sports2d 0.8.0__py3-none-any.whl → 0.8.2__py3-none-any.whl

Sports2D/Demo/Config_demo.toml

@@ -93,7 +93,6 @@ tracking_mode = 'sports2d' # 'sports2d' or 'deepsort'. 'deepsort' is slower, har
                   # 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`
 
-
 # Processing parameters
 keypoint_likelihood_threshold = 0.3 # Keypoints whose likelihood is lower will not be taken into account
 average_likelihood_threshold = 0.5  # Person will be ignored if average likelihood of good keypoints is lower than this value

Sports2D/Sports2D.py

@@ -252,7 +252,7 @@ CONFIG_HELP =   {'config': ["C", "path to a toml configuration file"],
                 'device': ["", "Device for pose estimatino can be 'auto', 'openvino', 'onnxruntime', 'opencv'"],
                 'to_meters': ["M", "convert pixels to meters. true if not specified"],
                 'make_c3d': ["", "Convert trc to c3d file. true if not specified"],
-                'floor_angle': ["", "angle of the floor. 'auto' if not specified"],
+                'floor_angle': ["", "angle of the floor (degrees). 'auto' if not specified"],
                 'xy_origin': ["", "origin of the xy plane. 'auto' if not specified"],
                 'calib_file': ["", "path to calibration file. '' if not specified, eg no calibration file"],
                 'save_calib': ["", "save calibration file. true if not specified"],

Sports2D/process.py

@@ -56,6 +56,7 @@ import sys
 import logging
 import json
 import ast
+import copy
 import shutil
 import os
 from importlib.metadata import version
@@ -642,7 +643,7 @@ def make_trc_with_trc_data(trc_data, trc_path, fps=30):
 
     INPUTS:
     - trc_data: pd.DataFrame. The time and coordinates of the keypoints. 
-                    The column names must be 't', 'kpt1', 'kpt1', 'kpt1', 'kpt2', 'kpt2', 'kpt2', ...
+                    The column names must be 'time', 'kpt1', 'kpt1', 'kpt1', 'kpt2', 'kpt2', 'kpt2', ...
     - trc_path: Path. The path to the TRC file to save
     - fps: float. The framerate of the video
 
@@ -1349,10 +1350,16 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
     trimmed_extrema_percent = config_dict.get('kinematics').get('trimmed_extrema_percent')
     close_to_zero_speed_px = config_dict.get('kinematics').get('close_to_zero_speed_px')
     close_to_zero_speed_m = config_dict.get('kinematics').get('close_to_zero_speed_m')
-    if do_ik:
-        if use_augmentation:
-            from Pose2Sim.markerAugmentation import augment_markers_all
-        from Pose2Sim.kinematics import kinematics_all
+    if do_ik or use_augmentation:
+        try:
+            if use_augmentation:
+                from Pose2Sim.markerAugmentation import augment_markers_all
+            if do_ik:
+                from Pose2Sim.kinematics import kinematics_all
+        except ImportError:
+            logging.error("OpenSim package is not installed. Please install it to use inverse kinematics or marker augmentation features (see 'Full install' section of the documentation).")
+            raise ImportError("OpenSim package is not installed. Please install it to use inverse kinematics or marker augmentation features (see 'Full install' section of the documentation).")
+        
         # Create a Pose2Sim dictionary and fill in missing keys
         recursivedict = lambda: defaultdict(recursivedict)
         Pose2Sim_config_dict = recursivedict()
@@ -1427,7 +1434,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
                         backend=backend, device=device)
             
         except (json.JSONDecodeError, TypeError):
-            logging.warning("\nInvalid mode. Must be 'lightweight', 'balanced', 'performance', or '''{dictionary}''' of parameters within triple quotes. Make sure input_sizes are within square brackets.")
+            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'
     
