[nit] fix some typo within documentation (#40692)

Jiayu Liu · facebook-github-bot · commit 0203d70c6315 · 2020-06-30T19:24:44.000-07:00
Summary: Apologize if this seems trivial, but i'd like to fix them on my way of reading some of the source code. Thanks! Pull Request resolved: #40692 Differential Revision: D22284651 Pulled By: mrshenli fbshipit-source-id: 4259d1808aa4d15a02cfd486cfb44dd75fdc58f8
diff --git a/torch/csrc/jit/codegen/cuda/ir_printer.h b/torch/csrc/jit/codegen/cuda/ir_printer.h
@@ -8,7 +8,7 @@
 
 /*
  * IRMathPrinter and IRTransformPrinter allow the splitting up of fusion print
- * functions. IRMathPrinter as its name implies focuses soley on what tensor
+ * functions. IRMathPrinter as its name implies focuses solely on what tensor
  * computations are taking place. Resulting TensorView math will reflect the
  * series of split/merge/computeAts that have taken place, however these
  * nodes will not be displayed in what is printed. IRTransformPrinter does not
diff --git a/torch/nn/modules/linear.py b/torch/nn/modules/linear.py
@@ -96,7 +96,7 @@ def extra_repr(self) -> str:
         )
 
 
-# This class exists soley for Transformer; it has an annotation stating
+# This class exists solely for Transformer; it has an annotation stating
 # that bias is never None, which appeases TorchScript
 class _LinearWithBias(Linear):
     bias: Tensor
diff --git a/torch/nn/modules/loss.py b/torch/nn/modules/loss.py
@@ -474,7 +474,7 @@ class BCELoss(_WeightedLoss):
     However, an infinite term in the loss equation is not desirable for several reasons.
 
     For one, if either :math:`y_n = 0` or :math:`(1 - y_n) = 0`, then we would be
-    multipying 0 with infinity. Secondly, if we have an infinite loss value, then
+    multiplying 0 with infinity. Secondly, if we have an infinite loss value, then
     we would also have an infinite term in our gradient, since
     :math:`\lim_{x\to 0} \frac{d}{dx} \log (x) = \infty`.
     This would make BCELoss's backward method nonlinear with respect to :math:`x_n`,
@@ -1316,7 +1316,7 @@ class CTCLoss(_Loss):
         >>> # Initialize random batch of input vectors, for *size = (T,N,C)
         >>> input = torch.randn(T, N, C).log_softmax(2).detach().requires_grad_()
         >>> input_lengths = torch.full(size=(N,), fill_value=T, dtype=torch.long)
-        >>> 
+        >>>
         >>> # Initialize random batch of targets (0 = blank, 1:C = classes)
         >>> target_lengths = torch.randint(low=1, high=T, size=(N,), dtype=torch.long)
         >>> target = torch.randint(low=1, high=C, size=(sum(target_lengths),), dtype=torch.long)
diff --git a/torch/nn/modules/module.py b/torch/nn/modules/module.py
@@ -60,7 +60,7 @@ def register_module_forward_pre_hook(hook: Callable[..., None]) -> RemovableHand
     .. warning ::
 
         This adds global state to the `nn.module` module
-        and it is only intended for debugging/profiling purposes. 
+        and it is only intended for debugging/profiling purposes.
 
     The hook will be called every time before :func:`forward` is invoked.
     It should have the following signature::
@@ -92,7 +92,7 @@ def register_module_forward_hook(hook: Callable[..., None]) -> RemovableHandle:
     .. warning ::
 
         This adds global state to the `nn.module` module
-        and it is only intended for debugging/profiling purposes. 
+        and it is only intended for debugging/profiling purposes.
 
     The hook will be called every time after :func:`forward` has computed an output.
     It should have the following signature::
@@ -124,7 +124,7 @@ def register_module_backward_hook(
 
     .. warning ::
         This adds global state to the `nn.module` module
-        and it is only intended for debugging/profiling purposes. 
+        and it is only intended for debugging/profiling purposes.
 
         The current implementation will not have the presented behavior
         for complex :class:`Module` that perform many operations.
@@ -977,7 +977,7 @@ def _load_from_state_dict(self, state_dict, prefix, local_metadata, strict,
                     error_msgs.append('While copying the parameter named "{}", '
                                       'whose dimensions in the model are {} and '
                                       'whose dimensions in the checkpoint are {}, '
-                                      'an exception occured : {}.'
+                                      'an exception occurred : {}.'
                                       .format(key, param.size(), input_param.size(), ex.args))
             elif strict:
                 missing_keys.append(key)
@@ -1329,7 +1329,7 @@ def _get_name(self):
     def extra_repr(self) -> str:
         r"""Set the extra representation of the module
 
-        To print customized extra information, you should reimplement
+        To print customized extra information, you should re-implement
         this method in your own modules. Both single-line and multi-line
         strings are acceptable.
         """
diff --git a/torch/nn/quantized/modules/functional_modules.py b/torch/nn/quantized/modules/functional_modules.py
@@ -6,7 +6,7 @@
 
 
 class FloatFunctional(torch.nn.Module):
-    r"""State collector class for float operatitons.
+    r"""State collector class for float operations.
 
     The instance of this class can be used instead of the ``torch.`` prefix for
     some operations. See example usage below.
@@ -84,7 +84,7 @@ def add_relu(self, x, y):
 
 
 class QFunctional(torch.nn.Module):
-    r"""Wrapper class for quantized operatitons.
+    r"""Wrapper class for quantized operations.
 
     The instance of this class can be used instead of the
     ``torch.ops.quantized`` prefix. See example usage below.

Original file line number	Diff line number	Diff line change
`@@ -96,7 +96,7 @@ def extra_repr(self) -> str:`
`96`	`96`	`)`
`97`	`97`
`98`	`98`
`99`		`-# This class exists soley for Transformer; it has an annotation stating`
	`99`	`+# This class exists solely for Transformer; it has an annotation stating`
`100`	`100`	`# that bias is never None, which appeases TorchScript`
`101`	`101`	`class _LinearWithBias(Linear):`
`102`	`102`	`bias: Tensor`