app.py

import gradio as gr
import cv2
import torch
from PIL import Image
from transformers import DetrImageProcessor, DetrForObjectDetection

# Load the pre-trained DETR model
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
model.eval()

# Function for image object detection
def image_object_detection(image_pil):
    # Process the image with the DETR model
    inputs = processor(images=image_pil, return_tensors="pt")
    outputs = model(**inputs)

    # Convert the image to numpy array for drawing bounding boxes
    image_np = cv2.cvtColor(cv2.cvtColor(cv2.cvtColor(np.array(image_pil), cv2.COLOR_RGB2BGR), cv2.COLOR_BGR2RGB), cv2.COLOR_RGB2BGR)

    # convert outputs (bounding boxes and class logits) to COCO API
    # let's only keep detections with score > 0.9
    target_sizes = torch.tensor([image_pil.size[::-1]])
    results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]

    # Draw bounding boxes on the image
    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
        box = [int(round(i)) for i in box.tolist()]
        cv2.rectangle(image_np, (box[0], box[1]), (box[2], box[3]), (0, 255, 0), 2)
        label_text = f"{model.config.id2label[label.item()]}: {round(score.item(), 3)}"
        cv2.putText(image_np, label_text, (box[0], box[1] - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)

    return image_np

# Function for live object detection from the camera
def live_object_detection(image_pil):
    # Process the frame with the DETR model
    inputs = processor(images=image_pil, return_tensors="pt")
    outputs = model(**inputs)

    # convert outputs (bounding boxes and class logits) to COCO API
    # let's only keep detections with score > 0.9
    target_sizes = torch.tensor([image_pil.size[::-1]])
    results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]

    # Draw bounding boxes on the image
    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
        box = [int(round(i)) for i in box.tolist()]
        cv2.rectangle(image_pil, (box[0], box[1]), (box[2], box[3]), (0, 255, 0), 2)
        label_text = f"{model.config.id2label[label.item()]}: {round(score.item(), 3)}"
        cv2.putText(image_pil, label_text, (box[0], box[1] - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)

    return image_pil

# Define the Gradio interface
iface = gr.Interface(
    fn=[image_object_detection, live_object_detection],
    inputs=[
        gr.Image(type="pil", label="Upload an image for object detection", hover=True),
        "webcam",
    ],
    outputs=["image", "image"],
    live=True,
)

# Launch the Gradio interface
iface.launch()