More improvements of NAS documents (#4741)

docs/source/reference/python_api.rst

@@ -5,7 +5,7 @@ Python API Reference
     :maxdepth: 1
 
     Hyperparameter Optimization <hpo>
-    Neural Architecture Search <nas>
+    Neural Architecture Search <nas/index>
     Model Compression <compression>
     Experiment <experiment>
     Others <others>

nni/retiarii/nn/pytorch/cell.py

@@ -45,7 +45,18 @@ class Cell(nn.Module):
 
     A cell consists of multiple "nodes". Each node is a sum of multiple operators. Each operator is chosen from
     ``op_candidates``, and takes one input from previous nodes and predecessors. Predecessor means the input of cell.
-    The output of cell is the concatenation of some of the nodes in the cell (currently all the nodes).
+    The output of cell is the concatenation of some of the nodes in the cell (by default all the nodes).
+
+    Two examples of searched cells are illustrated in the figure below.
+    In these two cells, ``op_candidates`` are series of convolutions and pooling operations.
+    ``num_nodes_per_node`` is set to 2. ``num_nodes`` is set to 5. ``merge_op`` is ``loose_end``.
+    Please take a look at this
+    `review article <https://sh-tsang.medium.com/review-nasnet-neural-architecture-search-network-image-classification-23139ea0425d>`__
+    if you are interested in details.
+
+    .. image:: ../../../img/nasnet_cell.png
+       :width: 900
+       :align: center
 
     Here is a glossary table, which could help better understand the terms used above:
 
@@ -56,9 +67,9 @@ class Cell(nn.Module):
         * - Name
           - Brief Description
         * - Cell
-          - A cell consists of several nodes.
+          - A cell consists of ``num_nodes`` nodes.
         * - Node
-          - A node is the **sum** of several operators.
+          - A node is the **sum** of ``num_ops_per_node`` operators.
         * - Operator
           - Each operator is independently chosen from a list of user-specified candidate operators.
         * - Operator's input
@@ -66,7 +77,7 @@ class Cell(nn.Module):
         * - Predecessors
           - Input of cell. A cell can have multiple predecessors. Predecessors are sent to *preprocessor* for preprocessing.
         * - Cell's output
-          - Output of cell. Usually concatenation of several nodes (possibly all nodes) in the cell. Cell's output,
+          - Output of cell. Usually concatenation of some nodes (possibly all nodes) in the cell. Cell's output,
             along with predecessors, are sent to *postprocessor* for postprocessing.
         * - Preprocessor
           - Extra preprocessing to predecessors. Usually used in shape alignment (e.g., predecessors have different shapes).