opensportslib 0.0.1.dev2__py3-none-any.whl

opensportslib-0.0.1.dev2.dist-info/METADATA

@@ -0,0 +1,566 @@
+Metadata-Version: 2.4
+Name: opensportslib
+Version: 0.0.1.dev2
+Summary: OpenSportsLib is the professional library, designed for advanced video understanding in sports. It provides state-of-the-art tools for action recognition, spotting, retrieval, and captioning, making it ideal for researchers, analysts, and developers working with sports video data.
+Author: Jeet Vora
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: LICENSE-COMMERCIAL
+Requires-Dist: SoccerNet
+Requires-Dist: av
+Requires-Dist: decord; platform_system != "Darwin" and platform_machine != "arm64"
+Requires-Dist: evaluate
+Requires-Dist: scikit-learn
+Requires-Dist: torch
+Requires-Dist: torchvision
+Requires-Dist: transformers==4.57.3
+Requires-Dist: tokenizers==0.22.1
+Requires-Dist: accelerate
+Requires-Dist: wandb
+Requires-Dist: opencv-python
+Requires-Dist: omegaconf
+Requires-Dist: timm
+Provides-Extra: localization
+Requires-Dist: nvidia-dali-cuda120; extra == "localization"
+Requires-Dist: cupy-cuda12x; extra == "localization"
+Requires-Dist: tabulate; extra == "localization"
+Provides-Extra: tracking
+Requires-Dist: torch-geometric; extra == "tracking"
+Dynamic: license-file
+
+# OpenSportsLib
+OpenSportsLib is the professional library, designed for advanced video understanding in soccer. It provides state-of-the-art tools for action recognition, spotting, retrieval, and captioning, making it ideal for researchers, analysts, and developers working with soccer video data.
+
+## Development
+```bash
+### Clone the github repo
+git clone https://github.com/OpenSportsLab/opensportslib.git 
+
+### Requirements and installation ###
+conda create -n osl python=3.12 pip
+conda activate osl
+pip install -e .
+
+or 
+
+pip install -e .[localization]
+or 
+pip install -e .[tracking]
+
+### git branch and merge rules ###
+1. Check and verify current branch is "dev" - git status
+
+2. Create new branch from source "dev" - 
+git pull
+git checkout -b <new_feature/fix/bug>
+
+3. Raise PR request to merge your branch <new_feature/fix/bug> to "dev" branch 
+```
+
+## Installation
+
+```bash
+conda create -n osl python=3.12 pip
+conda activate osl
+pip install --pre opensportslib
+```
+
+## 🤝 Contributing & Developer Guide
+
+We welcome contributions to OpenSportsLib.
+
+- 📘 **Contributor Guide:** [CONTRIBUTING.md](opensportslib/docs/CONTRIBUTING.md)  
+- 🛠 **Developer Guide:** [DEVELOPERS.md](opensportslib/docs/DEVELOPERS.md)
+
+These documents explain:
+- How to add models and datasets  
+- Coding standards  
+- Training pipeline structure  
+- How to run and test the framework  
+
+
+## Configuration Sample (.yaml) file
+1. Classification 
+```bash
+TASK: classification
+
+DATA:
+  dataset_name: mvfouls
+  data_dir: /home/vorajv/opensportslib/SoccerNet/mvfouls
+  data_modality: video
+  view_type: multi  # multi or single
+  num_classes: 8 # mvfoul
+  train: 
+    type: annotations_train.json
+    video_path: ${DATA.data_dir}/train