@@ -1457,6 +1464,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
         keypoints_ids = [node.id for _, _, node in RenderTree(pose_model) if node.id!=None]
         keypoints_names = [node.name for _, _, node in RenderTree(pose_model) if node.id!=None]
         t0 = 0
+        print(keypoints_names, keypoints_ids)
 
         # Set up pose tracker
         try:
@@ -1468,7 +1476,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
         if tracking_mode not in ['deepsort', 'sports2d']:
             logging.warning(f"Tracking mode {tracking_mode} not recognized. Using sports2d method.")
             tracking_mode = 'sports2d'
-        logging.info(f'\nPose tracking set up for "{pose_model_name}" model.')
+        logging.info(f'Pose tracking set up for "{pose_model_name}" model.')
         logging.info(f'Mode: {mode}.\n')
         logging.info(f'Persons are detected every {det_frequency} frames and tracked inbetween. Tracking is done with {tracking_mode}.')
         if tracking_mode == 'deepsort': logging.info(f'Deepsort parameters: {deepsort_params}.')
@@ -1494,7 +1502,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
                 logging.warning(f"Skipping {ang_name} angle computation because at least one of the following keypoints is not provided by the model: {ang_params[0]}.")
 
 
-    # ====================================================
+    #%% ==================================================
     # Process video or webcam feed
     # ====================================================
     logging.info(f"\nProcessing video stream...")
@@ -1528,10 +1536,6 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
             else:
                 frames.append(frame.copy())
 
-                cv2.putText(frame, f"Press 'q' to quit", (cam_width-int(400*fontSize), cam_height-20), cv2.FONT_HERSHEY_SIMPLEX, fontSize+0.2, (255,255,255), thickness+1, cv2.LINE_AA)
-                cv2.putText(frame, f"Press 'q' to quit", (cam_width-int(400*fontSize), cam_height-20), cv2.FONT_HERSHEY_SIMPLEX, fontSize+0.2, (0,0,255), thickness, cv2.LINE_AA)
-
-
             # Retrieve pose or Estimate pose and track people
             if load_trc_px: 
                 if frame_nb >= len(keypoints_all):
@@ -1607,6 +1611,8 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
             # Draw keypoints and skeleton
             if show_realtime_results:
                 img = frame.copy()
+                cv2.putText(img, f"Press 'q' to stop", (cam_width-int(600*fontSize), cam_height-20), cv2.FONT_HERSHEY_SIMPLEX, fontSize+0.2, (255,255,255), thickness+1, cv2.LINE_AA)
+                cv2.putText(img, f"Press 'q' to stop", (cam_width-int(600*fontSize), cam_height-20), cv2.FONT_HERSHEY_SIMPLEX, fontSize+0.2, (0,0,255), thickness, cv2.LINE_AA)
                 img = draw_bounding_box(img, valid_X, valid_Y, colors=colors, fontSize=fontSize, thickness=thickness)
                 img = draw_keypts(img, valid_X, valid_Y, valid_scores, cmap_str='RdYlGn')
                 img = draw_skel(img, valid_X, valid_Y, pose_model)
@@ -1636,7 +1642,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
             cv2.destroyAllWindows()
 
 
-    # ====================================================
+    #%% ==================================================
     # Post-processing: Select persons, Interpolate, filter, and save pose and angles
     # ====================================================
     all_frames_X_homog = make_homogeneous(all_frames_X)
@@ -1651,12 +1657,11 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
     all_frames_angles_homog = make_homogeneous(all_frames_angles)
 
     frame_range = [0,frame_count] if video_file == 'webcam' else frame_range
+    all_frames_time = pd.Series(np.linspace(frame_range[0]/fps, frame_range[1]/fps, frame_count-frame_range[0]), name='time')
     if load_trc_px:
-        all_frames_time = time_col
         selected_persons = [0]
     else:
         # Select persons 
-        all_frames_time = pd.Series(np.linspace(frame_range[0]/fps, frame_range[1]/fps, frame_count-frame_range[0]), name='time')
         nb_detected_persons = all_frames_scores_homog.shape[1]
         if nb_persons_to_detect == 'all':
             nb_persons_to_detect = all_frames_scores_homog.shape[1]
@@ -1687,7 +1692,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
         logging.info(f'Reordered persons: IDs of persons {selected_persons} become {list(range(len(selected_persons)))}.')
     
