app.py

# import gradio as gr
# import cv2
# import numpy as np
# import onnxruntime as ort

# # Load the ONNX model using onnxruntime
# onnx_model_path = "Model_IV.onnx"  # Update with your ONNX model path
# session = ort.InferenceSession(onnx_model_path)

# # Function to perform object detection with the ONNX model
# def detect_objects(frame, confidence_threshold=0.5):
#     # Convert the frame from BGR (OpenCV) to RGB
#     image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
    
#     # Preprocessing: Resize and normalize the image
#     # Assuming YOLO model input is 640x640, update according to your model's input size
#     input_size = (640, 640)
#     image_resized = cv2.resize(image, input_size)
#     image_normalized = image_resized / 255.0  # Normalize to [0, 1]
#     image_input = np.transpose(image_normalized, (2, 0, 1))  # Change to CHW format
#     image_input = np.expand_dims(image_input, axis=0).astype(np.float32)  # Add batch dimension

#     # Perform inference
#     inputs = {session.get_inputs()[0].name: image_input}
#     outputs = session.run(None, inputs)
    
#     # # Assuming YOLO model outputs are in the form of [boxes, confidences, class_probs]
#     # boxes, confidences, class_probs = outputs

#     # # Post-processing: Filter boxes by confidence threshold
#     # detections = []
#     # for i, confidence in enumerate(confidences[0]):
#     #     if confidence >= confidence_threshold:
#     #         x1, y1, x2, y2 = boxes[0][i]
#     #         class_id = np.argmax(class_probs[0][i])  # Get class with highest probability
#     #         detections.append((x1, y1, x2, y2, confidence, class_id))
    
#     # # Draw bounding boxes and labels on the image
#     # for (x1, y1, x2, y2, confidence, class_id) in detections:
#     #     color = (0, 255, 0)  # Green color for bounding boxes
#     #     cv2.rectangle(image, (int(x1), int(y1)), (int(x2), int(y2)), color, 2)
#     #     label = f"Class {class_id}: {confidence:.2f}"
#     #     cv2.putText(image, label, (int(x1), int(y1)-10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
    
#     # # Convert the image back to BGR for displaying in Gradio
#     # image_bgr = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
    
#     return outputs

# # Gradio interface to use the webcam for real-time object detection
# # Added a slider for the confidence threshold
# iface = gr.Interface(fn=detect_objects, 
#                      #inputs=[
#                          # gr.Video(sources="webcam", type="numpy"),  # Webcam input
#                          inputs = gr.Image(sources=["webcam"], type="numpy"),
#                          # gr.Slider(minimum=0.0, maximum=1.0, default=0.5, label="Confidence Threshold")  # Confidence slider
#                      # ],  
#                      outputs="image")  # Show output image with bounding boxes

# iface.launch()

import gradio as gr
import cv2
from huggingface_hub import hf_hub_download
from gradio_webrtc import WebRTC
from twilio.rest import Client
import os
from inference import YOLOv8

model_file = hf_hub_download(
    repo_id="aje6/ASL-Fingerspelling-Detection", filename="onnx/Model_IV.onnx"
)

model = YOLOv8(model_file)

account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")

if account_sid and auth_token:
    client = Client(account_sid, auth_token)

    token = client.tokens.create()

    rtc_configuration = {
        "iceServers": token.ice_servers,
        "iceTransportPolicy": "relay",
    }
else:
    rtc_configuration = None


def detection(image, conf_threshold=0.3):
    image = cv2.resize(image, (model.input_width, model.input_height))
    new_image = model.detect_objects(image, conf_threshold)
    return cv2.resize(new_image, (500, 500))


css = """.my-group {max-width: 600px !important; max-height: 600 !important;}
                      .my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""


with gr.Blocks(css=css) as demo:
    gr.HTML(
        """
    <h1 style='text-align: center'>
    YOLOv10 Webcam Stream (Powered by WebRTC ⚡️)
    </h1>
    """
    )
    gr.HTML(
        """
        <h3 style='text-align: center'>
        <a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
        </h3>
        """
    )
    with gr.Column(elem_classes=["my-column"]):
        with gr.Group(elem_classes=["my-group"]):
            image = WebRTC(label="Stream", rtc_configuration=rtc_configuration)
            conf_threshold = gr.Slider(
                label="Confidence Threshold",
                minimum=0.0,
                maximum=1.0,
                step=0.05,
                value=0.30,
            )

        image.stream(
            fn=detection, inputs=[image, conf_threshold], outputs=[image], time_limit=10
        )

if __name__ == "__main__":
    demo.launch()