fix: typo spelling grammar

docs/block_sparse_tutorial.rst

@@ -232,7 +232,7 @@ notable difference to numpy arrays. For example, while reshaping of
 `a1` into a shape `(19,2,10,21)` would be possible if `a1` was a
 dense `numpy.ndarray`, it is no longer possible for
 `BlockSparseTensor` because we don't have the neccessary information
-to split up `i1` into two seperate legs. If you try anyway, we'll
+to split up `i1` into two separate legs. If you try anyway, we'll
 raise a `ValueError`:
 
 .. code-block:: python3

docs/copy_contract.rst

@@ -13,11 +13,11 @@ Using a contraction algorithm is very easy.
 
 .. figure:: _static/contractors.png
 
-We have several contraction algorithms avaliable as of April 2020.
+We have several contraction algorithms available as of April 2020.
 
-- `optimal`: Find the true optimal path via brute force. It can be extremly slow for more than ~10 nodes.
+- `optimal`: Find the true optimal path via brute force. It can be extremely slow for more than ~10 nodes.
 - `greedy`: Continuously do the cheapest contraction possible. Works well as a default for networks with many nodes.
-- `branch`: Brute search, but only check the top `n` possiblities per step.
+- `branch`: Brute search, but only check the top `n` possibilities per step.
 - `auto`: Automatically decide which of the above 3 algorithms to use.
 
 When contracting a network with more than one dangling leg, you must specify the output order of the dangling legs. 
@@ -31,11 +31,11 @@ When contracting a network with more than one dangling leg, you must specify the
 
 .. figure:: _static/dangling_contract.png
 
-If you do not care about the final output order (for instance, if you are only doing a partial network contraction and the intermidiate order doesn't matter), then you can set `ignore_edge_order=True` and you won't need to supply an `output_edge_order`.
+If you do not care about the final output order (for instance, if you are only doing a partial network contraction and the intermediate order doesn't matter), then you can set `ignore_edge_order=True` and you won't need to supply an `output_edge_order`.
 
 Contracting subgraph
 ---------------------
-There are many instances when you want to contract only a subset of your network. Perhaps you know good intermidiate states, but not how to get there efficiently. You can still very easily get a good contraction order by using the subnetwork contraction feature of the `contractors`.
+There are many instances when you want to contract only a subset of your network. Perhaps you know good intermediate states, but not how to get there efficiently. You can still very easily get a good contraction order by using the subnetwork contraction feature of the `contractors`.
 
  .. code-block:: python3
 
@@ -54,7 +54,7 @@ When building tensor networks, it's very common to want to use a single tensorne
 
  .. code-block:: python3
 
-  # Calcualte the inner product of two MPS/Product state networks.
+  # Calculate the inner product of two MPS/Product state networks.
   def inner_product(x: List[tn.Node], y: List[tn.Node]) -> tn.Node:
     for a, b in zip(x, y)
       # Assume all of the dangling edges are mapped to the name "dangling"

tensornetwork/backends/symmetric/symmetric_backend.py

@@ -488,7 +488,7 @@ def gmres(self,#pylint: disable=arguments-differ
     Reshaping to and from a matrix problem is handled internally.
 
     The numpy backend version of GMRES is simply an interface to
-    `scipy.sparse.linalg.gmres`, itself an interace to ARPACK.
+    `scipy.sparse.linalg.gmres`, itself an interface to ARPACK.
     SciPy 1.1.0 or newer (May 05 2018) is required.
 
     Args:

tensornetwork/block_sparse/linalg.py

@@ -320,7 +320,7 @@ def qr(matrix: BlockSparseTensor, mode: Text = 'reduced') -> Any:
   if mode not in ('reduced', 'complete', 'raw', 'r'):
     raise ValueError('unknown value {} for input `mode`'.format(mode))
   if mode == 'raw':
-    raise NotImplementedError('mode `raw` currenntly not supported')
+    raise NotImplementedError('mode `raw` currently not supported')
 
   flat_charges = matrix._charges
   flat_flows = matrix._flows

tensornetwork/linalg/initialization.py

@@ -111,7 +111,7 @@ def ones_like(tensor: Union[Any],
               backend: Optional[Union[Text, AbstractBackend]] = None) -> Tensor:
   """Return a Tensor shape full of ones the same shape as input
   Args:
-    tensor : Object to recieve shape from
+    tensor : Object to receive shape from
      dtype (optional) : dtype of object
      backend(optional): The backend or its name."""
   if backend is None:
@@ -139,7 +139,7 @@ def zeros_like(tensor: Union[Any],
                                        AbstractBackend]] = None) -> Tensor:
   """Return a Tensor shape full of zeros the same shape as input
   Args:
-    tensor : Object to recieve shape from
+    tensor : Object to receive shape from
      dtype (optional) : dtype of object
      backend(optional): The backend or its name."""
   if backend is None:

tensornetwork/network_components.py

@@ -2078,7 +2078,7 @@ def contract_between(
           np.mean(node1_output_axes) > np.mean(node2_output_axes)):
         node1, node2 = node2, node1
         axes1, axes2 = axes2, axes1
-    # Sorting the indicies improves performance.
+    # Sorting the indices improves performance.
     ind_sort = [axes1.index(l) for l in sorted(axes1)]
     axes1 = [axes1[i] for i in ind_sort]
     axes2 = [axes2[i] for i in ind_sort]

tensornetwork/network_operations.py

@@ -800,7 +800,7 @@ def switch_backend(nodes: Iterable[AbstractNode], new_backend: Text) -> None:
     nodes: iterable of nodes
     new_backend (str): The new backend.
     dtype (datatype): The dtype of the backend. If `None`,
-      a defautl dtype according to config.py will be chosen.
+      a default dtype according to config.py will be chosen.
 
   Returns:
     None

tensornetwork/tn_keras/dense.py

@@ -65,7 +65,7 @@ def __init__(self,
                **kwargs) -> None:
 
     # Allow specification of input_dim instead of input_shape,
-    # for compatability with Keras layers that support this
+    # for compatibility with Keras layers that support this
     if 'input_shape' not in kwargs and 'input_dim' in kwargs:
       kwargs['input_shape'] = (kwargs.pop('input_dim'),)
 

tensornetwork/tn_keras/mpo.py

@@ -65,7 +65,7 @@ def __init__(self,
                **kwargs) -> None:
 
     # Allow specification of input_dim instead of input_shape,
-    # for compatability with Keras layers that support this
+    # for compatibility with Keras layers that support this
     if 'input_shape' not in kwargs and 'input_dim' in kwargs:
       kwargs['input_shape'] = (kwargs.pop('input_dim'),)