 
-    # ====================================================
+    #%% ==================================================
     # Post-processing pose
     # ====================================================
     all_frames_X_processed, all_frames_X_flipped_processed, all_frames_Y_processed, all_frames_scores_processed, all_frames_angles_processed = all_frames_X_homog.copy(), all_frames_X_flipped_homog.copy(), all_frames_Y_homog.copy(), all_frames_scores_homog.copy(), all_frames_angles_homog.copy()
@@ -1706,8 +1711,8 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
             if frame_count - frame_range[0] - pose_nan_count <= 10:
                 all_frames_X_processed[:,idx_person,:], all_frames_X_flipped_processed[:,idx_person,:], all_frames_Y_processed[:,idx_person,:] = np.nan, np.nan, np.nan
                 columns=np.array([[c]*3 for c in all_frames_X_person.columns]).flatten()
-                trc_data_i = pd.DataFrame(0, index=all_frames_X_person.index, columns=['t']+list(columns))
-                trc_data_i['t'] = all_frames_time
+                trc_data_i = pd.DataFrame(0, index=all_frames_X_person.index, columns=['time']+list(columns))
+                trc_data_i['time'] = all_frames_time
                 trc_data.append(trc_data_i)
                 trc_data_unfiltered_i = trc_data_i.copy()
                 trc_data_unfiltered.append(trc_data_unfiltered_i)
@@ -1777,7 +1782,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
                 all_frames_X_processed[:,idx_person,:], all_frames_X_flipped_processed[:,idx_person,:], all_frames_Y_processed[:,idx_person,:] = all_frames_X_person_filt, all_frames_X_flipped_person, all_frames_Y_person_filt
                 
 
-        # Convert px to meters
+        #%% Convert px to meters
         trc_data_m = []
         if to_meters and save_pose:
             logging.info('\nConverting pose to meters:')
@@ -1796,17 +1801,17 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
                 toe_speed_below_px_frame = toe_speed_below * px_per_m / fps
                 if floor_angle == 'auto' or xy_origin == 'auto':
                     # estimated from the line formed by the toes when they are on the ground (where speed = 0)
-                    # try:
+                    try:
                         if all(key in trc_data[0] for key in ['LBigToe', 'RBigToe']):
                             floor_angle_estim, xy_origin_estim, _ = compute_floor_line(trc_data[0], keypoint_names=['LBigToe', 'RBigToe'], toe_speed_below=toe_speed_below_px_frame)
                         else:
                             floor_angle_estim, xy_origin_estim, _ = compute_floor_line(trc_data[0], keypoint_names=['LAnkle', 'RAnkle'], toe_speed_below=toe_speed_below_px_frame)
                             xy_origin_estim[0] = xy_origin_estim[0]-0.13
                             logging.warning(f'The RBigToe and LBigToe are missing from your model. Using ankles - 13 cm to compute the floor line.')
-                    # except:
-                    #     floor_angle_estim = 0
-                    #     xy_origin_estim = cam_width/2, cam_height/2
-                    #     logging.warning(f'Could not estimate the floor angle and xy_origin from person {0}. Make sure that the full body is visible. Using floor angle = 0° and xy_origin = [{cam_width/2}, {cam_height/2}] px.')
+                    except:
+                        floor_angle_estim = 0
+                        xy_origin_estim = cam_width/2, cam_height/2
+                        logging.warning(f'Could not estimate the floor angle and xy_origin from person {0}. Make sure that the full body is visible. Using floor angle = 0° and xy_origin = [{cam_width/2}, {cam_height/2}] px.')
                 if not floor_angle == 'auto':
                     floor_angle_estim = floor_angle
                 if xy_origin == 'auto':
@@ -1845,9 +1850,10 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
                     
