add note on iterations to tutorial

lab4d-org · Jul 3, 2024 · a83cbc7 · a83cbc7
1 parent d901fb9
commit a83cbc7
Show file tree

Hide file tree

Showing 7 changed files with 18 additions and 5 deletions.
diff --git a/.gitignore b/.gitignore
@@ -11,6 +11,7 @@ run-long.sh
 lab4d.egg-info
 __pycache__/
 *.pth
+*.ckpt
 
 preprocess/third_party/vcnplus/vcn_rob.pth
 preprocess/third_party/viewpoint/human.pth

diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -7,9 +7,7 @@
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
 
 project = "Lab4D"
-copyright = (
-    "2023, Gengshan Yang, Jeff Tan, Alex Lyons, Neehar Peri, Carnegie Mellon University"
-)
+copyright = "2023, Gengshan Yang, Jeff Tan, Alex Lyons, Neehar Peri, Deva Ramanan, Carnegie Mellon University"
 release = "0.0.0"
 
 # -- General configuration ---------------------------------------------------

diff --git a/docs/source/tutorials/arbitrary_video.rst b/docs/source/tutorials/arbitrary_video.rst
@@ -281,4 +281,8 @@ To export meshes and motion parameters, run::
       </model-viewer>
   </div>
 
+.. note::
+
+  The default setting may produce broken meshes. To get better one as shown above, train for more iterations by adding `--num_rounds 120`. Also see `this <https://github.com/lab4d-org/lab4d/issues/46#issuecomment-2206518886>`_ for an explanation.
+
 Visit other `tutorials </lab4d/tutorials/#content>`_.
diff --git a/docs/source/tutorials/category_model.rst b/docs/source/tutorials/category_model.rst
@@ -143,6 +143,9 @@ To export meshes and motion parameters of video 0, run::
       </model-viewer>
   </div>
 
+.. note::
+
+  The default setting may produce broken meshes. To get better one as shown above, train for more iterations by adding `--num_rounds 120`. Also see `this <https://github.com/lab4d-org/lab4d/issues/46#issuecomment-2206518886>`_ for an explanation.
 
 Re-animation
 ----------------------------

diff --git a/docs/source/tutorials/index.rst b/docs/source/tutorials/index.rst
@@ -23,8 +23,8 @@ The tutorials introduce a complete workflow of Lab4D. We'll use the method and d
 Each of the tutorial can be executed in a couple of ways:
 
 - **Custom videos**: This option allows you to train a model on your own videos.
-- **Preprocessed data**: This option skips the preprocessing step and train models on the `preprocessed data </lab4d/data_models.html>`_ we provide.
-- **Render-only**: This option skips model training and allows you to render the `pre-trained model weights </lab4d/data_models.html>`_ we provide.
+- **Preprocessed data**: This option skips the preprocessing step and train models on the `preprocessed data </lab4d/data_models.html>`_ we provided.
+- **Render-only**: This option skips model training and allows you to render the `pre-trained model weights </lab4d/data_models.html>`_ we provided.
 
 
 Content

diff --git a/docs/source/tutorials/multi_video_cat.rst b/docs/source/tutorials/multi_video_cat.rst
@@ -135,4 +135,8 @@ To export meshes and motion parameters, run::
       </model-viewer>
   </div>
 
+.. note::
+
+  The default setting may produce broken meshes. To get better one as shown above, train for more iterations by adding `--num_rounds 120`. Also see `this <https://github.com/lab4d-org/lab4d/issues/46#issuecomment-2206518886>`_ for an explanation.
+
 Visit other `tutorials </lab4d/tutorials/#content>`_.
diff --git a/docs/source/tutorials/single_video_cat.rst b/docs/source/tutorials/single_video_cat.rst
@@ -155,6 +155,9 @@ To export meshes and motion parameters, run::
       </model-viewer>
   </div>
 
+.. note::
+
+  The default setting may produce broken meshes. To get better one as shown above, train for more iterations by adding `--num_rounds 120`. Also see `this <https://github.com/lab4d-org/lab4d/issues/46#issuecomment-2206518886>`_ for an explanation.
 
 Reconstruct the total scene
 ------------------------------------------------------------