feat: fix app.py

app.py

@@ -5,8 +5,14 @@ import os
 
 from ultralytics import YOLO
 
-model = YOLO('best_model.pt')
-example_list = [["examples/" + example] for example in os.listdir("examples")]
+model = YOLO("best_model.pt")
+example_imgs = [
+    os.path.join("example", "img", example) for example in os.listdir("example/img")
+]
+example_vids = [
+    os.path.join("example", "vid", example) for example in os.listdir("example/vid")
+]
+
 
 def show_preds_image(image_path):
     image = cv2.imread(image_path)
@@ -19,61 +25,58 @@ def show_preds_image(image_path):
             (int(det[2]), int(det[3])),
             color=(0, 0, 255),
             thickness=2,
-            lineType=cv2.LINE_AA
+            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"),
-]
+
+def show_preds_image(image_path):
+    image = cv2.imread(image_path)
+    outputs = model.predict(source=image_path)
+    results = outputs[0].cpu().numpy()
+    for det in 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)
+
+
+# Define the Gradio interface for image input
 interface_image = gr.Interface(
     fn=show_preds_image,
-    inputs=inputs_image,
-    outputs=outputs_image,
-    title="Pothole detector",
-    examples=path,
+    inputs=gr.components.Image(type="filepath", label="Input Image"),
+    outputs=gr.components.Image(type="numpy", label="Output Image"),
+    title="Pothole Detector - Image",
+    examples=example_imgs,
     cache_examples=False,
 )
 
+
+# For video processing, it's best to process and then show the output video.
+# This is a simplified placeholder for video processing, indicating where to include the video processing logic.
 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)
+    # Placeholder for video processing function
+    # Process the video here and save the output, then return the path to the processed video
+    processed_video_path = "processed_video.mp4"  # Example output path
+    return processed_video_path
 
-inputs_video = [
-    gr.components.Video(type="filepath", label="Input Video"),
 
-]
-outputs_video = [
-    gr.components.Image(type="numpy", label="Output Image"),
-]
+# Define the Gradio interface for video input
 interface_video = gr.Interface(
     fn=show_preds_video,
-    inputs=inputs_video,
-    outputs=outputs_video,
-    title="Pothole detector",
-    examples=video_path,
+    inputs=gr.components.Video(type="filepath", label="Input Video"),
+    outputs=gr.components.Video(label="Processed Video"),
+    title="Pothole Detector - Video",
+    examples=example_vids,
     cache_examples=False,
 )
 
+# Combine the interfaces into a tabbed interface
 gr.TabbedInterface(
-    [interface_image, interface_video],
-    tab_names=['Image inference', 'Video inference']
-).queue().launch()
+    [interface_image, interface_video], tab_names=["Image Inference", "Video Inference"]
+).launch()