Merge pull request #183 from devendragovil/tpm3

Fixes #169, Thumbnails Updated
pyt-team · Sep 13, 2023 · 1ece602 · 1ece602
2 parents efc1d1c + 6ed555e
commit 1ece602
Show file tree

Hide file tree

Showing 40 changed files with 118 additions and 21 deletions.
diff --git a/docs/_thumbnails/cell/can_train.png b/docs/_thumbnails/cell/can_train.png
diff --git a/docs/_thumbnails/cell/can_train_bis.png b/docs/_thumbnails/cell/can_train_bis.png
diff --git a/docs/_thumbnails/cell/ccxn_train.png b/docs/_thumbnails/cell/ccxn_train.png
diff --git a/docs/_thumbnails/cell/cwn_train.png b/docs/_thumbnails/cell/cwn_train.png
diff --git a/docs/_thumbnails/hypergraph/allset_train.png b/docs/_thumbnails/hypergraph/allset_train.png
diff --git a/docs/_thumbnails/hypergraph/allset_transformer_train.png b/docs/_thumbnails/hypergraph/allset_transformer_train.png
diff --git a/docs/_thumbnails/hypergraph/dhgcn_train.png b/docs/_thumbnails/hypergraph/dhgcn_train.png
diff --git a/docs/_thumbnails/hypergraph/hmpnn_train.png b/docs/_thumbnails/hypergraph/hmpnn_train.png
diff --git a/docs/_thumbnails/hypergraph/hnhn_train.png b/docs/_thumbnails/hypergraph/hnhn_train.png
diff --git a/docs/_thumbnails/hypergraph/hnhn_train_bis.png b/docs/_thumbnails/hypergraph/hnhn_train_bis.png
diff --git a/docs/_thumbnails/hypergraph/hypergat_train.png b/docs/_thumbnails/hypergraph/hypergat_train.png
diff --git a/docs/_thumbnails/hypergraph/hypersage_train.png b/docs/_thumbnails/hypergraph/hypersage_train.png
diff --git a/docs/_thumbnails/hypergraph/template_train.png b/docs/_thumbnails/hypergraph/template_train.png
diff --git a/docs/_thumbnails/hypergraph/unigcn_train.png b/docs/_thumbnails/hypergraph/unigcn_train.png
diff --git a/docs/_thumbnails/hypergraph/unigcnii_train.png b/docs/_thumbnails/hypergraph/unigcnii_train.png
diff --git a/docs/_thumbnails/hypergraph/unigin_train.png b/docs/_thumbnails/hypergraph/unigin_train.png
diff --git a/docs/_thumbnails/hypergraph/unisage_train.png b/docs/_thumbnails/hypergraph/unisage_train.png
diff --git a/docs/_thumbnails/simplicial/dist2cycle_train.png b/docs/_thumbnails/simplicial/dist2cycle_train.png
diff --git a/docs/_thumbnails/simplicial/hsn_train.png b/docs/_thumbnails/simplicial/hsn_train.png
diff --git a/docs/_thumbnails/simplicial/san_train.png b/docs/_thumbnails/simplicial/san_train.png
diff --git a/docs/_thumbnails/simplicial/sca_cmps_train.png b/docs/_thumbnails/simplicial/sca_cmps_train.png
diff --git a/docs/_thumbnails/simplicial/sccn_train.png b/docs/_thumbnails/simplicial/sccn_train.png
diff --git a/docs/_thumbnails/simplicial/sccnn_train.png b/docs/_thumbnails/simplicial/sccnn_train.png
diff --git a/docs/_thumbnails/simplicial/scconv_train.png b/docs/_thumbnails/simplicial/scconv_train.png
diff --git a/docs/_thumbnails/simplicial/scn2_train.png b/docs/_thumbnails/simplicial/scn2_train.png
diff --git a/docs/_thumbnails/simplicial/scnn_train.png b/docs/_thumbnails/simplicial/scnn_train.png
diff --git a/docs/_thumbnails/simplicial/scone_train.png b/docs/_thumbnails/simplicial/scone_train.png
diff --git a/docs/_thumbnails/simplicial/scone_train_bis.png b/docs/_thumbnails/simplicial/scone_train_bis.png
diff --git a/docs/tutorials/index.rst b/docs/tutorials/index.rst
@@ -4,10 +4,33 @@
 Tutorials
 =========
 
+---------------------------------------------------------
+Tutorials for Topological Neural Nets on Cellular Complex
+---------------------------------------------------------
+
 .. nbgallery::
    :maxdepth: 1
    :glob:
 
    ../notebooks/cell/*
+
+
+----------------------------------------------------
+Tutorials for Topological Neural Nets on Hypergraphs
+----------------------------------------------------
+
+.. nbgallery::
+   :maxdepth: 1
+   :glob:
+
    ../notebooks/hypergraph/*
-   ../notebooks/simplicial/*
+
+-----------------------------------------------------------
+Tutorials for Topological Neural Nets on Simplicial Complex
+-----------------------------------------------------------
+
+.. nbgallery::
+   :maxdepth: 1
+   :glob:
+
+   ../notebooks/simplicial/*
diff --git a/tutorials/README.md b/tutorials/README.md
@@ -0,0 +1,16 @@
+
+# Tutorials
+
+This section contains tutorials for a variety of topological neural networks.
+
+## Contribution
+
+To add an additional tutorial follow the following:
+1. Prepare a well documented and self-explanatory .ipynb file using various modules of the library.
+2. Place your notebook in the right directory depending on the data structure used. e.g. cell for Cellular Complex
+3. The notebook title (H1 heading) will be displayed as the title of the notebook in the Sphinx Notebook Gallery, so please chose that wisely.
+4. Make sure the notebook is able to test pytest for the notebook.
+5. Prepare a thumbnail (ideally a tensor diagram) for the notebook.
+6. Place the thumbnail in the docs/_thumbnails under the correct directory. "cell" directory in our example as used above.
+7. Make sure to change the conf.py file present within docs to include the thumbnail to be included in Sphinx generated Gallery.
+
diff --git a/tutorials/cell/ccxn_train.ipynb b/tutorials/cell/ccxn_train.ipynb
@@ -634,7 +634,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.6 64-bit",
    "language": "python",
    "name": "python3"
   },
@@ -648,7 +648,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.9.6"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
+   }
   }
  },
  "nbformat": 4,

