update doc

Author: yifanfeng97

README.md

@@ -70,14 +70,22 @@ The Optuna library endows DHG with the Auto-ML ability. DHG supports automatical
 
 ## Installation
 
-DHG is available for **Python 3.8** and **Pytorch 1.11.0** and above. 
 
-### Install with pip
+Current, the stable version of **DHG** is 0.9.1. You can install it with ``pip`` as follows:
 
-```bash
+```python
 pip install dhg
 ```
 
+You can also try the nightly version (0.9.2) of **DHG** library with ``pip`` as follows:
+
+```python
+pip install git+https://github.com/iMoonLab/DeepHypergraph.git
+```
+
+Nightly version is the development version of **DHG**. It may include the lastest SOTA methods and datasets, but it can also be unstable and not fully tested. 
+If you find any bugs, please report it to us in [GitHub Issues](https://github.com/iMoonLab/DeepHypergraph/issues).
+
 ## Quick Start
 
 ### Learning on Low-Order Structures

dhg/models/hypergraphs/hypergcn.py

@@ -8,6 +8,7 @@
 
 class HyperGCN(nn.Module):
     r"""The HyperGCN model proposed in `HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs <https://papers.nips.cc/paper/2019/file/1efa39bcaec6f3900149160693694536-Paper.pdf>`_ paper (NeurIPS 2019).
+    
     Args:
         ``in_channels`` (``int``): :math:`C_{in}` is the number of input channels.
         ``hid_channels`` (``int``): :math:`C_{hid}` is the number of hidden channels.

docs/source/_static/img/vis_ft_euclidean.png

@@ -9,9 +9,19 @@ Installation
 - Python >= 3.8
 - Pytorch >=1.11
 
-
-You can install **DHG** library with ``pip`` as follows:
+Current, the stable version of **DHG** is 0.9.1. You can install it with ``pip`` as follows:
 
 .. code-block:: bash
 
     pip install dhg
+
+You can also try the nightly version (0.9.2) of **DHG** library with ``pip`` as follows:
+
+.. code-block:: bash
+
+    pip install git+https://github.com/iMoonLab/DeepHypergraph.git
+
+.. note:: 
+    
+    Nightly version is the development version of **DHG**. It may include the lastest SOTA methods and datasets, but it can also be unstable and not fully tested. 
+    If you find any bugs, please report it to us in `GitHub Issues <https://github.com/iMoonLab/DeepHypergraph/issues>`_.

docs/source/_static/img/vis_ft_euclidean_ani.png

@@ -10,10 +10,12 @@ Basic Usages
 ---------------
 DHG provides an interface to visualize the distribution of feaures:
 
-1. Load data of features and lable by specifying the corresponding path;
-2. Specify parameters (*i.e.*, `the dimensionality of the visualisation`, `the storage path` and `the method of dimensionality reduction`);
-3. Call our funtion to show or save the figure . 
+1. Input the features and lable (optional);
+2. Specify parameters (*i.e.*, `the dimensionality of the visualisation`, `point size`, `color` and `the method of dimensionality reduction`);
+3. Call ``plt.show()`` funtion to show the figure/animation. 
 
+   
+.. note:: The ``plt`` is short for ``matplotlib.pyplot`` module.
 
 
 Visualization of Features in Euclidean Space
@@ -27,6 +29,16 @@ Visualization of Features in Euclidean Space
 
 .. code-block:: python
 
+    >>> import dhg
+    >>> import numpy as np
+    >>> import matplotlib.pyplot as plt
+    >>> import dhg.visualization as vis
+    >>> lbl = (np.random.rand(200)*10).astype(int)
+    >>> ft = dhg.random.normal_features(lbl)
+    >>> vis.draw_in_euclidean_space(ft, lbl)
+    >>> plt.show()
+
+..
     >>> import numpy as np
     >>> from dhg.visualization.feature import draw_in_euclidean_space
     >>> ile_dir = "data/modelnet40/test_img_feat_4.npy"