                     # Convert to meters
                     px_to_m_i = [convert_px_to_meters(trc_data[i][kpt_name], first_person_height, height_px, cx, cy, -floor_angle_estim, visible_side=visible_side_i) for kpt_name in new_keypoints_names]
-                    trc_data_m_i = pd.concat([all_frames_time.rename('t')]+px_to_m_i, axis=1)
+                    trc_data_m_i = pd.concat([all_frames_time.rename('time')]+px_to_m_i, axis=1)
+                    trc_data_m_i = trc_data_m_i.ffill(axis=0).bfill(axis=0)
                     px_to_m_unfiltered_i = [convert_px_to_meters(trc_data_unfiltered[i][kpt_name], first_person_height, height_px, cx, cy, -floor_angle_estim) for kpt_name in new_keypoints_names]
-                    trc_data_unfiltered_m_i = pd.concat([all_frames_time.rename('t')]+px_to_m_unfiltered_i, axis=1)
+                    trc_data_unfiltered_m_i = pd.concat([all_frames_time.rename('time')]+px_to_m_unfiltered_i, axis=1)
 
                     if to_meters and show_plots:
                         pose_plots(trc_data_unfiltered_m_i, trc_data_m_i, i)
@@ -1904,7 +1910,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
 
 
 
-    # ====================================================
+    #%% ==================================================
     # Post-processing angles
     # ====================================================
     if save_angles and calculate_angles:
@@ -1984,11 +1990,11 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
 
                 # Plotting angles before and after interpolation and filtering
                 if show_plots:
-                    all_frames_angles_person.insert(0, 't', all_frames_time)
+                    all_frames_angles_person.insert(0, 'time', all_frames_time)
                     angle_plots(all_frames_angles_person, angle_data, i) # i = current person
 
 
-    # ====================================================
+    #%% ==================================================
     # Save images/video with processed pose and angles
     # ====================================================
     if save_vid or save_img:
@@ -2003,7 +2009,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
         all_frames_angles_processed = all_frames_angles_processed[:,selected_persons,:]
 
         # Reorder keypoints ids
-        pose_model_with_new_ids = pose_model
+        pose_model_with_new_ids = copy.deepcopy(pose_model)
         new_id = 0
         for node in PreOrderIter(pose_model_with_new_ids):
             if node.id!=None:
@@ -2021,7 +2027,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
             img = frame.copy()
             img = draw_bounding_box(img, valid_X, valid_Y, colors=colors, fontSize=fontSize, thickness=thickness)
             img = draw_keypts(img, valid_X, valid_Y, valid_scores, cmap_str='RdYlGn')
-            img = draw_skel(img, valid_X, valid_Y, pose_model)
+            img = draw_skel(img, valid_X, valid_Y, pose_model_with_new_ids)
             if calculate_angles:
                 img = draw_angles(img, valid_X, valid_Y, valid_angles, valid_X_flipped, new_keypoints_ids, new_keypoints_names, angle_names, display_angle_values_on=display_angle_values_on, colors=colors, fontSize=fontSize, thickness=thickness)
 
@@ -2043,7 +2049,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
             logging.info(f"Processed images saved to {img_output_dir.resolve()}.")
 
 
-    # ====================================================
+    #%% ==================================================
     # OpenSim inverse kinematics (and optional marker augmentation)
     # ====================================================
     if do_ik or use_augmentation:
@@ -2064,6 +2070,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
 
             heights_m, masses = [], []
             for i in range(len(trc_data_m)):
+                trc_data_m_i = trc_data_m[i]
                 if do_ik and not use_augmentation:
                     logging.info(f'- Person {i}: Running scaling and inverse kinematics without marker augmentation. Set use_augmentation to True if you need it.') 
                 elif not do_ik and use_augmentation:

{sports2d-0.8.0.dist-info → sports2d-0.8.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sports2d
-Version: 0.8.0
+Version: 0.8.2
 Summary: Compute 2D human pose and angles from a video or a webcam.
 Author-email: David Pagnon <contact@david-pagnon.com>
 License: BSD 3-Clause License
@@ -105,7 +105,7 @@ Dynamic: license-file
 > - Better visualization output 
 > - More flexible, easier to run
 >
-> Run `pip install sports2d -U` to get the latest version.
+> Run `pip install sports2d pose2sim -U` to get the latest version.
 
