Add creation time to model config, and docs improvements

docs/index.rst

@@ -5,6 +5,24 @@ Lightning Pose Homepage
 
 .. image:: images/LightningPose_horizontal_light.png
 
+.. admonition:: 📢 Official Release: Lightning Pose App 2.0
+
+   A new modern UI is available for multi-camera single-animal pose estimation,
+   featuring end-to-end support for labeling, model management, and viewing predictions.
+
+   Since the initial release in late Jan 2026. Over 40 researchers from 8 countries have installed and run the app.
+
+   * **Get started:**
+     Check out the :doc:`Create your first project <source/create_first_project>` tutorial and
+     :doc:`installation guide <source/installation_guide>`.
+
+   * **See what's new:**
+     Check out the `release notes <https://github.com/paninski-lab/lightning-pose-app?tab=readme-ov-file#-release-notes>`_
+     for the latest updates. New capabilities are released weekly.
+
+   * **📣 Join the discord:** Have a question or feature request?
+     Just want to chat? We'd love to hear from you in the
+     `Discord channel <https://discord.gg/tDUPdRj4BM>`_!
 
 .. meta::
    :description: Accessible documentation for animal pose estimation.
@@ -175,7 +193,7 @@ It covers the end-to-end workflow of labeling, training, and evaluation.
 .. toctree::
    :maxdepth: 2
    :hidden:
-   :caption: Getting started
+   :caption: 🚀 Getting started
 
    source/installation_guide
    source/core_concepts
@@ -186,7 +204,7 @@ It covers the end-to-end workflow of labeling, training, and evaluation.
 .. toctree::
    :maxdepth: 4
    :hidden:
-   :caption: CLI User guides
+   :caption: 💻 CLI User guides
 
    source/user_guide_singleview/index
    source/user_guide_multiview/index
@@ -196,21 +214,21 @@ It covers the end-to-end workflow of labeling, training, and evaluation.
 .. toctree::
    :maxdepth: 2
    :hidden:
-   :caption: Community
+   :caption: 🧑‍🤝‍🧑 Community
 
    source/migrating_to_app
-   Discord channel <https://discord.gg/tDUPdRj4BM>
+   📣 Discord channel 📣 <https://discord.gg/tDUPdRj4BM>
    Github Repo <https://github.com/paninski-lab/lightning-pose>
    Release notes <https://github.com/paninski-lab/lightning-pose/releases>
-   App Github Repo <https://github.com/paninski-lab/lightning-pose-app>
+   App Github Repo 📁 <https://github.com/paninski-lab/lightning-pose-app>
    App Release notes <https://github.com/paninski-lab/lightning-pose-app?tab=readme-ov-file#-release-notes>
    source/faqs
 
 
 .. toctree::
    :maxdepth: 2
    :hidden:
-   :caption: Reference
+   :caption: 📖 Reference
 
    source/directory_structure_reference/index
    source/api

docs/source/directory_structure_reference/changelog.rst

@@ -10,6 +10,16 @@ over time.
    :depth: 2
 
 
+v2.0.7.0 | Feb 26, 2026
+------------------------------------
+
+* Added ``creation_datetime`` to the model config file, for display in the model list page.
+  The app backfills the field for existing models on startup.
+* Videos must be stored in ``DATA_DIR/videos`` to be viewable in the viewer. Previously the
+  app supported viewing videos anywhere in the data directory.
+* Label files must be stored at the top-level of ``DATA_DIR`` to be accessible in the labeler. Previously the
+  app supported viewing label files anywhere in the data directory.
+
 v2.0.5.3 | Feb 8, 2026
 ------------------------------------
 

docs/source/directory_structure_reference/model_config_file.rst

@@ -281,3 +281,12 @@ The following parameters are used for general evaluation.
 
