changes to requirements and app.py for video uplaod

app.py

@@ -3,35 +3,69 @@ from PIL import Image
 import gradio as gr
 from huggingface_hub import snapshot_download
 import os
-
-model_path = "/Users/charmchua/Desktop/Y3S2/ATA/ATA_ASSN2/224684P/best_int8_openvino_model"
+import cv2
+import tempfile
 
 def load_model(repo_id):
     download_dir = snapshot_download(repo_id)
     print(download_dir)
-    path  = os.path.join(download_dir, "best_int8_openvino_model")
+    path = os.path.join(download_dir, "best_int8_openvino_model")
     print(path)
     detection_model = YOLO(path, task='detect')
     return detection_model
 
-
-def predict(pilimg):
-
+def predict_image(pilimg):
+    # Process image
     source = pilimg
-    # x = np.asarray(pilimg)
-    # print(x.shape)
     result = detection_model.predict(source, conf=0.5, iou=0.6)
     img_bgr = result[0].plot()
-    out_pilimg = Image.fromarray(img_bgr[..., ::-1])  # RGB-order PIL image
-    
+    out_pilimg = Image.fromarray(img_bgr[..., ::-1])  # Convert BGR to RGB
     return out_pilimg
 
+def predict_video(video_path):
+    # Read video file
+    cap = cv2.VideoCapture(video_path)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    fps = cap.get(cv2.CAP_PROP_FPS)
 
-REPO_ID = "CharmainChua/windowsandcurtains"
+    # Create temporary output file
+    temp_video = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4")
+    out = cv2.VideoWriter(temp_video.name, cv2.VideoWriter_fourcc(*'mp4v'), fps, (width, height))
+
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        # Run YOLO prediction on each frame
+        result = detection_model.predict(frame, conf=0.5, iou=0.6)
+        frame_with_boxes = result[0].plot()
 
+        # Write processed frame to output video
+        out.write(frame_with_boxes)
+
+    cap.release()
+    out.release()
+
+    return temp_video.name
+
+REPO_ID = "CharmainChua/windowsandcurtains"
 detection_model = load_model(REPO_ID)
 
-gr.Interface(fn=predict,
-             inputs=gr.Image(type="pil"),
-             outputs=gr.Image(type="pil")
-             ).launch(share=True)
+# Gradio Interface
+image_input = gr.Interface(
+    fn=predict_image,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Image(type="pil"),
+    label="Object Detection on Image"
+)
+
+video_input = gr.Interface(
+    fn=predict_video,
+    inputs=gr.Video(type="file"),
+    outputs=gr.Video(),
+    label="Object Detection on Video"
+)
+
+gr.TabbedInterface([image_input, video_input], ["Image Detection", "Video Detection"]).launch(share=True)

requirements.txt

@@ -1,2 +1,5 @@
 ultralytics
 huggingface_hub
+gradio
+opencv-python
+Pillow