 ***N.B.:*** As always, I am more than happy to welcome contributions (see [How to contribute](#how-to-contribute-and-to-do-list))!
 <!--User-friendly Colab version released! (and latest issues fixed, too)\
@@ -122,7 +122,7 @@ https://github.com/user-attachments/assets/6a444474-4df1-4134-af0c-e9746fa433ad
 
 `Warning:` Angle estimation is only as good as the pose estimation algorithm, i.e., it is not perfect.\
 `Warning:` Results are acceptable only if the persons move in the 2D plane (sagittal or frontal plane). The persons need to be filmed as parallel as possible to the motion plane.\
-If you need 3D research-grade markerless joint kinematics, consider using several cameras, and constraining angles to a biomechanically accurate model. See **[Pose2Sim](https://github.com/perfanalytics/pose2sim)** for example.
+If you need 3D research-grade markerless joint kinematics, consider using several cameras with **[Pose2Sim](https://github.com/perfanalytics/pose2sim)**.
 
 <!--`Warning:` Google Colab does not follow the European GDPR requirements regarding data privacy. [Install locally](#installation) if this matters.-->
 
@@ -208,7 +208,7 @@ pip install .
    
 - **Install Sports2D with Pose2Sim**:
   ``` cmd
-  pip install sports2d pose2sim
+  pip install sports2d
   ```
 
 
@@ -238,7 +238,6 @@ The Demo video is voluntarily challenging to demonstrate the robustness of the p
 - One person walking in the sagittal plane
 - One person doing jumping jacks in the frontal plane. This person then performs a flip while being backlit, both of which are challenging for the pose detection algorithm
 - One tiny person flickering in the background who needs to be ignored
-- The first person is starting high and ending low on the image, which messes up the automatic floor angle calculation. You can set it up manually with the parameter `--floor_angle 0`
 
 <br>
 
@@ -509,7 +508,7 @@ sports2d --help
 'device': ["", "Device for pose estimatino can be 'auto', 'openvino', 'onnxruntime', 'opencv'"],
 'to_meters': ["M", "convert pixels to meters. true if not specified"],
 'make_c3d': ["", "Convert trc to c3d file. true if not specified"],
-'floor_angle': ["", "angle of the floor. 'auto' if not specified"],
+'floor_angle': ["", "angle of the floor (degrees). 'auto' if not specified"],
 'xy_origin': ["", "origin of the xy plane. 'auto' if not specified"],
 'calib_file': ["", "path to calibration file. '' if not specified, eg no calibration file"],
 'save_calib': ["", "save calibration file. true if not specified"],

sports2d-0.8.2.dist-info/RECORD

@@ -0,0 +1,15 @@
+Sports2D/Sports2D.py,sha256=KWrvWGq49UXta9VJisflyQA-4n7mdu-Uq4GsmDPkaRc,30470
+Sports2D/__init__.py,sha256=BuUkPEdItxlkeqz4dmoiPwZLkgAfABJK3KWQ1ujTGwE,153
+Sports2D/process.py,sha256=AtD17Q68Qh688BQKqgnmBWhlNgcl_Iz1igN5q-zxoMs,107297
+Sports2D/Demo/Config_demo.toml,sha256=GhV-VotYlpYMCu7rHY-AKdWVAT4f61z0oL9-MUBRsOc,13828
+Sports2D/Demo/demo.mp4,sha256=2aZkFxhWR7ESMEtXCT8MGA83p2jmoU2sp1ylQfO3gDk,3968304
+Sports2D/Utilities/__init__.py,sha256=BuUkPEdItxlkeqz4dmoiPwZLkgAfABJK3KWQ1ujTGwE,153
+Sports2D/Utilities/common.py,sha256=idMRmesFv5BPX-5g3z5dOVa7SpS_8tNgijvGrOZlR-k,11185
+Sports2D/Utilities/filter.py,sha256=rfZcqofjllKI_5ovZTKEAmyjOZpB_PzbAJ0P874T8Ak,4973
+Sports2D/Utilities/tests.py,sha256=XnPNK63AZ_xlJBmFmPJtOMrzssBXIPXFzYd73CPzchI,4740
+sports2d-0.8.2.dist-info/licenses/LICENSE,sha256=f4qe3nE0Y7ltJho5w-xAR0jI5PUox5Xl-MsYiY7ZRM8,1521
+sports2d-0.8.2.dist-info/METADATA,sha256=KqPyLRBEtEVB_CK7OrZQBMebuHFaT2gbGXqx745TgWU,39516
+sports2d-0.8.2.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+sports2d-0.8.2.dist-info/entry_points.txt,sha256=V8dFDIXatz9VvoGgoHzb2wE71C9-f85K6_OjnEQlxww,108
+sports2d-0.8.2.dist-info/top_level.txt,sha256=DoURf9UDB8lQ_9lMUPQMQqhXCvWPFFjJco9NzPlHJ6I,9
+sports2d-0.8.2.dist-info/RECORD,,

sports2d-0.8.0.dist-info/RECORD

@@ -1,15 +0,0 @@
-Sports2D/Sports2D.py,sha256=0BQ5ainW3EOxElwiXHGywDKVlnHktTIz3EfEH3JhJR0,30460
-Sports2D/__init__.py,sha256=BuUkPEdItxlkeqz4dmoiPwZLkgAfABJK3KWQ1ujTGwE,153
-Sports2D/process.py,sha256=ymiWlS_VakIUy99pEle2mbuZKcQV2KE5AaauAy95Xuo,106637
-Sports2D/Demo/Config_demo.toml,sha256=STcdCLpi4-94RpkP6JjvRUxce_QRQnTzjAny71b6ejI,13829
-Sports2D/Demo/demo.mp4,sha256=2aZkFxhWR7ESMEtXCT8MGA83p2jmoU2sp1ylQfO3gDk,3968304
-Sports2D/Utilities/__init__.py,sha256=BuUkPEdItxlkeqz4dmoiPwZLkgAfABJK3KWQ1ujTGwE,153
-Sports2D/Utilities/common.py,sha256=idMRmesFv5BPX-5g3z5dOVa7SpS_8tNgijvGrOZlR-k,11185
-Sports2D/Utilities/filter.py,sha256=rfZcqofjllKI_5ovZTKEAmyjOZpB_PzbAJ0P874T8Ak,4973
-Sports2D/Utilities/tests.py,sha256=XnPNK63AZ_xlJBmFmPJtOMrzssBXIPXFzYd73CPzchI,4740
-sports2d-0.8.0.dist-info/licenses/LICENSE,sha256=f4qe3nE0Y7ltJho5w-xAR0jI5PUox5Xl-MsYiY7ZRM8,1521
-sports2d-0.8.0.dist-info/METADATA,sha256=QrX8rCAoE8-aHew7HeY5eGsvRBrez7AVVWQBfdCoYyc,39763
-sports2d-0.8.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-sports2d-0.8.0.dist-info/entry_points.txt,sha256=V8dFDIXatz9VvoGgoHzb2wE71C9-f85K6_OjnEQlxww,108
-sports2d-0.8.0.dist-info/top_level.txt,sha256=DoURf9UDB8lQ_9lMUPQMQqhXCvWPFFjJco9NzPlHJ6I,9
-sports2d-0.8.0.dist-info/RECORD,,