+    path: ${DATA.train.video_path}/annotations-train.json
+    dataloader:
+      batch_size: 8
+      shuffle: true
+      num_workers: 4
+      pin_memory: true
+  valid:
+    type: annotations_valid.json
+    video_path: ${DATA.data_dir}/valid
+    path: ${DATA.valid.video_path}/annotations-valid.json
+    dataloader:
+      batch_size: 1
+      num_workers: 1
+      shuffle: false
+  test:
+    type: annotations_test.json
+    video_path: ${DATA.data_dir}/test
+    path: ${DATA.test.video_path}/annotations-test.json
+    dataloader:
+      batch_size: 1
+      num_workers: 1
+      shuffle: false
+  num_frames: 16               # 8 before + 8 after the foul
+  input_fps: 25                # Original FPS of video
+  target_fps: 17               # Temporal downsampling to 1s clip (approx)
+  start_frame: 63            # Start frame of clip relative to foul frame
+  end_frame: 87              # End frame of clip relative to foul frame
+  frame_size: [224, 224]       # Spatial resolution (HxW)
+  augmentations:
+    random_affine: true
+    translate: [0.1, 0.1]        
+    affine_scale: [0.9, 1.0]     
+    random_perspective: true
+    distortion_scale: 0.3        
+    perspective_prob: 0.5
+    random_rotation: true
+    rotation_degrees: 5          
+    color_jitter: true
+    jitter_params: [0.2, 0.2, 0.2, 0.1]   # brightness, contrast, saturation, hue
+    random_horizontal_flip: true
+    flip_prob: 0.5
+    random_crop: false
+
+MODEL:
+  type: custom # huggingface, custom 
+  backbone: 
+    type: mvit_v2_s # video_mae, r3d_18, mc3_18, r2plus1d_18, s3d, mvit_v2_s
+  neck:
+    type: MV_Aggregate
+    agr_type: max   # max, mean, attention
+  head: 
+    type: MV_LinearLayer
+  pretrained_model: mvit_v2_s # MCG-NJU/videomae-base, OpenGVLab/VideoMAEv2-Base, r3d_18, mc3_18, r2plus1d_18, s3d, mvit_v2_s
+  unfreeze_head: true  # for videomae backbone
+  unfreeze_last_n_layers: 3 # for videomae backbone
+    
+
+TRAIN:
+  monitor: balanced_accuracy # balanced_accuracy, loss
+  mode: max # max or min
+  enabled: true
+  use_weighted_sampler: false
+  use_weighted_loss: true
+  epochs: 20 #20
+  save_dir: ./checkpoints
+  log_interval: 10
+  save_every: 2 #5
+
+  criterion:
+    type: CrossEntropyLoss
+
+  optimizer:
+    type: AdamW
+    lr: 0.0001  #0.001
+    backbone_lr: 0.00005
+    head_lr: 0.001
+    betas: [0.9, 0.999]
+    eps: 0.0000001
+    weight_decay: 0.001 #0.01 - videomae, 0.001 - others
+    amsgrad: false
+  
+  scheduler:
+    type: StepLR
+    step_size: 3
+    gamma: 0.1
+
+SYSTEM:
+  log_dir: ./logs
+  use_seed: false
+  seed: 42
+  GPU: 4
+  device: cuda   # auto | cuda | cpu
+  gpu_id: 0
+
+```
+
+2. Classification (Tracking)
+```bash
+TASK: classification
+
+DATA:
+  dataset_name: sngar
+  data_modality: tracking_parquet
+  data_dir: /home/karkid/opensportslib/sngar-tracking
+  preload_data: false
+  train: 
+    type: annotations_train.json
+    video_path: ${DATA.data_dir}/train
+    path: ${DATA.train.video_path}/train.json
+    dataloader:
+      batch_size: 32
+      shuffle: true
+      num_workers: 8
