Update app.py

app.py

@@ -1,58 +1,104 @@
 import gradio as gr
-import torch
-from sahi.prediction import ObjectPrediction
-from sahi.utils.cv import visualize_object_predictions, read_image
-from ultralyticsplus import YOLO, render_result
-
-
-def yolov8_inference(
-    image,
-    model_path,
-    image_size,
-    conf_threshold,
-    iou_threshold,
-):
-    """
-    YOLOv8 inference function
-    Args:
-        image: Input image
-        model_path: Path to the model
-        image_size: Image size
-        conf_threshold: Confidence threshold
-        iou_threshold: IOU threshold
-    Returns:
-        Rendered image
-    """
-    model = YOLO('yolov8l')
-    # set model parameters
-    model.overrides['conf'] = conf_threshold  # NMS confidence threshold
-    model.overrides['iou'] = iou_threshold  # NMS IoU threshold
-    model.overrides['agnostic_nms'] = False  # NMS class-agnostic
-    model.overrides['max_det'] = 1000  # maximum number of detections per image
-    results = model.predict(image, imgsz=image_size)
-    render = render_result(model=model, image=image, result=results[0])
-    return render
-        
-
-inputs = [
-    gr.Image(type="filepath", label="Input Image"),
-    gr.Dropdown(["yolov8n", "yolov8m", "yolov8l", "yolov8x"], 
-                       value="yolov8m", label="Model"),
-    gr.Slider(minimum=320, maximum=1280, value=640, step=320, label="Image Size"),
-    gr.Slider(minimum=0.0, maximum=1.0, value=0.25, step=0.05, label="Confidence Threshold"),
-    gr.Slider(minimum=0.0, maximum=1.0, value=0.45, step=0.05, label="IOU Threshold"),
+import cv2
+import requests
+import os
+
+from ultralytics import YOLO
+
+file_urls = [
+    'https://www.dropbox.com/s/b5g97xo901zb3ds/pothole_example.jpg?dl=1',
+    'https://www.dropbox.com/s/86uxlxxlm1iaexa/pothole_screenshot.png?dl=1',
+    'https://www.dropbox.com/s/7sjfwncffg8xej2/video_7.mp4?dl=1'
 ]
 
-outputs = gr.Image(type="filepath", label="Output Image")
-title = "YOLOv8 Models for Object detection"
-
-# examples = [['demo_01.jpg', 'yolov8n', 640, 0.25, 0.45], ['demo_02.jpg', 'yolov8l', 640, 0.25, 0.45], ['demo_03.jpg', 'yolov8x', 1280, 0.25, 0.45]]
-demo_app = gr.Interface(
-    fn=yolov8_inference,
-    inputs=inputs,
-    outputs=outputs,
-    title=title,
-    # examples=examples,
-    cache_examples=True,
+def download_file(url, save_name):
+    url = url
+    if not os.path.exists(save_name):
+        file = requests.get(url)
+        open(save_name, 'wb').write(file.content)
+
+for i, url in enumerate(file_urls):
+    if 'mp4' in file_urls[i]:
+        download_file(
+            file_urls[i],
+            f"video.mp4"
+        )
+    else:
+        download_file(
+            file_urls[i],
+            f"image_{i}.jpg"
+        )
+
+model = YOLO('best.pt')
+path  = [['image_0.jpg'], ['image_1.jpg']]
+video_path = [['video.mp4']]
+
+def show_preds_image(image_path):
+    image = cv2.imread(image_path)
+    outputs = model.predict(source=image_path)
+    results = outputs[0].cpu().numpy()
+    for i, det in enumerate(results.boxes.xyxy):
+        cv2.rectangle(
+            image,
+            (int(det[0]), int(det[1])),
+            (int(det[2]), int(det[3])),
+            color=(0, 0, 255),
+            thickness=2,
+            lineType=cv2.LINE_AA
+        )
+    return cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+inputs_image = [
+    gr.components.Image(type="filepath", label="Input Image"),
+]
+outputs_image = [
+    gr.components.Image(type="numpy", label="Output Image"),
+]
+interface_image = gr.Interface(
+    fn=show_preds_image,
+    inputs=inputs_image,
+    outputs=outputs_image,
+    title="Pothole detector app",
+    examples=path,
+    cache_examples=False,
 )
-demo_app.launch(debug=True)
+
+def show_preds_video(video_path):
+    cap = cv2.VideoCapture(video_path)
+    while(cap.isOpened()):
+        ret, frame = cap.read()
+        if ret:
+            frame_copy = frame.copy()
+            outputs = model.predict(source=frame)
+            results = outputs[0].cpu().numpy()
+            for i, det in enumerate(results.boxes.xyxy):
+                cv2.rectangle(
+                    frame_copy,
+                    (int(det[0]), int(det[1])),
+                    (int(det[2]), int(det[3])),
+                    color=(0, 0, 255),
+                    thickness=2,
+                    lineType=cv2.LINE_AA
+                )
+            yield cv2.cvtColor(frame_copy, cv2.COLOR_BGR2RGB)
+
+inputs_video = [
+    gr.components.Video(type="filepath", label="Input Video"),
+
+]
+outputs_video = [
+    gr.components.Image(type="numpy", label="Output Image"),
+]
+interface_video = gr.Interface(
+    fn=show_preds_video,
+    inputs=inputs_video,
+    outputs=outputs_video,
+    title="Pothole detector",
+    examples=video_path,
+    cache_examples=False,
+)
+
+gr.TabbedInterface(
+    [interface_image, interface_video],
+    tab_names=['Image inference', 'Video inference']
+).queue().launch()