sports2d 0.8.26__tar.gz → 0.8.27__tar.gz

{sports2d-0.8.26/sports2d.egg-info → sports2d-0.8.27}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sports2d
-Version: 0.8.26
+Version: 0.8.27
 Summary: Compute 2D human pose and angles from a video or a webcam.
 Author-email: David Pagnon <contact@david-pagnon.com>
 Maintainer-email: David Pagnon <contact@david-pagnon.com>
@@ -23,7 +23,7 @@ Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: imageio_ffmpeg
-Requires-Dist: Pose2Sim>=0.10.38
+Requires-Dist: Pose2Sim>=0.10.40
 Dynamic: license-file
 
 
@@ -100,23 +100,23 @@ If you need 3D research-grade markerless joint kinematics, consider using severa
       1. [Run the demo](#run-the-demo)
       2. [Visualize in OpenSim](#visualize-in-opensim)
       3. [Visualize in Blender](#visualize-in-blender)
-   3. [Play with the parameters](#play-with-the-parameters)
-      1. [Run on a custom video or on a webcam](#run-on-a-custom-video-or-on-a-webcam)
-      2. [Run for a specific time range](#run-for-a-specific-time-range)
-      3. [Select the persons you are interested in](#select-the-persons-you-are-interested-in)
-      4. [Get coordinates in meters](#get-coordinates-in-meters)
-      5. [Run inverse kinematics](#run-inverse-kinematics)
-      6. [Run on several videos at once](#run-on-several-videos-at-once)
-      7. [Use the configuration file or run within Python](#use-the-configuration-file-or-run-within-python)
-      8. [Get the angles the way you want](#get-the-angles-the-way-you-want)
-      9. [Customize your output](#customize-your-output)
-      10. [Use a custom pose estimation model](#use-a-custom-pose-estimation-model)
-      11. [All the parameters](#all-the-parameters)
-2. [Go further](#go-further)
+2. [Play with the parameters](#play-with-the-parameters)
+   1. [Run on a custom video or on a webcam](#run-on-a-custom-video-or-on-a-webcam)
+   2. [Run for a specific time range](#run-for-a-specific-time-range)
+   3. [Select the persons you are interested in](#select-the-persons-you-are-interested-in)
+   4. [Get coordinates in meters](#get-coordinates-in-meters)
+   5. [Run inverse kinematics](#run-inverse-kinematics)
+   6. [Run on several videos at once](#run-on-several-videos-at-once)
+   7. [Use the configuration file or run within Python](#use-the-configuration-file-or-run-within-python)
+   8. [Get the angles the way you want](#get-the-angles-the-way-you-want)
+   9. [Customize your output](#customize-your-output)
+   10. [Use a custom pose estimation model](#use-a-custom-pose-estimation-model)
+   11. [All the parameters](#all-the-parameters)
+3. [Go further](#go-further)
    1. [Too slow for you?](#too-slow-for-you)
    3. [Run inverse kinematics](#run-inverse-kinematics)
    4. [How it works](#how-it-works)
-3. [How to cite and how to contribute](#how-to-cite-and-how-to-contribute)
+4. [How to cite and how to contribute](#how-to-cite-and-how-to-contribute)
 
 <br>
 

{sports2d-0.8.26 → sports2d-0.8.27}/README.md

@@ -72,23 +72,23 @@ If you need 3D research-grade markerless joint kinematics, consider using severa
       1. [Run the demo](#run-the-demo)
       2. [Visualize in OpenSim](#visualize-in-opensim)
       3. [Visualize in Blender](#visualize-in-blender)
-   3. [Play with the parameters](#play-with-the-parameters)
-      1. [Run on a custom video or on a webcam](#run-on-a-custom-video-or-on-a-webcam)
-      2. [Run for a specific time range](#run-for-a-specific-time-range)
-      3. [Select the persons you are interested in](#select-the-persons-you-are-interested-in)
-      4. [Get coordinates in meters](#get-coordinates-in-meters)
-      5. [Run inverse kinematics](#run-inverse-kinematics)
-      6. [Run on several videos at once](#run-on-several-videos-at-once)
-      7. [Use the configuration file or run within Python](#use-the-configuration-file-or-run-within-python)
-      8. [Get the angles the way you want](#get-the-angles-the-way-you-want)
-      9. [Customize your output](#customize-your-output)
-      10. [Use a custom pose estimation model](#use-a-custom-pose-estimation-model)
-      11. [All the parameters](#all-the-parameters)
-2. [Go further](#go-further)
+2. [Play with the parameters](#play-with-the-parameters)
+   1. [Run on a custom video or on a webcam](#run-on-a-custom-video-or-on-a-webcam)
+   2. [Run for a specific time range](#run-for-a-specific-time-range)
+   3. [Select the persons you are interested in](#select-the-persons-you-are-interested-in)
+   4. [Get coordinates in meters](#get-coordinates-in-meters)
+   5. [Run inverse kinematics](#run-inverse-kinematics)
+   6. [Run on several videos at once](#run-on-several-videos-at-once)
+   7. [Use the configuration file or run within Python](#use-the-configuration-file-or-run-within-python)
+   8. [Get the angles the way you want](#get-the-angles-the-way-you-want)
+   9. [Customize your output](#customize-your-output)
+   10. [Use a custom pose estimation model](#use-a-custom-pose-estimation-model)
+   11. [All the parameters](#all-the-parameters)
+3. [Go further](#go-further)
    1. [Too slow for you?](#too-slow-for-you)
    3. [Run inverse kinematics](#run-inverse-kinematics)
    4. [How it works](#how-it-works)
-3. [How to cite and how to contribute](#how-to-cite-and-how-to-contribute)
+4. [How to cite and how to contribute](#how-to-cite-and-how-to-contribute)
 