+      pin_memory: true
+  valid:
+    type: annotations_valid.json
+    video_path: ${DATA.data_dir}/valid
+    path: ${DATA.valid.video_path}/valid.json
+    dataloader:
+      batch_size: 32
+      num_workers: 8
+      shuffle: false
+  test:
+    type: annotations_test.json
+    video_path: ${DATA.data_dir}/test
+    path: ${DATA.test.video_path}/test.json
+    dataloader:
+      batch_size: 32
+      num_workers: 8
+      shuffle: false
+  num_frames: 16
+  frame_interval: 9
+  augmentations:
+    vertical_flip: true
+    horizontal_flip: true
+    team_flip: true
+  normalize: true
+  num_objects: 23
+  feature_dim: 8
+  pitch_half_length: 85.0
+  pitch_half_width: 50.0
+  max_displacement: 110.0
+  max_ball_height: 30.0
+
+MODEL:
+  type: custom
+  backbone:
+    type: graph_conv
+    encoder: graphconv
+    hidden_dim: 64
+    num_layers: 20
+    dropout: 0.1
+  neck:
+    type: TemporalAggregation
+    agr_type: maxpool
+    hidden_dim: 64
+    dropout: 0.1
+  head:
+    type: TrackingClassifier
+    hidden_dim: 64
+    dropout: 0.1
+    num_classes: 10
+  edge: positional
+  k: 8
+  r: 15.0
+
+TRAIN:
+  monitor: loss # balanced_accuracy, loss
+  mode: min # max or min
+  enabled: true
+  use_weighted_sampler: true
+  use_weighted_loss: false
+  samples_per_class: 4000
+  epochs: 10
+  patience: 10
+  save_every: 20
+  detailed_results: true
+
+  optimizer:
+    type: Adam
+    lr: 0.001
+
+  scheduler:
+    type: ReduceLROnPlateau
+    mode: ${TRAIN.mode}
+    patience: 10
+    factor: 0.1
+    min_lr: 1e-8
+  
+  criterion:
+    type: CrossEntropyLoss
+
+  save_dir: ./checkpoints_tracking
+
+SYSTEM:
+ log_dir: ./logs
+ use_seed: true
+ seed: 42
+ GPU: 4
+ device: cuda   # auto | cuda | cpu
+ gpu_id: 0
+```
+
+3. Localization
+```bash
+TASK: localization
+
+dali: True
+
+DATA:
+  dataset_name: SoccerNet
+  data_dir: /home/vorajv/opensportslib/SoccerNet/annotations/
+  classes:
+    - PASS
+    - DRIVE
+    - HEADER
+    - HIGH PASS
+    - OUT
+    - CROSS
+    - THROW IN
+    - SHOT
+    - BALL PLAYER BLOCK
+    - PLAYER SUCCESSFUL TACKLE
+    - FREE KICK
+    - GOAL
+    
+  epoch_num_frames: 500000
+  mixup: true
+  modality: rgb
+  crop_dim: -1
+  dilate_len: 0        # Dilate ground truth labels
+  clip_len: 100
+  input_fps: 25
+  extract_fps: 2
+  imagenet_mean: [0.485, 0.456, 0.406]
+  imagenet_std: [0.229, 0.224, 0.225]
+  target_height: 224
+  target_width: 398
+
+  train:
+    type: VideoGameWithDali
+    classes: ${DATA.classes}
+    output_map: [data, label]
+    video_path: ${DATA.data_dir}/train/
+    path: ${DATA.train.video_path}/annotations-2024-224p-train.json
+    dataloader:
+      batch_size: 8
+      shuffle: true
+      num_workers: 4
+      pin_memory: true
+
+  valid:
+    type: VideoGameWithDali
+    classes: ${DATA.classes}
+    output_map: [data, label]
+    video_path: ${DATA.data_dir}/valid/
+    path: ${DATA.valid.video_path}/annotations-2024-224p-valid.json
+    dataloader:
+      batch_size: 8
+      shuffle: true
+
+  valid_data_frames:
+    type: VideoGameWithDaliVideo