@@ -51,6 +63,16 @@ Visualization of Features in Poincare Space
 
 .. code-block:: python
 
+    >>> import dhg
+    >>> import numpy as np
+    >>> import matplotlib.pyplot as plt
+    >>> import dhg.visualization as vis
+    >>> lbl = (np.random.rand(200)*10).astype(int)
+    >>> ft = dhg.random.normal_features(lbl)
+    >>> vis.draw_in_poincare_space(ft, lbl)
+    >>> plt.show()
+
+..
     >>> import numpy as np
     >>> from dhg.visualization.feature import draw_in_poincare_space
     >>> file_dir = "data/modelnet40/test_img_feat_4.npy" #This varies depending on the situation
@@ -68,20 +90,29 @@ Visualization of Features in Poincare Space
 Make Animation
 -------------------------
 
-Furthermore, we also offer interfaces for the visual presentation of 
-rotation on three-dimensional visualisations with the option of `Rotation` in Euclidean and Poincare Space. 
+We provide functions to make 3D rotation animation for feature visualization.
 
 Rotating Visualization of Features in Euclidean Space
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-.. .. image:: ../_static/img/vis_ft_euclidean.png
-..     :align: center
-..     :alt: Rotating Visualization of Features in Euclidean Space
-..     :height: 400px
+.. image:: ../_static/img/vis_ft_euclidean_ani.png
+    :align: center
+    :alt: Rotating Visualization of Features in Euclidean Space
+    :height: 400px
 
 
 .. code-block:: python
 
+    >>> import dhg
+    >>> import numpy as np
+    >>> import matplotlib.pyplot as plt
+    >>> import dhg.visualization as vis
+    >>> lbl = (np.random.rand(200)*10).astype(int)
+    >>> ft = dhg.random.normal_features(lbl)
+    >>> vis.animation_of_3d_euclidean_space(ft, lbl)
+    >>> plt.show()
+
+.. 
     >>> import numpy as np
     >>> from dhg.visualization.feature import animation_of_3d_euclidean_ball
     >>> ile_dir = "data/modelnet40/test_img_feat_4.npy"
@@ -98,14 +129,24 @@ Rotating Visualization of Features in Euclidean Space
 Rotating Visualization of Features in Poincare Space
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-.. .. image:: ../_static/img/vis_ft_euclidean.png
-..     :align: center
-..     :alt: Rotating Visualization of Features in Poincare Space
-..     :height: 400px
+.. image:: ../_static/img/vis_ft_poincare_ani.png
+    :align: center
+    :alt: Rotating Visualization of Features in Poincare Space
+    :height: 400px
 
 
 .. code-block:: python
 
+    >>> import dhg
+    >>> import numpy as np
+    >>> import matplotlib.pyplot as plt
+    >>> import dhg.visualization as vis
+    >>> lbl = (np.random.rand(200)*10).astype(int)
+    >>> ft = dhg.random.normal_features(lbl)
+    >>> vis.animation_of_3d_poincare_ball(ft, lbl)
+    >>> plt.show()
+
+..
     >>> import numpy as np
     >>> from dhg.visualization.feature import animation_of_3d_poincare_ball
     >>> file_dir = "data/modelnet40/test_img_feat_4.npy" #This varies depending on the situation

docs/source/_static/img/vis_ft_poincare.png

@@ -10,8 +10,21 @@
 - Python >= 3.8
 - Pytorch >=1.11
 
-您可以使用 ``pip`` 指令直接安装 **DHG** 包：
+
+目前， **DHG** 的最新稳定版本 **0.9.1** 已经发布，可以使用 ``pip`` 指令直接安装：
 
 .. code-block:: bash
 
     pip install dhg
+
+如果您想尝试最新的日构建版本(nightly version) **0.9.2** ，可以使用以下指令安装：
+
+.. code-block:: bash
+
+    pip install git+https://github.com/iMoonLab/DeepHypergraph.git
+
+.. note:: 
+    
+    Nightly version 通常会比稳定版本更新，因为它包含了最新的功能和SOTA方法、数据集。但是，nightly version 也可能会有一些bug，因此不建议在生产环境中使用。
+    如果您发现了bug，请在 `GitHub <https://github.com/iMoonLab/DeepHypergraph/issues>`_ 上提交issue。
+