When working with the default global graph, is it possible to remove nodes after they've been added, or alternatively to reset the default graph to empty? When working with TF interactively in IPython, I find myself having to restart the kernel repeatedly. I would like to be able to experiment with graphs more easily if possible.
Clears the default graph stack and resets the global default graph.
A graph is like a TODO: list. You may use more than one graphs (created with tf. Graph() in the same process, but one is the default. Note you will have to use different sessions for each graph, but each graph can be used in multiple sessions. Even more, a session allows executing graphs or part of graphs.
Graph execution means that tensor computations are executed as a TensorFlow graph, sometimes referred to as a tf. Graph or simply a "graph." Graphs are data structures that contain a set of tf. Operation objects, which represent units of computation; and tf.
Update 11/2/2016
tf.reset_default_graph()
Old stuff
There's reset_default_graph
, but not part of public API (I think it should be, does someone wants to file an issue on GitHub?)
My work-around to reset things is this:
from tensorflow.python.framework import ops ops.reset_default_graph() sess = tf.InteractiveSession()
By default, a session is constructed around the default graph. To avoid leaving dead nodes in the session, you need to either control the default graph or use an explicit graph.
To clear the default graph, you can use the tf.reset_default_graph function.
tf.reset_default_graph() sess = tf.InteractiveSession()
You can also construct explicitly a graph and avoid using the default one. If you use a normal Session
, you will need to fully create the graph before constructing the session. For InteractiveSession
, you can just declare the graph and use it as a context to declare further changes:
g = tf.Graph() sess = tf.InteractiveSession(graph=g) with g.asdefault(): # Put variable declaration and other tf operation # in the graph context .... b = tf.matmul(A, x) .... sess.run([b], ...)
EDIT: For recent versions of tensorflow
(1.0+), the correct function is g.as_default
.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With