+    classes: ${DATA.classes}
+    output_map: [data, label]
+    video_path: ${DATA.valid.video_path}
+    path: ${DATA.valid.path}
+    overlap_len: 0
+    dataloader:
+      batch_size: 4
+      shuffle: false
+
+  test:
+    type: VideoGameWithDaliVideo
+    classes: ${DATA.classes}
+    output_map: [data, label]
+    video_path: ${DATA.data_dir}/test/
+    path: ${DATA.test.video_path}/annotations-2024-224p-test.json
+    results: results_spotting_test
+    nms_window: 2 
+    metric: tight
+    overlap_len: 50
+    dataloader:
+      batch_size: 4
+      shuffle: false
+
+  challenge:
+    type: VideoGameWithDaliVideo
+    overlap_len: 50
+    output_map: [data, label]
+    path: ${DATA.data_dir}/challenge/annotations.json
+    dataloader:
+      batch_size: 4
+      shuffle: false
+
+MODEL:
+    type: E2E
+    runner:
+      type: runner_e2e
+    backbone:
+      type: rny008_gsm
+    head:
+      type: gru
+    multi_gpu: true
+    load_weights: null
+    save_dir: ./checkpoints
+    work_dir: ${MODEL.save_dir}
+
+TRAIN:
+  type: trainer_e2e
+  num_epochs: 10
+  acc_grad_iter: 1
+  base_num_valid_epochs: 30
+  start_valid_epoch: 4
+  valid_map_every: 1
+  criterion_valid: map
+
+  criterion:
+    type: CrossEntropyLoss
+
+  optimizer:
+    type: AdamWithScaler
+    lr: 0.01
+
+  scheduler:
+    type: ChainedSchedulerE2E
+    acc_grad_iter: 1
+    num_epochs: ${TRAIN.num_epochs}
+    warm_up_epochs: 3
+
+SYSTEM:
+  log_dir: ./logs
+  seed: 42
+  GPU: 4         # number of gpus to use
+  device: cuda   # auto | cuda | cpu
+  gpu_id: 0      # device id for single gpu training
+```
+
+## Annotations (train/valid/test) (.json) format
+Download annotations file from below links
+1. Classification
+mvfouls = https://huggingface.co/datasets/OpenSportsLab/opensportslib-classification-vars/tree/mvfouls
+svfouls = https://huggingface.co/datasets/OpenSportsLab/opensportslib-classification-vars/tree/svfouls
+
+2. Localization
+ball-action-spotting = https://huggingface.co/datasets/OpenSportsLab/opensportslib-localization-snbas/tree/main
+
+# Download weights from HF
+1. classification (mvit)
+(MVFoul classification) https://huggingface.co/jeetv/snpro-classification-mvit/tree/main
+
+2. Localization (E2E spot)
+- (2023 Ball Action Spotting - 2 classes) https://huggingface.co/jeetv/snpro-snbas-2023/tree/main
+- (2024 Ball Action Spotting - 12 classes) https://huggingface.co/jeetv/snpro-snbas-2024/tree/main
+
+
+Usage:
+```bash
+### Load weights from HF ###
+
+#### For Classification ####
+myModel.infer(
+    test_set="/path/to/annotations.json",
+    pretrained="jeetv/snpro-classification-mvit", # classification (MViT)
+)
+
+#### For Localization ####
+pretrained = "jeetv/snpro-snbas-2023" # SNBAS - 2 classes (E2E spot)
+pretrained = "jeetv/snpro-snbas-2024" # SNBAS - 12 classes (E2E spot)
+```
+
+## Train on SINGLE GPU
+```bash
+from opensportslib import model
+import wandb
+
+# Initialize model with config
+myModel = model.classification(
+    config="/path/to/classification.yaml"
+)
+
+## Localization ##
