global_step in momemtum_optimezer #4

Open

opened

on Feb 28, 2017

Is setting trainable = False not necessary in the variable batch in the function momentum_optimzer?
ie. batch = tf.Variable(0,trainable=False,name=global_step) instead of just
batch = tf.Variable(0).

to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests