adding label_maps

app.py

@@ -76,6 +76,44 @@ def predict2(image_np):
     
     return result_pil_img
 
+def detect_video(video):
+    # Create a video capture object
+    cap = cv2.VideoCapture(video)
+
+    # Process frames in a loop
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        # Expand dimensions since model expects images to have shape: [1, None, None, 3]
+        image_np_expanded = np.expand_dims(frame, axis=0)
+
+        # Run inference
+        output_dict = detection_model(image_np_expanded)
+
+        # Extract detections
+        boxes = output_dict['detection_boxes'][0].numpy()
+        scores = output_dict['detection_scores'][0].numpy()
+        classes = output_dict['detection_classes'][0].numpy().astype(np.int64)
+
+        # Draw bounding boxes and labels
+        image_np_with_detections = viz_utils.visualize_boxes_and_labels_on_image_array(
+            frame,
+            boxes,
+            classes,
+            scores,
+            category_index,
+            use_normalized_coordinates=True,
+            max_boxes_to_draw=20,
+            min_score_thresh=.5,
+            agnostic_mode=False)
+
+        # Yield the processed frame
+        yield image_np_with_detections
+
+    # Release resources
+    cap.release()
 
 REPO_ID = "apailang/mytfodmodel"
 detection_model = load_model()
@@ -89,3 +127,12 @@ gr.Interface(fn=predict,
              inputs=gr.Image(type="pil"),
              outputs=gr.Image(type="pil")
              ).launch(share=True)
+
+# iface = gr.Blocks()
+
+# iface.Image(fn=predict, inputs=gr.Image(type="pil"), label="Image Detection",outputs=gr.Image(type="pil"))
+# iface.Video(fn=detect_video, inputs=gr.Video(type="mp4", live=True, label="Input Video"),outputs=gr.Video(type="mp4", label="Detected Video", live=True), label="Video Detection", interpretation="default")
+
+# iface.launch(share=True)
+
+