fix docs

docs/source/encoding.rst

@@ -46,3 +46,7 @@ Functions
     :members:
 
 
+:hidden:`assign`
+~~~~~~~~~~~~~~~~~~~
+
+.. autofunction:: assign

docs/source/notes/compile.rst

@@ -20,3 +20,13 @@ Install PyTorch-Encoding
 
          MACOSX_DEPLOYMENT_TARGET=10.9 CC=clang CXX=clang++ python setup.py install
 
+- Reference:
+    Hang Zhang, Jia Xue, and Kristin Dana. "Deep TEN: Texture Encoding Network." *The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017*::
+
+        @InProceedings{Zhang_2017_CVPR,
+        author = {Zhang, Hang and Xue, Jia and Dana, Kristin},
+        title = {Deep TEN: Texture Encoding Network},
+        booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
+        month = {July},
+        year = {2017}
+        }

encoding/functions/aggregate.py

@@ -239,6 +239,17 @@ class square_squeeze(Function):
     
 
 def assign(R, S):
+    r"""
+    Calculate assignment weights for given residuals (:math:`R`) and scale (:math:`S`)
+
+    .. math::
+        a_{ik} = \frac{exp(-s_k\|x_{i}-c_k\|^2)}{\sum_{j=1}^K exp(-s_j\|x_{i}-c_j\|^2)}
+
+    Shape:
+        - Input: :math:`R\in\mathcal{R}^{B\times N\times K\times D}` :math:`S\in \mathcal{R}^K` (where :math:`B` is batch, :math:`N` is total number of features, :math:`K` is number is codewords, :math:`D` is feature dimensions.)
+        - Output :math:`A\in\mathcal{R}^{B\times N\times K}`
+
+    """
     L = square_squeeze()(R)
     K = S.size(0)
     SL = L * S.view(1,1,K)

encoding/modules/encoding.py

@@ -23,7 +23,7 @@ class Encoding(nn.Module):
 
     .. math::
 
-        a_{ik} = \frac{exp(-\beta\|x_{i}-c_k\|^2)}{\sum_{j=1}^K exp(-\beta\|x_{i}-c_j\|^2)}
+        e_{ik} = \frac{exp(-s_k\|x_{i}-c_k\|^2)}{\sum_{j=1}^K exp(-s_j\|x_{i}-c_j\|^2)} (x_i - c_k)
 
     Args:
         D: dimention of the features or feature channels
@@ -95,7 +95,7 @@ class Aggregate(nn.Module):
     Aggregate operation, aggregate the residuals (:math:`R`) with assignment weights (:math:`A`).
 
     .. math::
-        e_{k} = \sum_{i=1}^{N} a_{ik} (r_{ik})
+        e_{k} = \sum_{i=1}^{N} a_{ik} r_{ik}
 
     Shape:
         - Input: :math:`A\in\mathcal{R}^{B\times N\times K}` :math:`R\in\mathcal{R}^{B\times N\times K\times D}` (where :math:`B` is batch, :math:`N` is total number of features, :math:`K` is number is codewords, :math:`D` is feature dimensions.)