+# myModel = model.localization(
+#     config="/path/to/classification.yaml"
+# )
+
+# Train on your dataset
+myModel.train(
+    train_set="/path/to/train_annotations.json",
+    valid_set="/path/to/valid_annotations.json",
+    pretrained=/path/to/  # or path to pretrained checkpoint
+)
+```
+
+## Train on Multiple GPU (DDP)
+```bash
+from opensportslib import model
+
+def main():
+    myModel = model.classification(
+        config="/path/to/classification.yaml",
+        data_dir="/path/to/dataset_root"
+    )
+
+    ## Localization ##
+    # myModel = model.localization(
+    #     config="/path/to/classification.yaml"
+    # )
+
+    myModel.train(
+        train_set="/path/to/train_annotations.json",
+        valid_set="/path/to/valid_annotations.json",
+        pretrained="/path/to/pretrained.pt",  # optional
+        use_ddp=True,  # IMPORTANT
+    )
+
+if __name__ == "__main__":
+    main()
+```
+
+
+## Test / Inference on SINGLE GPU
+```bash
+from opensportslib import model
+
+# Load trained model
+myModel = model.classification(
+    config="/path/to/classification.yaml"
+)
+
+## Localization ##
+# myModel = model.localization(
+#     config="/path/to/classification.yaml"
+# )
+
+# Run inference on test set
+metrics = myModel.infer(
+    test_set="/path/to/test_annotations.json",
+    pretrained="/path/to/checkpoints/final_model",
+    predictions="/path/to/predictions.json"
+)
+```
+
+## Test / Inference on Multiple GPU (DDP)
+```bash
+from opensportslib import model
+
+def main():
+    myModel = model.classification(
+        config="/path/to/classification.yaml",
+        data_dir="/path/to/dataset_root"
+    )
+
+    ## Localization ##
+    # myModel = model.localization(
+    #     config="/path/to/classification.yaml"
+    # )
+
+    metrics = myModel.infer(
+        test_set="/path/to/test_annotations.json",
+        pretrained="/path/to/checkpoints/best.pt",
+        predictions="/path/to/predictions.json",
+        use_ddp=True,   # optional (usually not needed)
+    )
+
+    print(metrics)
+
+if __name__ == "__main__":
+    main()
+```

opensportslib-0.0.1.dev2.dist-info/RECORD

@@ -0,0 +1,73 @@
+opensportslib/__init__.py,sha256=TfWJS-l96bTYJGvqvXWEEhs7RqjLGgwLpJEofsfWnZQ,621
+opensportslib/apis/__init__.py,sha256=3pfQ45yO62fa8EUzczw8EYzOTVrxK15ZsH22AFAvdGU,759
+opensportslib/apis/classification.py,sha256=-VrP9VusqgoNNCClJhR6zYJm7ML1cGIdnaFQ6gbKy6w,12986
+opensportslib/apis/localization.py,sha256=eyuSxmxLcvgt4kpezpsQ-FSlBwIuEygAkBXmmumw2oY,9878
+opensportslib/config/classification.yaml,sha256=NWJhTjFHpVDSqZuSOBlHIUVswCkIsJ-T3DbPkpffHSE,2849
+opensportslib/config/classification_tracking.yaml,sha256=CRZVGZ7Lk0JCYjHsdclDeyNECe49Q0NQVluCHRPQD6A,2050
+opensportslib/config/localization.yaml,sha256=p0n3buxCHe9uTbQNJg55CG2ckO40PTnhDzb2p3PlEZQ,2769
+opensportslib/config/sngar_frames.yaml,sha256=lSqtWAZcJ0asp4BVJebXgZ9a0miV09fPOksDeKLDN9w,2370
+opensportslib/config/graph_tracking_classification/avgpool.yaml,sha256=s38HwcGt-2SyUgZm6giGcmtsSfm3-gOg1p3mNzhfoqM,1571
