Update web-demos/hugging_face/app.py

web-demos/hugging_face/app.py

@@ -233,51 +233,9 @@ def show_mask(video_state, interactive_state, mask_dropdown):
 # tracking vos
 def vos_tracking_video(video_state, interactive_state, mask_dropdown):
     operation_log = [("",""), ("Tracking finished! Try to click the Inpainting button to get the inpainting result.","Normal")]
+    masks, logits, painted_images = model.generator(images=following_frames, template_mask=template_mask)
     model.cutie.clear_memory()
-    if interactive_state["track_end_number"]:
-        following_frames = video_state["origin_images"][video_state["select_frame_number"]:interactive_state["track_end_number"]]
-    else:
-        following_frames = video_state["origin_images"][video_state["select_frame_number"]:]
-
-    if interactive_state["multi_mask"]["masks"]:
-        if len(mask_dropdown) == 0:
-            mask_dropdown = ["mask_001"]
-        mask_dropdown.sort()
-        template_mask = interactive_state["multi_mask"]["masks"][int(mask_dropdown[0].split("_")[1]) - 1] * (int(mask_dropdown[0].split("_")[1]))
-        for i in range(1,len(mask_dropdown)):
-            mask_number = int(mask_dropdown[i].split("_")[1]) - 1 
-            template_mask = np.clip(template_mask+interactive_state["multi_mask"]["masks"][mask_number]*(mask_number+1), 0, mask_number+1)
-        video_state["masks"][video_state["select_frame_number"]]= template_mask
-    else:      
-        template_mask = video_state["masks"][video_state["select_frame_number"]]
-    fps = video_state["fps"]
-
-    # operation error
-    if len(np.unique(template_mask))==1:
-        template_mask[0][0]=1
-        operation_log = [("Please add at least one mask to track by clicking the image in step2.","Error"), ("","")]
-        # return video_output, video_state, interactive_state, operation_error
-    chunk_size = 5
-    masks = []
-    logits = []
-    painted_images = []
-
-    for start in range(0, len(following_frames), chunk_size):
-        end = min(start + chunk_size, len(following_frames))
-        chunk_frames = following_frames[start:end]
-
-    # всегда используем одну и ту же template_mask
-        chunk_masks, chunk_logits, chunk_painted = model.generator(
-            images=chunk_frames,
-            template_mask=template_mask
-        )
-
-        masks.extend(chunk_masks)
-        logits.extend(chunk_logits)
-        painted_images.extend(chunk_painted)
-
-
-    model.cutie.clear_memory()
+    
 
     if interactive_state["track_end_number"]: 
         video_state["masks"][video_state["select_frame_number"]:interactive_state["track_end_number"]] = masks