cuda

main.py

@@ -157,8 +157,7 @@ def pose2dhand(video, kpt_threshold):
     video = check_extension(video)
     print(device)
     # ultraltics
-    if torch.cuda.is_available():
-        device = "cuda"
+
     # Define new unique folder
     add_dir = str(uuid.uuid4())
     vis_out_dir = os.path.join("/".join(video.split("/")[:-1]), add_dir)
@@ -186,7 +185,7 @@ def run_UI():
                     with gr.Column():
                         video_input = gr.Video(source="upload", type="filepath", height=612)
                         # Insert slider with kpt_thr
-                        file_kpthr = gr.Slider(minimum=0.1, maximum=1, step=1e3, default=0.3, label='Keypoint threshold')
+                        file_kpthr = gr.Slider(minimum=0.1, maximum=1, step=20, default=0.3, label='Keypoint threshold')
 
                         submit_pose_file = gr.Button("Make 2d pose estimation")
                         submit_pose3d_file = gr.Button("Make 3d pose estimation")
@@ -205,7 +204,7 @@ def run_UI():
                         with gr.Column():
                             webcam_input = gr.Video(source="webcam", height=612)
                             
-                            web_kpthr = gr.Slider(minimum=0.1, maximum=1, step=1e3, default=0.3, label='Keypoint threshold')
+                            web_kpthr = gr.Slider(minimum=0.1, maximum=1, step=20, default=0.3, label='Keypoint threshold')
 
                             submit_pose_web = gr.Button("Make 2d pose estimation")
                             submit_pose3d_web = gr.Button("Make 3d pose estimation")
@@ -236,7 +235,7 @@ def run_UI():
                             The 3D pose model is used for estimating the 3D coordinates of human body joints from an image or a video frame. The model uses a combination of 2D pose estimation and depth estimation to infer the 3D joint locations. 
                             All of these models are pre-trained on large datasets and can be fine-tuned on custom datasets for specific applications. 
                             
-                            Ultralight detection and tracking model: The `track()` method in the Ultralight model is used for object tracking in videos. It takes a video file or a camera stream as input and returns the tracked objects in each frame. The method uses the COCO dataset classes for object detection and tracking. The COCO dataset contains 80 classes of objects such as person, car, bicycle, etc. The `track()` method uses the COCO classes to detect and track the objects in the video frames.
+                            Ultralight detection and tracking model: The `track()` method in the Ultralight model is used for object tracking in videos. It takes a video file or a camera stream as input and returns the tracked objects in each frame. The method uses the COCO dataset classes for object detection and tracking. The COCO dataset contains 80 classes of objects such as person, car, bicycle, etc. See https://docs.ultralytics.com/datasets/detect/coco/ for all available classes. The `track()` method uses the COCO classes to detect and track the objects in the video frames.
                             The tracked objects are represented as bounding boxes with labels indicating the class of the object. The Ultralight model is designed to be fast and efficient, making it suitable for real-time object tracking applications.""")