 * ``eval.confidence_thresh_for_vid`` (*float, default: 0.9*): predictions with confidence below this
   value will not be plotted in the labeled videos
+
+Additional Metadata
+===================
+
+The following parameters are added to the config by lightning pose on model creation:
+
+* ``creation_datetime``: (*string*) An ISO datetime string of the model creation datetime.
+* ``model.lightning_pose_version``: (*string*) The lightning-pose package version number that created
+  this model.

docs/source/directory_structure_reference/multiview_structure.rst

@@ -19,7 +19,7 @@ The detailed documentation for a multiview project data directory.
       │   ├── session0_view0.mp4
       │   └── session0_view1.mp4
       ├── CollectedData_view0.csv ...........................[4]
-      └── CollectedData_view1.csv
+      ├── CollectedData_view1.csv
       ├── CollectedData_view0.unlabeled.jsonl ...............[5]
       └── CollectedData_view1.unlabeled.jsonl
 

docs/source/installation_guide.rst

@@ -81,18 +81,34 @@ Option B: Installation from Source (Development)
 
 Use this if you plan to modify the source code. This requires cloning the repositories for an **editable** install.
 
+If you want to edit the core training/inference logic:
+
 .. code-block:: bash
 
    # Clone the core repo and install
    git clone https://github.com/paninski-lab/lightning-pose.git
    cd lightning-pose
-   pip install -e .
+   pip install -e ".[dev]"
    cd ..
 
+If you want to edit the app/UI code:
+
+.. code-block:: bash
+
    # Clone the app repo and install
    git clone https://github.com/paninski-lab/lightning-pose-app.git
-   cd lightning-pose-app
+   cd lightning-pose-app/app_server
    pip install -e .
+   cd ..
+
+   # Install node.js via nvm to be able to compile and run the web UI.
+   # Follow the directions here: https://github.com/nvm-sh/nvm
+   # Then:
+   npm install -g @angular/cli
+   cd web_ui
+   npm install
+   cd ..
+   honcho -f Procfile.dev
 
 .. note::
 

lightning_pose/train.py

@@ -1,6 +1,7 @@
 """Example model training function."""
 
 import contextlib
+from datetime import datetime
 import json
 import math
 import os
@@ -21,7 +22,6 @@
 from lightning_pose.api.model_config import ModelConfig
 from lightning_pose.utils import pretty_print_cfg, pretty_print_str
 from lightning_pose.utils.io import (
-    find_video_files_for_views,
     return_absolute_data_paths,
 )
 from lightning_pose.utils.scripts import (
@@ -218,6 +218,7 @@ def _train(cfg: DictConfig, status_file: Path = None) -> Model:
 
     # record lightning-pose version
     with open_dict(cfg):
+        cfg.creation_datetime = datetime.now().isoformat()
         cfg.model.lightning_pose_version = lightning_pose.version
 
     print("Config file:")
@@ -302,7 +303,8 @@ def _train(cfg: DictConfig, status_file: Path = None) -> Model:
     # Log hydra config to tensorboard as helpful metadata.
     for key, value in cfg.items():
         logger.experiment.add_text(
-            "hydra_config_%s" % key, "```\n%s```" % OmegaConf.to_yaml(value)
+            "hydra_config_%s" % key,
+            "```\n%s```" % (value if isinstance(value, str) else OmegaConf.to_yaml(value))
         )
 
     # early stopping, learning rate monitoring, model checkpointing, backbone unfreezing

lightning_pose/utils/__init__.py

@@ -20,7 +20,10 @@ def pretty_print_cfg(cfg):
         print("--------------------")
         print("%s parameters" % key)
         print("--------------------")
-        for k, v in val.items():
-            print("{}: {}".format(k, v))
+        if hasattr(val, "items"):
+            for k, v in val.items():
+                print("{}: {}".format(k, v))
+        if isinstance(val, str):
+            print(val)
         print()
     print("\n\n")

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [project]
 name = "lightning-pose"
-version = "2.0.6"
+version = "2.0.7"
 description = "Semi-supervised pose estimation using pytorch lightning"
 license = "MIT"
 readme = "README.md"