 <br>
 

{sports2d-0.8.26 → sports2d-0.8.27}/Sports2D/Demo/Config_demo.toml

@@ -89,7 +89,7 @@ det_frequency = 4       # Run person detection only every N frames, and inbetwee
 device = 'auto' # 'auto', 'CPU', 'CUDA', 'MPS', 'ROCM'
 backend = 'auto' # 'auto', 'openvino', 'onnxruntime', 'opencv'
 tracking_mode = 'sports2d' # 'sports2d' or 'deepsort'. 'deepsort' is slower, harder to parametrize but can be more robust if correctly tuned
-# deepsort_params = """{'max_age':30, 'n_init':3, 'max_cosine_distance':0.3, 'max_iou_distance':0.8, 'embedder_gpu': True, embedder':'torchreid'}""" # """{dictionary between 3 double quotes}"""
+# deepsort_params = """{'max_age':30, 'n_init':3, 'max_cosine_distance':0.3, 'max_iou_distance':0.8, 'embedder_gpu': True, 'embedder':'torchreid'}""" # """{dictionary between 3 double quotes}"""
                   # More robust in crowded scenes but tricky to parametrize. More information there: https://github.com/levan92/deep_sort_realtime/blob/master/deep_sort_realtime/deepsort_tracker.py#L51
                   # Requires `pip install torch torchvision torchreid gdown tensorboard`
 

{sports2d-0.8.26 → sports2d-0.8.27}/Sports2D/process.py

@@ -75,29 +75,32 @@ import matplotlib as mpl
 import matplotlib.pyplot as plt
 from matplotlib.widgets import Slider, Button
 from matplotlib import patheffects
-
-from rtmlib import PoseTracker, BodyWithFeet, Wholebody, Body, Hand, Custom
 from rtmlib.tools.object_detection.post_processings import nms
 
 from Sports2D.Utilities.common import *
 from Pose2Sim.common import *
 from Pose2Sim.skeletons import *
 from Pose2Sim.calibration import toml_write
+from Pose2Sim.poseEstimation import setup_model_class_mode, setup_backend_device, setup_pose_tracker
 from Pose2Sim.triangulation import indices_of_first_last_non_nan_chunks
 from Pose2Sim.personAssociation import *
 from Pose2Sim.filtering import *
 
-# Silence numpy "RuntimeWarning: Mean of empty slice"
-import warnings
+os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'
+np.set_printoptions(legacy='1.21') # otherwise prints np.float64(3.0) rather than 3.0
+import warnings # Silence numpy and CoreML warnings
 warnings.filterwarnings("ignore", category=RuntimeWarning, message="Mean of empty slice")
 warnings.filterwarnings("ignore", category=RuntimeWarning, message="All-NaN slice encountered")
 warnings.filterwarnings("ignore", category=RuntimeWarning, message="invalid value encountered in scalar divide")
+warnings.filterwarnings("ignore", message=".*Input.*has a dynamic shape.*but the runtime shape.*has zero elements.*")
+
 
 # Not safe, but to be used until OpenMMLab/RTMlib's SSL certificates are updated
 import ssl
 ssl._create_default_https_context = ssl._create_unverified_context
 
 
+CORRECTION_2D_TO_3D = 1.063  # Corrective factor for height calculation: segments do not perfectly lie in the 2D plane and look shorter than in 3D
 DEFAULT_MASS = 70
 DEFAULT_HEIGHT = 1.7
 
