Fix math formatting of PairwiseDistance and CosineSimilarity docs and fix math format...

Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/19534

Differential Revision: D15034011

Pulled By: ezyang

fbshipit-source-id: 60b81c970c919508a57c86fb23edc9f64973117c

diff --git a/torch/nn/modules/distance.py b/torch/nn/modules/distance.py
index 9218992..29edfdd 100644 (file)
--- a/torch/nn/modules/distance.py
+++ b/torch/nn/modules/distance.py
@@ -7,8 +7,10 @@ from ..._jit_internal import weak_module, weak_script_method
 class PairwiseDistance(Module):
     r"""
     Computes the batchwise pairwise distance between vectors :math:`v_1`, :math:`v_2` using the p-norm:
+
     .. math ::
-        \Vert x \Vert _p = \left( \sum_{i=1}^n  \vert x_i \vert ^ p \right) ^ {1/p}
+        \Vert x \Vert _p = \left( \sum_{i=1}^n  \vert x_i \vert ^ p \right) ^ {1/p}.
+
     Args:
         p (real): the norm degree. Default: 2
         eps (float, optional): Small value to avoid division by zero.
@@ -41,8 +43,10 @@ class PairwiseDistance(Module):
 @weak_module
 class CosineSimilarity(Module):
     r"""Returns cosine similarity between :math:`x_1` and :math:`x_2`, computed along dim.
+
     .. math ::
-        \text{similarity} = \dfrac{x_1 \cdot x_2}{\max(\Vert x_1 \Vert _2 \cdot \Vert x_2 \Vert _2, \epsilon)}
+        \text{similarity} = \dfrac{x_1 \cdot x_2}{\max(\Vert x_1 \Vert _2 \cdot \Vert x_2 \Vert _2, \epsilon)}.
+
     Args:
         dim (int, optional): Dimension where cosine similarity is computed. Default: 1
         eps (float, optional): Small value to avoid division by zero.

diff --git a/torch/nn/modules/loss.py b/torch/nn/modules/loss.py
index 38aefc6..ee3e6a1 100644 (file)
--- a/torch/nn/modules/loss.py
+++ b/torch/nn/modules/loss.py
@@ -1221,7 +1221,7 @@ class CTCLoss(_Loss):
     Calculates loss between a continuous (unsegmented) time series and a target sequence. CTCLoss sums over the
     probability of possible alignments of input to target, producing a loss value which is differentiable
     with respect to each input node. The alignment of input to target is assumed to be "many-to-one", which
-    limits the length of the target sequence such that it must be :math: `\leq` the input length.
+    limits the length of the target sequence such that it must be :math:`\leq` the input length.
 
     **Args:**
         **blank** (int, optional): blank label. Default :math:`0`.
@@ -1238,21 +1238,21 @@ class CTCLoss(_Loss):
 
     **Inputs:**
         **log_probs**: Tensor of size :math:`(T, N, C)`
-            | :math:`T = input length`
-            | :math:`N = batch size`
-            | :math:`C = number of classes (including blank)`
+            | :math:`T = \text{input length}`
+            | :math:`N = \text{batch size}`
+            | :math:`C = \text{number of classes (including blank)}`
 
             The logarithmized probabilities of the outputs
             (e.g. obtained with :func:`torch.nn.functional.log_softmax`).
-        **targets**: Tensor of size :math:`(N, S)` or `(sum(target_lengths))`
-            | :math:`N = batch size`
-            | :math:`S = max target length, if shape is (N, S)`.
+        **targets**: Tensor of size :math:`(N, S)` or :math:`(\text{sum(target_lengths)})`
+            | :math:`N = \text{batch size}`
+            | :math:`S = \text{max target length, if shape is } (N, S)`.
 
             | Target sequences. Each element in the target sequence is a class index. Target index
               cannot be blank (default=0).
 
             | In the :math:`(N, S)` form, targets are padded to the length of the longest sequence, and stacked.
-            | In the :math:`(sum(target_lengths))` form, the targets are assumed to be un-padded and concatenated
+            | In the :math:`(\text{sum(target_lengths)})` form, the targets are assumed to be un-padded and concatenated
               within 1 dimension.
         **input_lengths**: Tuple or tensor of size :math:`(N)`.
             Lengths of the inputs (must each be :math:`\leq T`).