT + SAM")
exp = comet_ml.Experiment()
# To display the image
from PIL import Image
logged_artifact = exp.get_artifact("L3-data", "anmorgan24")
# Display the images
raw_image = Image.open("L3_data/dogs.jpg")
raw_image

from transformers import pipeline
OWL_checkpoint = "./models/google/owlvit-base-patch32"

# Load the model
detector = pipeline(
    model= OWL_checkpoint,
    task="zero-shot-object-detection"
)

# What you want to identify in the image
text_prompt = "dog"

output = detector(
    raw_image,
    candidate_labels = [text_prompt]
)

# Print the output to identify the bounding boxes detected
output

from utils import preprocess_outputs

input_scores, input_labels, input_boxes = preprocess_outputs(output)

from utils import show_boxes_and_labels_on_image

# Show the image with the bounding boxes
show_boxes_and_labels_on_image(
    raw_image,
    input_boxes[0],
    input_labels,
    input_scores
)

#Model distillation