@@ -206,165 +209,6 @@ def setup_video(video_file_path, vid_output_path, save_vid):
     return cap, out_vid, cam_width, cam_height, fps
 
 
-def setup_model_class_mode(pose_model, mode, config_dict={}):
-    '''
-    Set up the pose model class and mode for the pose tracker.
-    '''
-
-    if pose_model.upper() in ('HALPE_26', 'BODY_WITH_FEET'):
-        model_name = 'HALPE_26'
-        ModelClass = BodyWithFeet # 26 keypoints(halpe26)
-        logging.info(f"Using HALPE_26 model (body and feet) for pose estimation in {mode} mode.")
-    elif pose_model.upper() in ('COCO_133', 'WHOLE_BODY', 'WHOLE_BODY_WRIST'):
-        model_name = 'COCO_133'
-        ModelClass = Wholebody
-        logging.info(f"Using COCO_133 model (body, feet, hands, and face) for pose estimation in {mode} mode.")
-    elif pose_model.upper() in ('COCO_17', 'BODY'):
-        model_name = 'COCO_17'
-        ModelClass = Body
-        logging.info(f"Using COCO_17 model (body) for pose estimation in {mode} mode.")
-    elif pose_model.upper() =='HAND':
-        model_name = 'HAND_21'
-        ModelClass = Hand
-        logging.info(f"Using HAND_21 model for pose estimation in {mode} mode.")
-    elif pose_model.upper() =='FACE':
-        model_name = 'FACE_106'
-        logging.info(f"Using FACE_106 model for pose estimation in {mode} mode.")
-    elif pose_model.upper() =='ANIMAL':
-        model_name = 'ANIMAL2D_17'
-        logging.info(f"Using ANIMAL2D_17 model for pose estimation in {mode} mode.")
-    else:
-        model_name = pose_model.upper()
-        logging.info(f"Using model {model_name} for pose estimation in {mode} mode.")
-    try:
-        pose_model = eval(model_name)
-    except:
-        try: # from Config.toml
-            from anytree.importer import DictImporter
-            model_name = pose_model.upper()
-            pose_model = DictImporter().import_(config_dict.get('pose').get(pose_model)[0])
-            if pose_model.id == 'None':
-                pose_model.id = None
-            logging.info(f"Using model {model_name} for pose estimation.")
-        except:
-            raise NameError(f'{pose_model} not found in skeletons.py nor in Config.toml')
-
-    # Manually select the models if mode is a dictionary rather than 'lightweight', 'balanced', or 'performance'
-    if not mode in ['lightweight', 'balanced', 'performance'] or 'ModelClass' not in locals():
-        try:
-            from functools import partial
-            try:
-                mode = ast.literal_eval(mode)
-            except: # if within single quotes instead of double quotes when run with sports2d --mode """{dictionary}"""
-                mode = mode.strip("'").replace('\n', '').replace(" ", "").replace(",", '", "').replace(":", '":"').replace("{", '{"').replace("}", '"}').replace('":"/',':/').replace('":"\\',':\\')
-                mode = re.sub(r'"\[([^"]+)",\s?"([^"]+)\]"', r'[\1,\2]', mode) # changes "[640", "640]" to [640,640]
-                mode = json.loads(mode)
-            det_class = mode.get('det_class')
-            det = mode.get('det_model')
-            det_input_size = mode.get('det_input_size')
-            pose_class = mode.get('pose_class')
-            pose = mode.get('pose_model')
-            pose_input_size = mode.get('pose_input_size')
-
-            ModelClass = partial(Custom,
-                        det_class=det_class, det=det, det_input_size=det_input_size,
-                        pose_class=pose_class, pose=pose, pose_input_size=pose_input_size)
-            logging.info(f"Using model {model_name} with the following custom parameters: {mode}.")
-
-            if pose_class == 'RTMO' and model_name != 'COCO_17':
-                logging.warning("RTMO currently only supports 'Body' pose_model. Switching to 'Body'.")
-                pose_model = eval('COCO_17')
-            
-        except (json.JSONDecodeError, TypeError):
-            logging.warning("Invalid mode. Must be 'lightweight', 'balanced', 'performance', or '''{dictionary}''' of parameters within triple quotes. Make sure input_sizes are within square brackets.")
-            logging.warning('Using the default "balanced" mode.')
-            mode = 'balanced'
-
-    return pose_model, ModelClass, mode
-
-
-def setup_backend_device(backend='auto', device='auto'):
-    '''
-    Set up the backend and device for the pose tracker based on the availability of hardware acceleration.
