Update app.py

app.py

@@ -40,7 +40,7 @@ def load_model(model_repo_id):
 def predict(pilimg):
 
     image_np = pil_image_as_numpy_array(pilimg)
-    return predict2(image_np)
+    return predict2(image_np),predict3(image_np)
 
 def predict2(image_np):
 
@@ -68,12 +68,8 @@ def predict2(image_np):
     
     return result_pil_img2
 
-def predict3(pilimg):
 
-    image_np = pil_image_as_numpy_array(pilimg)
-    return predict4(image_np)
-
-def predict4(image_np):
+def predict3(image_np):
 
     results = detection_model2(image_np)
 
@@ -99,50 +95,50 @@ def predict4(image_np):
     
     return result_pil_img4
 
-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 = 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()
+# 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 = 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()
 
 a = os.path.join(os.path.dirname(__file__), "data/c_base_detected.mp4")  # Video
 b = os.path.join(os.path.dirname(__file__), "data/c_tuned_detected.mp4")  # Video
 
-def video_demo(video1, video2):
-    return [video1, video2]
+# def video_demo(video1, video2):
+#     return [video1, video2]
 
 label_id_offset = 0    
 REPO_ID = "apailang/mytfodmodel"
@@ -173,24 +169,22 @@ test12 = os.path.join(os.path.dirname(__file__), "data/test12.jpeg")
 base_image = gr.Interface(
     fn=predict,
     inputs=[gr.Image(type="pil"),gr.Slider(minimum=0.01, maximum=0.99, value=0.6 ,label="Threshold(WIP)",info="[not in used]to set prediction confidence threshold")],
-    outputs=gr.Image(type="pil"),
-    title="Luffy and Chopper face detection (Base mobile net model)",
-    description="Upload a Image for prediction or click on below examples. Prediction confident >38%",
-    examples=[[test1],[test2],[test3],[test4],[test5],[test6],[test7],[test8],[test9],[test10],[test11],[test12],],
-    cache_examples=True
-    )#.launch(share=True)
-
-tuned_image = gr.Interface(
-    fn=predict3,
-    inputs=gr.Image(type="pil"),
-    outputs=gr.Image(type="pil"),
-    title="Luffy and Chopper face detection (tuned mobile net model)",
-    description="Upload a Image for prediction or click on below examples. Mobile net tuned with data Augmentation. Prediction confident >38%",
+    outputs=[gr.Image(type="pil",label="Base Model"),gr.Image(type="pil",label="Tuned Model")],
+    title="Luffy and Chopper Head detection. SSD mobile net V2 320x320",
+    description="Upload a Image for prediction or click on below examples. Prediction confident >38% will be shown in dectected images. Threshold slider is WIP",
     examples=[[test1],[test2],[test3],[test4],[test5],[test6],[test7],[test8],[test9],[test10],[test11],[test12],],
     cache_examples=True
     )#.launch(share=True)
 
-
+# tuned_image = gr.Interface(
+#     fn=predict3,
+#     inputs=gr.Image(type="pil"),
+#     outputs=gr.Image(type="pil"),
+#     title="Luffy and Chopper face detection on images. Result comparison of base vs tuned SSD mobile net V2 320x320",
+#     description="Upload a Image for prediction or click on below examples. Mobile net tuned with data Augmentation. Prediction confident >38%",
+#     examples=[[test1],[test2],[test3],[test4],[test5],[test6],[test7],[test8],[test9],[test10],[test11],[test12],],
+#     cache_examples=True
+#     )#.launch(share=True)
 
 # a = os.path.join(os.path.dirname(__file__), "data/a.mp4")  # Video
 # b = os.path.join(os.path.dirname(__file__), "data/b.mp4")  # Video
@@ -211,19 +205,18 @@ tuned_image = gr.Interface(
 # )
 
 
-
 video = gr.Interface(
     fn=lambda x,y: [x,y], #video_demo,
     inputs=[gr.Video(label="base model Video"),gr.Video(label="tuned model Video")], 
-    outputs=[gr.Video(label="base model"), gr.Video(label="Tuned model")],
+    outputs=[gr.Video(label="Base model inferenced video"), gr.Video(label="Tuned model inferenced video")],
     examples=[
         [a, b]
     ],
-    title="Comparing base vs tuned detected video",
-    description="using SSD mobile net V2 320x320. Model has been customed trained to detect Character of Luffy and Chopper"
+    title="Luffy and Chopper face detection on video Result comparison of base vs tuned SSD mobile net V2 320x320",
+    description="Model has been customed trained to detect Character of Luffy and Chopper with Prediction confident >10%. Videos are pre-inferenced to reduce load time. (Browser zoom out to view right columne - top (base model inference) & bottom(tuned model inference)) "
 )
 
-demo = gr.TabbedInterface([base_image,tuned_image, video], ["Image (Base Model)","Image (Tuned Model)", "Display Detected Video"])
+demo = gr.TabbedInterface([base_image, video], ["Images", "Video"])
 
 
 if __name__ == "__main__":