Spaces:
Sleeping
Sleeping
File size: 1,545 Bytes
b764ffe 0aa924d be425b2 ec23149 0aa924d e134b51 0aa924d 6cd21dc 0aa924d 6cd21dc b764ffe 0aa924d b764ffe 0aa924d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
import gradio as gr
from ultralytics import YOLO
import spaces
import torch
# Load pre-trained YOLOv8 model
model = YOLO("yolov8x-doclaynet-epoch64-imgsz640-initiallr1e-4-finallr1e-5.pt")
# Get class names from model
class_names = model.names
@spaces.GPU(duration=60)
def process_image(image):
try:
# Process the image
results = model(source=image, save=False, show_labels=True, show_conf=True, show_boxes=True)
result = results[0] # Get the first result
# Extract annotated image and labels with class names
annotated_image = result.plot()
# Use cls attribute for labels and get class name from model
detected_areas_labels = "\n".join([
f"{class_names[int(box.cls.item())].upper()}: {box.conf:.2f}" for box in result.boxes
])
return annotated_image, detected_areas_labels
except Exception as e:
return None, f"Error processing image: {e}"
# Create the Gradio Interface
with gr.Blocks() as demo:
gr.Markdown("# Document Segmentation Demo (ZeroGPU)")
# Input Components
input_image = gr.Image(type="pil", label="Upload Image")
# Output Components
output_image = gr.Image(type="pil", label="Annotated Image")
output_text = gr.Textbox(label="Detected Areas and Labels")
# Button to trigger inference
btn = gr.Button("Run Document Segmentation")
btn.click(fn=process_image, inputs=input_image, outputs=[output_image, output_text])
# Launch the demo with queuing
demo.queue(max_size=1).launch()
|