-    TensorRT is not supported by RTMLib yet: https://github.com/Tau-J/rtmlib/issues/12
-
-    If device and backend are not specified, they are automatically set up in the following order of priority:
-    1. GPU with CUDA and ONNXRuntime backend (if CUDAExecutionProvider is available)
-    2. GPU with ROCm and ONNXRuntime backend (if ROCMExecutionProvider is available, for AMD GPUs)
-    3. GPU with MPS or CoreML and ONNXRuntime backend (for macOS systems)
-    4. CPU with OpenVINO backend (default fallback)
-    '''
-
-    if device!='auto' and backend!='auto':
-        device = device.lower()
-        backend = backend.lower()
-
-    if device=='auto' or backend=='auto':
-        if device=='auto' and backend!='auto' or device!='auto' and backend=='auto':
-            logging.warning(f"If you set device or backend to 'auto', you must set the other to 'auto' as well. Both device and backend will be determined automatically.")
-
-        try:
-            import torch
-            import onnxruntime as ort
-            if torch.cuda.is_available() == True and 'CUDAExecutionProvider' in ort.get_available_providers():
-                device = 'cuda'
-                backend = 'onnxruntime'
-                logging.info(f"\nValid CUDA installation found: using ONNXRuntime backend with GPU.")
-            elif torch.cuda.is_available() == True and 'ROCMExecutionProvider' in ort.get_available_providers():
-                device = 'rocm'
-                backend = 'onnxruntime'
-                logging.info(f"\nValid ROCM installation found: using ONNXRuntime backend with GPU.")
-            else:
-                raise 
-        except:
-            try:
-                import onnxruntime as ort
-                if 'MPSExecutionProvider' in ort.get_available_providers() or 'CoreMLExecutionProvider' in ort.get_available_providers():
-                    device = 'mps'
-                    backend = 'onnxruntime'
-                    logging.info(f"\nValid MPS installation found: using ONNXRuntime backend with GPU.")
-                else:
-                    raise
-            except:
-                device = 'cpu'
-                backend = 'openvino'
-                logging.info(f"\nNo valid CUDA installation found: using OpenVINO backend with CPU.")
-        
-    return backend, device
-
-
-def setup_pose_tracker(ModelClass, det_frequency, mode, tracking, backend, device):
-    '''
-    Set up the RTMLib pose tracker with the appropriate model and backend.
-    If CUDA is available, use it with ONNXRuntime backend; else use CPU with openvino
-
-    INPUTS:
-    - ModelClass: class. The RTMlib model class to use for pose detection (Body, BodyWithFeet, Wholebody)
-    - det_frequency: int. The frequency of pose detection (every N frames)
-    - mode: str. The mode of the pose tracker ('lightweight', 'balanced', 'performance')
-    - tracking: bool. Whether to track persons across frames with RTMlib tracker
-    - backend: str. The backend to use for pose detection (onnxruntime, openvino, opencv)
-    - device: str. The device to use for pose detection (cpu, cuda, rocm, mps)
-
-    OUTPUTS:
-    - pose_tracker: PoseTracker. The initialized pose tracker object    
-    '''
-
-    backend, device = setup_backend_device(backend=backend, device=device)
-
-    # Initialize the pose tracker with Halpe26 model
-    pose_tracker = PoseTracker(
-        ModelClass,
-        det_frequency=det_frequency,
-        mode=mode,
-        backend=backend,
-        device=device,
-        tracking=tracking,
-        to_openpose=False)
-        
-    return pose_tracker
-
-
 def flip_left_right_direction(person_X, L_R_direction_idx, keypoints_names, keypoints_ids):
     '''
     Flip the points to the right or left for more consistent angle calculation 
@@ -1959,7 +1803,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
                     #             cv2.circle(frame, (int(kpt[0]), int(kpt[1])), 3, colors[person_idx%len(colors)], -1)
                     #     if not np.isnan(bboxes[person_idx]).any():
                     #         cv2.rectangle(frame, (int(bboxes[person_idx][0]), int(bboxes[person_idx][1])), (int(bboxes[person_idx][2]), int(bboxes[person_idx][3])), colors[person_idx%len(colors)], 1)
-                    #     cv2.imshow(f'{video_file} Sports2D', frame)
+                    # cv2.imshow(f'{video_file} Sports2D', frame)
 
