Fix typos

README.md

@@ -1,10 +1,10 @@
 # Pretty Tensor - Fluent Neural Networks in TensorFlow
 
-Pretty Tensor provides a high level builder API for TensorFlow. It provides
+Pretty Tensor is a high level builder API for TensorFlow. It provides
 thin wrappers on Tensors so that you can easily build multi-layer neural
 networks.
 
-Pretty Tensor provides a set of objects that behave likes Tensors, but also
+Pretty Tensor provides a set of objects that behave like Tensors, but also
 support a chainable object syntax to quickly define neural networks
 and other layered architectures in TensorFlow.
 
@@ -14,17 +14,15 @@ and other layered architectures in TensorFlow.
               .fully_connected(10, activation_fn=None)
               .softmax(labels, name=softmax_name))
 
-Please look here for full documentation of the PrettyTensor object for all
-available operations:
-[Available Operations](docs/PrettyTensor.md) or you can check out the [complete
-documentation](docs/pretty_tensor_top_level.md)
+Please see [here](docs/PrettyTensor.md) for full documentation of the PrettyTensor object for all
+available operations. You can also check out the [complete documentation](docs/pretty_tensor_top_level.md).
 
 See the tutorial directory for samples:
 [tutorial/](prettytensor/tutorial/)
 
 ## Installation
 
-The easiest installation is just to use pip:
+The easiest way to install is just to use pip:
 
 1. Follow the instructions at
     [tensorflow.org](https://www.tensorflow.org/versions/master/get_started/os_setup.html#pip_install)
@@ -72,28 +70,28 @@ The easiest installation is just to use pip:
 
 #### Full power of TensorFlow is easy to use
 
-Pretty Tensors can be used (almost) everywhere that a tensor can.  Just call
+Pretty Tensors can be used (almost) everywhere that a tensor can. Just call
 `pt.wrap` to make a tensor pretty.
 
 You can also add any existing TensorFlow function to the chain using `apply`.
 `apply` applies the current Tensor as the first argument and takes all the other
 arguments as normal.
 
-*Note:* because apply is so generic, Pretty Tensor doesn't try to wrap the
+*Note:* Because apply is so generic, Pretty Tensor doesn't try to wrap the
 world.
 
 #### Plays well with other libraries
 
 It also uses standard TensorFlow idioms so that it plays well with other
-libraries, this means that you can use it a little bit in a model or throughout.
+libraries. This means that you can use it a little bit in a model or throughout.
 Just make sure to run the update_ops on each training set
 (see [with_update_ops](docs/pretty_tensor_top_level.md#with_update_ops)).
 
 ### Terse
 
 You've already seen how a Pretty Tensor is chainable and you may have noticed
-that it takes care of handling the input shape.  One other feature worth noting
-are defaults.  Using defaults you can specify reused values in a single place
+that it takes care of handling the input shape. One other feature worth noting
+is defaults. Using defaults you can specify reused values in a single place
 without having to repeat yourself.
 
     with pt.defaults_scope(activation_fn=tf.nn.relu):
@@ -142,14 +140,14 @@ There are also some convenient shorthands for LSTMs and GRUs:
 ### Extensible
 
 You can call any existing operation by using `apply` and it will simply
-subsitute the current tensor for the first argument.
+substitute the current tensor for the first argument.
 
     pretty_input.apply(tf.mul, 5)
 
-You can also create a new operation  There are two supported registration
+You can also create a new operation. There are two supported registration
 mechanisms to add your own functions. `@Register()` allows you to create a
-method on PrettyTensor that operates on the Tensors and returns either a loss or
-a new value. Name scoping and variable scoping are handled by the framework.
+method on PrettyTensor that operates on the tensors and returns either a loss or
+a new value. Name scoping and variable scoping is handled by the framework.
 
 The following method adds the leaky_relu method to every Pretty Tensor:
 
@@ -158,19 +156,19 @@ The following method adds the leaky_relu method to every Pretty Tensor:
       return tf.select(tf.greater(input_pt, 0.0), input_pt, 0.01 * input_pt)
 
 
-`@RegisterCompoundOp()` is like adding a macro, it is designed to group together
+`@RegisterCompoundOp()` is like adding a macro; it is designed to group together
 common sets of operations.
 
 ### Safe variable reuse
 
-Within a graph, you can reuse variables by using templates.  A template is
+Within a graph, you can reuse variables by using templates. A template is
 just like a regular graph except that some variables are left unbound.
 
 See more details in [PrettyTensor class](docs/PrettyTensor.md).
 
 ### Accessing Variables
 
-Pretty Tensor uses the standard graph collections from TensorFlow to store variables.  These can be accessed using `tf.get_collection(key)` with the following keys:
+Pretty Tensor uses the standard graph collections from TensorFlow to store variables. These can be accessed using `tf.get_collection(key)` with the following keys:
 
 * `tf.GraphKeys.VARIABLES`: all variables that should be saved (including some statistics).
 * `tf.GraphKeys.TRAINABLE_VARIABLES: all variables that can be trained (including those before a `stop_gradients` call). These are what would typically be called *parameters* of the model in ML parlance.