Initialize variables in collection in the tensorflow

Question

how to initialize some variables in the collection?

 with tf.Session() as sess:
    col1 = tf.add_to_collection('init',a )
    sess.run(tf.variables_initializer(col1))
    uninitializer_vars  = []
    for var in tf.global_variables():
        try :
            sess.run(var)
        except tf.errors.FailedPreconditionError:
            uninitializer_vars.append(var)
    print(uninitializer_vars)

Answer 1

Just pass the list of variables in a collection to https://www.tensorflow.org/api_docs/python/tf/variables_initializer to get an op that will initialize these variables.

vars = tf.get_collection('my_collection_name')
vars_init_op = tf.variables_initializer(vars)
sess.run(vars_init_op)