+opensportslib/config/graph_tracking_classification/gin.yaml,sha256=_ODn7TBDECv2CUNEuKmf2OyNfd7MdyjlRnYUXB6TIjE,1571
+opensportslib/config/graph_tracking_classification/graphconv.yaml,sha256=AvK1_hsl-p3xPgUDMvIHVnGdPK0d4md2I09rF2yszqk,1577
+opensportslib/config/graph_tracking_classification/graphsage.yaml,sha256=XMADg6z2dECVuWx94V2tbojiVrNG-SXiMTNQ61LQwYY,1576
+opensportslib/config/graph_tracking_classification/maxpool.yaml,sha256=_ODn7TBDECv2CUNEuKmf2OyNfd7MdyjlRnYUXB6TIjE,1571
+opensportslib/config/graph_tracking_classification/noedges.yaml,sha256=DNwBjzIQQjXjSmeA-Ragi9Gw_WEIzUJE4hGadzLRXQM,1565
+opensportslib/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+opensportslib/core/loss/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+opensportslib/core/loss/builder.py,sha256=DpiVHOH-7hD32wSfjVkXjb0mjQyMx58zy8RXZPjG1Og,1250
+opensportslib/core/loss/calf.py,sha256=VmuN7hRMY1Q5fKjTceyQt7IMJacuYEbU6RJpbtMgJJc,7960
+opensportslib/core/loss/ce.py,sha256=k7CwAHWRjouE_wKmaVyHkbm5i8L9FNb7TNIZXF7N4G4,632
+opensportslib/core/loss/combine.py,sha256=9B03jOPC2LgKLW03ljys_d9eXm9MIyi-AWTCxbMWMPI,1193
+opensportslib/core/loss/nll.py,sha256=VYmSXR9iWcBYNMpeT_UH6jNM9FVdm-QiU5Pv7LmbTpE,607
+opensportslib/core/optimizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+opensportslib/core/optimizer/builder.py,sha256=SnESpU7BcouAnOdfZo7wxgoFsaJZ4rEEe_cLaIP3a80,1167
+opensportslib/core/sampler/weighted_sampler.py,sha256=3WVIP1GS5ksw0bwIY3EtvZ0-dUxqksWy9QShidTnzL8,3963
+opensportslib/core/scheduler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+opensportslib/core/scheduler/builder.py,sha256=saSQidzRZhKoplwGAAPruQfr8473gvz5jitOkzhPPNc,3280
+opensportslib/core/trainer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+opensportslib/core/trainer/classification_trainer.py,sha256=1NNWgXtHbxOpLvvNLHXgLZEirXwwUj7U2FwKwkynnYI,41303
+opensportslib/core/trainer/localization_trainer.py,sha256=RRkMt7tKiZYqyX4FtC24piILZYIHgZQSF_BWonWkm50,40341
+opensportslib/core/utils/checkpoint.py,sha256=MOSdN8wjLOA0dyItYMeAehqKLpDdzbE31mYNFDMWVok,8068
+opensportslib/core/utils/config.py,sha256=jLyVu01b-BKTMYOAH7sSH_aLisLf43Vx3vrMu9Zl2gg,5503
+opensportslib/core/utils/data.py,sha256=xmXfYCrfsU0TPVYPmzzEBtXFc6zgtfT1BoKMfGkXMkw,3142
+opensportslib/core/utils/ddp.py,sha256=7NJuHnwB5f45d6OXgRSnrB81CNkomxIplEBn0MSlxgU,2241
+opensportslib/core/utils/default_args.py,sha256=yTpZCGlsxT2Bq_q651mSliFNHd9kH-HszQMlX7kacII,3423
+opensportslib/core/utils/load_annotations.py,sha256=fOFvHNlmmTnEgmPpOHt_FJ0gp3EXWW_HStuYiFhW110,16607
+opensportslib/core/utils/seed.py,sha256=0MXbMWQw2jaEfUf5QcWN5eXj6V2RtqrbwvWwbjxBXKY,788
+opensportslib/core/utils/video_processing.py,sha256=JYQuJpf7vnpCdkqJ5H3fK1Gpi4sTA3LYg2TnOnqKu9Q,13777
+opensportslib/core/utils/wandb.py,sha256=oglwPyN2F__GIPSIbPb8nf7WHytFv0WbLOkaKBfkXtY,2829
+opensportslib/datasets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+opensportslib/datasets/builder.py,sha256=_vXzVCaeoup5OPo4T96q6dyx24H4vJ6Of3mH1oEyYrI,1805
+opensportslib/datasets/classification_dataset.py,sha256=EyxFGtGvZ9o8lKG2gy47wNsa12i73pSKvqyTPGR0fB8,20213
