3d change

main_noweb.py

@@ -2,8 +2,6 @@
 import mmpose
 from mmpose.apis import MMPoseInferencer
 
-# Ultralytics
-from ultralytics import YOLO
 import torch
 
 # Gradio
@@ -32,10 +30,9 @@ else:
 os.system("nvidia-smi")
 
 print("[INFO]: Imported modules!")
-human = MMPoseInferencer("dekr_hrnet-w32_8xb10-140e_coco-512x512")
+human = MMPoseInferencer("dekr_hrnet-w32_8xb10-140e_coco-512x512") # ipr_res50_debias-8xb64-210e_coco-256x256-055a7699_20220913
 hand = MMPoseInferencer("hand")
-human3d = MMPoseInferencer(pose3d="human3d")
-track_model = YOLO('yolov8n.pt')  # Load an official Detect model
+human3d = MMPoseInferencer("simplebaseline3d_h36m") # pose3d="human3d"
 
 print("[INFO]: Downloaded models!")
 
@@ -62,56 +59,6 @@ def check_extension(video):
     return video
 
 
-def tracking(video, model, boxes=True):
-    print("[INFO] Is cuda available? ", torch.cuda.is_available())
-    print(device)
-
-    print("[INFO] Loading model...")
-    # Load an official or custom model
-
-    # Perform tracking with the model
-    print("[INFO] Starting tracking!")
-    # https://docs.ultralytics.com/modes/predict/
-    annotated_frame = model(video, boxes=boxes, device=device)
-
-    return annotated_frame
-
-def show_tracking(video_content):
-
-        # https://docs.ultralytics.com/datasets/detect/coco/
-        video = cv2.VideoCapture(video_content)
-
-        # Track
-        video_track = tracking(video_content, track_model.track)
-
-        # Prepare to save video
-        #out_file = os.path.join(vis_out_dir, "track.mp4")
-        out_file = "track.mp4"
-        print("[INFO]: TRACK", out_file)
-
-        fourcc = cv2.VideoWriter_fourcc(*"mp4v")  # Codec for MP4 video
-        fps = video.get(cv2.CAP_PROP_FPS)
-        height, width, _ = video_track[0][0].orig_img.shape
-        size = (width,height)
-
-        out_track = cv2.VideoWriter(out_file, fourcc, fps, size)
-
-        # Go through frames and write them 
-        for frame_track in video_track:
-            result_track = frame_track[0].plot()  # plot a BGR numpy array of predictions
-            out_track.write(result_track)
-
-        print("[INFO] Done with frames")
-        #print(type(result_pose)) numpy ndarray
-    
-        out_track.release()
-
-        video.release()
-        cv2.destroyAllWindows() # Closing window
-
-        return out_file
-
-
 def pose3d(video, kpt_threshold):
     video = check_extension(video)
     print(device)