Changing to different streaming demo

app.py

@@ -1,59 +1,51 @@
-import cv2
 import gradio as gr
 import numpy as np
-from transformers import pipeline
-
-# Load YOLO model from Hugging Face's transformers library
-model = pipeline("object-detection", model="hustvl/yolos-tiny")
-
-# Function to capture and process video frames in real time
-def capture_and_detect():
-    cap = cv2.VideoCapture(0)  # OpenCV video capture from webcam
-
-    while True:
-        ret, frame = cap.read()
-        if not ret:
-            break
-
-        # Convert frame to RGB as required by YOLO model
-        rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-
-        # Perform object detection on the frame
-        results = model(rgb_frame)
-
-        # Draw bounding boxes and labels on the frame
-        for result in results:
-            label = result['label']
-            score = result['score']
-            box = result['box']
-            x1, y1, x2, y2 = int(box['xmin']), int(box['ymin']), int(box['xmax']), int(box['ymax'])
-
-            # Draw bounding box and label
-            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
-            text = f"{label}: {score:.2f}"
-            cv2.putText(frame, text, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
-
-        # Convert BGR back to RGB for Gradio display
-        yield cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-
-    cap.release()
-
-# Gradio Interface using real-time video capture and object detection
-def video_stream():
-    return capture_and_detect()
-
-# Create Gradio interface
-webcam_interface = gr.Interface(
-    fn=video_stream,
-    inputs=None,
-    outputs=gr.Image(),
-    live=True,
-    description="Real-Time Object Detection with YOLO and Gradio"
-)
-
-# Launch Gradio app
-if __name__ == "__main__":
-    webcam_interface.launch()
+import cv2
+
+def transform_cv2(frame, transform):
+    if transform == "cartoon":
+        # prepare color
+        img_color = cv2.pyrDown(cv2.pyrDown(frame))
+        for _ in range(6):
+            img_color = cv2.bilateralFilter(img_color, 9, 9, 7)
+        img_color = cv2.pyrUp(cv2.pyrUp(img_color))
+
+        # prepare edges
+        img_edges = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
+        img_edges = cv2.adaptiveThreshold(
+            cv2.medianBlur(img_edges, 7),
+            255,
+            cv2.ADAPTIVE_THRESH_MEAN_C,
+            cv2.THRESH_BINARY,
+            9,
+            2,
+        )
+        img_edges = cv2.cvtColor(img_edges, cv2.COLOR_GRAY2RGB)
+        # combine color and edges
+        img = cv2.bitwise_and(img_color, img_edges)
+        return img
+    elif transform == "edges":
+        # perform edge detection
+        img = cv2.cvtColor(cv2.Canny(frame, 100, 200), cv2.COLOR_GRAY2BGR)
+        return img
+    else:
+        return np.flipud(frame)
+
+
+css=""".my-group {max-width: 500px !important; max-height: 500px !important;}
+            .my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
+
+with gr.Blocks(css=css) as demo:
+    with gr.Column(elem_classes=["my-column"]):
+        with gr.Group(elem_classes=["my-group"]):
+            transform = gr.Dropdown(choices=["cartoon", "edges", "flip"],
+                                    value="flip", label="Transformation")
+            input_img = gr.Image(sources=["webcam"], type="numpy", streaming=True)
+    input_img.stream(transform_cv2, [input_img, transform], [input_img], time_limit=30, stream_every=0.1)
+
+
+demo.launch()
+