                     # Track poses across frames
                     if tracking_mode == 'deepsort':
@@ -2308,8 +2152,8 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
         if to_meters and save_pose:
             logging.info('\nConverting pose to meters:')
             
-            # Compute height in px of the first person
-            height_px = compute_height(trc_data[0].iloc[:,1:], new_keypoints_names,
+            # Compute height of the first person in pixels
+            height_px = CORRECTION_2D_TO_3D * compute_height(trc_data[0].iloc[:,1:], new_keypoints_names,
                                         fastest_frames_to_remove_percent=fastest_frames_to_remove_percent, close_to_zero_speed=close_to_zero_speed_px, large_hip_knee_angles=large_hip_knee_angles, trimmed_extrema_percent=trimmed_extrema_percent)
 
             # Compute distance from camera to compensate for perspective effects

{sports2d-0.8.26 → sports2d-0.8.27}/pyproject.toml

@@ -34,7 +34,7 @@ classifiers = [
 urls = {Homepage = "https://github.com/davidpagnon/Sports2D", "Bug Tracker" = "https://github.com/davidpagnon/Sports2D/issues"}
 dependencies = [
     "imageio_ffmpeg",
-    "Pose2Sim>=0.10.38"
+    "Pose2Sim>=0.10.40"
 ]
 
 [tool.setuptools_scm]

{sports2d-0.8.26 → sports2d-0.8.27/sports2d.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sports2d
-Version: 0.8.26
+Version: 0.8.27
 Summary: Compute 2D human pose and angles from a video or a webcam.
 Author-email: David Pagnon <contact@david-pagnon.com>
 Maintainer-email: David Pagnon <contact@david-pagnon.com>
@@ -23,7 +23,7 @@ Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: imageio_ffmpeg
-Requires-Dist: Pose2Sim>=0.10.38
+Requires-Dist: Pose2Sim>=0.10.40
 Dynamic: license-file
 
 
@@ -100,23 +100,23 @@ If you need 3D research-grade markerless joint kinematics, consider using severa
       1. [Run the demo](#run-the-demo)
       2. [Visualize in OpenSim](#visualize-in-opensim)
       3. [Visualize in Blender](#visualize-in-blender)
-   3. [Play with the parameters](#play-with-the-parameters)
-      1. [Run on a custom video or on a webcam](#run-on-a-custom-video-or-on-a-webcam)
-      2. [Run for a specific time range](#run-for-a-specific-time-range)
-      3. [Select the persons you are interested in](#select-the-persons-you-are-interested-in)
-      4. [Get coordinates in meters](#get-coordinates-in-meters)
-      5. [Run inverse kinematics](#run-inverse-kinematics)
-      6. [Run on several videos at once](#run-on-several-videos-at-once)
-      7. [Use the configuration file or run within Python](#use-the-configuration-file-or-run-within-python)
-      8. [Get the angles the way you want](#get-the-angles-the-way-you-want)
-      9. [Customize your output](#customize-your-output)
-      10. [Use a custom pose estimation model](#use-a-custom-pose-estimation-model)
-      11. [All the parameters](#all-the-parameters)
-2. [Go further](#go-further)
+2. [Play with the parameters](#play-with-the-parameters)
+   1. [Run on a custom video or on a webcam](#run-on-a-custom-video-or-on-a-webcam)
+   2. [Run for a specific time range](#run-for-a-specific-time-range)
+   3. [Select the persons you are interested in](#select-the-persons-you-are-interested-in)
+   4. [Get coordinates in meters](#get-coordinates-in-meters)
+   5. [Run inverse kinematics](#run-inverse-kinematics)
+   6. [Run on several videos at once](#run-on-several-videos-at-once)
+   7. [Use the configuration file or run within Python](#use-the-configuration-file-or-run-within-python)
+   8. [Get the angles the way you want](#get-the-angles-the-way-you-want)
+   9. [Customize your output](#customize-your-output)
+   10. [Use a custom pose estimation model](#use-a-custom-pose-estimation-model)
+   11. [All the parameters](#all-the-parameters)
+3. [Go further](#go-further)
    1. [Too slow for you?](#too-slow-for-you)
    3. [Run inverse kinematics](#run-inverse-kinematics)
    4. [How it works](#how-it-works)
-3. [How to cite and how to contribute](#how-to-cite-and-how-to-contribute)
+4. [How to cite and how to contribute](#how-to-cite-and-how-to-contribute)
 
 <br>
 

{sports2d-0.8.26 → sports2d-0.8.27}/sports2d.egg-info/SOURCES.txt

@@ -18,7 +18,6 @@ Content/paper.bib
 Content/paper.md
 Content/sports2d_blender.gif
 Content/sports2d_opensim.gif
-Sports2D/Sports2D.ipynb
 Sports2D/Sports2D.py
 Sports2D/__init__.py
 Sports2D/process.py

sports2d-0.8.27/sports2d.egg-info/requires.txt

@@ -0,0 +1,2 @@
+imageio_ffmpeg
+Pose2Sim>=0.10.40