opensportslib 0.3.0.dev8__tar.gz → 0.3.0.dev10__tar.gz

{opensportslib-0.3.0.dev8/opensportslib.egg-info → opensportslib-0.3.0.dev10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opensportslib
-Version: 0.3.0.dev8
+Version: 0.3.0.dev10
 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: >=3.12
@@ -54,6 +54,7 @@ OpenSportsLib is designed for **researchers, ML engineers, and sports analytics
 - Unified workflow for training and inference
 - Modular design for adding new tasks, datasets, and models
 - Config driven experiments for reproducibility
+- Optional SpoTTA test-time adaptation for E2ESpot inference
 - Support for multiple modalities and sports workflows
 - Research friendly while still usable in applied settings
 
@@ -211,7 +212,10 @@ Minimal localization sample:
 ```
 
 Relative paths in `inputs[].path` are resolved from the split media root in the
-YAML config, for example `DATA.common.splits.train.source_path`. See the full
+YAML config, for example `DATA.common.splits.train.source_path`. Localization
+records may also declare half-open physical-video ranges in
+`metadata.intervals`; the OpenCV loader treats them as ordered logical videos
+and evaluates only segments marked `verified`. See the full
 [OSL JSON format guide](docs/data/osl-json-format.md) for field definitions,
 multi-modal examples, prediction payloads, and conversion notes.
 

{opensportslib-0.3.0.dev8 → opensportslib-0.3.0.dev10}/README.md

@@ -18,6 +18,7 @@ OpenSportsLib is designed for **researchers, ML engineers, and sports analytics
 - Unified workflow for training and inference
 - Modular design for adding new tasks, datasets, and models
 - Config driven experiments for reproducibility
+- Optional SpoTTA test-time adaptation for E2ESpot inference
 - Support for multiple modalities and sports workflows
 - Research friendly while still usable in applied settings
 
@@ -175,7 +176,10 @@ Minimal localization sample:
 ```
 
 Relative paths in `inputs[].path` are resolved from the split media root in the
-YAML config, for example `DATA.common.splits.train.source_path`. See the full
+YAML config, for example `DATA.common.splits.train.source_path`. Localization
+records may also declare half-open physical-video ranges in
+`metadata.intervals`; the OpenCV loader treats them as ordered logical videos
+and evaluates only segments marked `verified`. See the full
 [OSL JSON format guide](docs/data/osl-json-format.md) for field definitions,
 multi-modal examples, prediction payloads, and conversion notes.
 

opensportslib-0.3.0.dev10/opensportslib/adaptation/__init__.py

@@ -0,0 +1,5 @@
+"""Test-time adaptation tools for OpenSportsLib models."""
+
+from .spotta import SpoTTA, SpoTTAConfig
+
+__all__ = ["SpoTTA", "SpoTTAConfig"]