diff --git a/tutorials/cell/cwn_train.ipynb b/tutorials/cell/cwn_train.ipynb
@@ -635,7 +635,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.6 64-bit",
    "language": "python",
    "name": "python3"
   },
@@ -649,7 +649,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.9.6"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
+   }
   }
  },
  "nbformat": 4,

diff --git a/tutorials/hypergraph/allset_train.ipynb b/tutorials/hypergraph/allset_train.ipynb
@@ -5,7 +5,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Train a Hypergraph Neural Network\n",
+    "# Train an All-Set TNN\n",
     "\n",
     "In this notebook, we will create and train a two-step message passing network named AllSet (Chien et al., [2021](https://arxiv.org/abs/2106.13264)) in the hypergraph domain. We will use a benchmark dataset, shrec16, a collection of 3D meshes, to train the model to perform classification at the level of the hypergraph. \n",
     "\n",
@@ -500,7 +500,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.6 64-bit",
    "language": "python",
    "name": "python3"
   },
@@ -514,7 +514,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.9.6"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
+   }
   }
  },
  "nbformat": 4,

diff --git a/tutorials/hypergraph/allset_transformer_train.ipynb b/tutorials/hypergraph/allset_transformer_train.ipynb
@@ -7,7 +7,7 @@
    "source": [
     "\n",
     "\n",
-    "# Train a Hypergraph Neural Network\n",
+    "# Train an All-Set-Transformer TNN\n",
     "\n",
     "In this notebook, we will create and train a two-step message passing network named AllSetTransformer (Chien et al., [2021](https://arxiv.org/abs/2106.13264)) in the hypergraph domain. We will use a benchmark dataset, shrec16, a collection of 3D meshes, to train the model to perform classification at the level of the hypergraph. \n",
     "\n",
@@ -512,7 +512,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.6 64-bit",
    "language": "python",
    "name": "python3"
   },
@@ -526,7 +526,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.9.6"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
+   }
   }
  },
  "nbformat": 4,

diff --git a/tutorials/hypergraph/dhgcn_train.ipynb b/tutorials/hypergraph/dhgcn_train.ipynb
@@ -5,7 +5,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Train a Hypergraph Neural Network\n",
+    "# Train a DHGCN TNN\n",
     "\n",
     "In this notebook, we will create and train a two-step message passing network in the hypergraph domain. We will use a benchmark dataset, shrec16, a collection of 3D meshes, to train the model to perform classification at the level of the hypergraph. "
    ]
@@ -466,7 +466,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.6 64-bit",
    "language": "python",
    "name": "python3"
   },
@@ -480,7 +480,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.9.6"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
+   }
   }
  },
  "nbformat": 4,

diff --git a/tutorials/hypergraph/hypersage_train.ipynb b/tutorials/hypergraph/hypersage_train.ipynb
@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Train a Hypergraph Neural Network\n",
+    "# Train a Hypersage TNN\n",
     "\n",
     "In this notebook, we will create and train HyperSAGE layer (Arya et al., [2020](https://arxiv.org/abs/2010.04558)) - two-levels message passing strategy for hypergraphs learning. We will use a benchmark dataset, shrec16, a collection of 3D meshes, to train the model to perform classification at the level of the hypergraph.\n",
     "\n",
@@ -389,7 +389,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "torchg",
+   "display_name": "Python 3.9.6 64-bit",
    "language": "python",
    "name": "python3"
   },
@@ -403,9 +403,14 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.9.6"
   },
-  "orig_nbformat": 4
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
+   }
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 2

diff --git a/tutorials/hypergraph/template_train.ipynb b/tutorials/hypergraph/template_train.ipynb
@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Train a Hypergraph Neural Network\n",
+    "# Train a (template) Hypergraph Neural Network\n",
     "\n",
     "In this notebook, we will create and train a two-step message passing network in the hypergraph domain. We will use a benchmark dataset, shrec16, a collection of 3D meshes, to train the model to perform classification at the level of the hypergraph. "
    ]
@@ -467,7 +467,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.6 64-bit",
    "language": "python",
    "name": "python3"
   },
@@ -481,7 +481,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.9.6"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
+   }
   }
  },
  "nbformat": 4,

diff --git a/tutorials/hypergraph/unigcn_train.ipynb b/tutorials/hypergraph/unigcn_train.ipynb
@@ -22,6 +22,14 @@
     "warnings.filterwarnings(\"ignore\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "ca204a1d",
+   "metadata": {},
+   "source": [
+    "# Train a UNIGCN TNN"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "40b0ed66",

diff --git a/tutorials/hypergraph/unigin_train.ipynb b/tutorials/hypergraph/unigin_train.ipynb
@@ -15,6 +15,13 @@
     "from topomodelx.nn.hypergraph.unigin_layer import UniGINLayer"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Train a UNIGIN TNN"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",

diff --git a/tutorials/hypergraph/unisage_train.ipynb b/tutorials/hypergraph/unisage_train.ipynb
@@ -31,6 +31,14 @@
     "warnings.filterwarnings(\"ignore\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "b7251cc4",
+   "metadata": {},
+   "source": [
+    "# Train a Uni-sage TNN"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "35742145",