fix

app.py

@@ -7,8 +7,10 @@ from moviepy.editor import VideoFileClip
 from moviepy.video.io.ImageSequenceClip import ImageSequenceClip
 from ultralytics import YOLO
 
+from configurations import *
+from core.data import format_frame
 from core.model import load_classifier
-from core.inference import FrameProcessor
+from core.inference import detect_object, classify_action, draw_boxes
 print("Tensorflow version " + tf.__version__)
 
 print('Load classifier.')
@@ -24,15 +26,27 @@ def fn(video: gr.Video):
   with tempfile.NamedTemporaryFile(delete=False, suffix=".mp4") as f:
     output = f.name
     clip = VideoFileClip(video)
-    process_frame = FrameProcessor(detector, classifier)
     processed_frames = []
-    for frame in clip.iter_frames():
-      processed_frames.append(process_frame(frame))
-      yield processed_frames[-1], None
+    frames = []
+    actions = []
+    detections = ([], [])
+    for i, frame in enumerate(clip.iter_frames()):
+      if i % classify_action_frame_steps == 0:
+        frames.append(format_frame(frame))
+      if i % detect_object_frame_steps == 0:
+        print(f'Detect object: Frame {i}')
+        detections = detect_object(detector, frame)
+      if len(frames) == classify_action_num_frames:
+        print(f'Classify action: Until frame {i}')
+        actions = classify_action(classifier, frames)
+        frames = []
+      frame = draw_boxes(frame, detections, actions)
+      processed_frames.append(frame)
+      yield frame, None
     processed_clip = ImageSequenceClip(processed_frames, clip.fps)
     processed_clip.audio = clip.audio
-    clip.write_videofile(output, fps=clip.fps, audio_codec='aac', logger=None)
-  yield processed_frames[-1], output
+    processed_clip.write_videofile(output, fps=clip.fps, audio_codec='aac', logger=None)
+  yield frame, output
 
 inputs = gr.Video(sources=['upload'], label='Input Video')
 outputs = [