+opensportslib/datasets/localization_dataset.py,sha256=VUdn8EYSymuFhpaDH0btUlCVPsxNleFxMos1vs2OGp0,32317
+opensportslib/datasets/utils/__init__.py,sha256=43aJF50ghFaoyioNwLoBawqjSDslL1CKPcs893VD52Y,240
+opensportslib/datasets/utils/tracking.py,sha256=Xiln9ZihREJi6boZJsXIo1H0FcBTtzu93ol9jAJ_ZXk,20864
+opensportslib/metrics/classification_metric.py,sha256=FaM2Dcweo0ykrROWObKMmY-cGNkTIVwSiao4DnuQ964,6823
+opensportslib/metrics/localization_metric.py,sha256=srcztV5qH_E9RYDG1shpoC0Ua-6oi-wO1tQlma9v98I,51607
+opensportslib/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+opensportslib/models/builder.py,sha256=5i_An-kP7UhdGaSFAmx2UAZ_r7R7GrrhbfTqIcBy8rU,1903
+opensportslib/models/backbones/builder.py,sha256=xzPjsl20cRbQWLVjvZtFt62MFIzNiNP4Jw-m1cmQYk4,21548
+opensportslib/models/base/e2e.py,sha256=zaSstTdaSHDtUkACgY5SHb4TzliCyyolOF_cB7bLAAk,9389
+opensportslib/models/base/tracking.py,sha256=GacGqMpJlqVWNnfgAVv26D_muONZKnFN1LC7ukPhEZ8,2230
+opensportslib/models/base/vars.py,sha256=2yuUKJPQxbmWox5wrtXcfEJmV7IlUs-FwyIJqqTfo4E,1004
+opensportslib/models/base/video.py,sha256=k1vAeG5OoC-gAqE1Wk05xZ1EbsIo12cKrBhiW-UC7qE,4387
+opensportslib/models/base/video_mae.py,sha256=5Er4x7FnY4H6Q7nVnpgS8YH1C8J6j_-k6lekGCR_NgE,2012
+opensportslib/models/heads/builder.py,sha256=rCPCfNx-G1AQYoEG8aSaQTQzmMVmxTERj7fwQbi2kU8,10005
+opensportslib/models/neck/builder.py,sha256=2hGvv9MsPq_nfnfzW2VbNrNwWcA4_B5y9Dffkx75LWQ,7505
+opensportslib/models/utils/common.py,sha256=NdYcqjHjHEhiv_on1pIA8mC8Mup8Z2k4DyEfJ4E5YQ8,6062
+opensportslib/models/utils/litebase.py,sha256=qXEJQUIUsmSJnlm8QeWwJ2BNzXcR9Rw25MI1B9LiSzg,1796
+opensportslib/models/utils/modules.py,sha256=BhYJgTnCBiQZMR-h6-e49tEHj0o59iLCb8KX4uu0oNw,4003
+opensportslib/models/utils/shift.py,sha256=FaLIvbqjfEUnZb1VMxljjxXd_IfkweseoBTmANL7B84,5441
+opensportslib/models/utils/utils.py,sha256=Hgy-ZOz5O6txoGaX8Op4Gcmyjq1S6gzM0lo7hyngL14,9898
+opensportslib/models/utils/impl/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+opensportslib/models/utils/impl/asformer.py,sha256=WaUxiE76mnpygUVoQocZ6URuohdBEPp1xfx94UYi_kM,17276
+opensportslib/models/utils/impl/calf.py,sha256=L_BBthf4EGGhCWZnRKjKAUUs2cqzVFnBrNMzIoAi-NY,2023
+opensportslib/models/utils/impl/gsm.py,sha256=H-FotqzxPk3IKZnYE76VClQi8F2OESdrGQKKMX2Jio8,5259
+opensportslib/models/utils/impl/gtad.py,sha256=QXae-tZj1Leyx501OYQuBKntHW7Rf0ggxVomxtV7Si4,16928
+opensportslib/models/utils/impl/tsm.py,sha256=URU1PB48jVvpeokCT3MNX8xUo7bi2jiidt3BRzIhVSY,5180
+opensportslib-0.0.1.dev2.dist-info/licenses/LICENSE,sha256=TfPDBt3ar0uv_f9cqCDMZ5rIzW3CY8anRRd4PkL6ejs,34522
+opensportslib-0.0.1.dev2.dist-info/licenses/LICENSE-COMMERCIAL,sha256=ECuFgJRmrIA9-urtAvmdBQg95DMVXjQry_quLxlphrg,161
+opensportslib-0.0.1.dev2.dist-info/METADATA,sha256=7oiATjjL5iiSeuUhx9_-90A9HOecg-_baqWveOoS5pM,13761
+opensportslib-0.0.1.dev2.dist-info/WHEEL,sha256=YCfwYGOYMi5Jhw2fU4yNgwErybb2IX5PEwBKV4ZbdBo,91
+opensportslib-0.0.1.dev2.dist-info/top_level.txt,sha256=XYrhCgrArYzt8sPlO6RTWZFaeLySOkT8GqHeS0xt0CY,14
+opensportslib-0.0.1.dev2.dist-info/RECORD,,

opensportslib-0.0.1.dev2.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+