How to load multiple identical models from save files in one session in Tensorflow

Question

In my main code, I create a model based on a configuration file like this

with tf.variable_scope('MODEL') as topscope:
    model = create_model(config_file)#returns input node, output node, and some other placeholders

The name of this area is the same for all saves.

Then I define the optimizer and cost function, etc. (they are outside this area)

Then I create a splash screen and save it:

saver = tf.train.Saver(max_to_keep=10)
saver.save(sess, 'unique_name', global_step=t)

Now I have created and saved 10 different models, and I want to download them immediately, as possible:

models = []
for config, save_path in zip(configs, save_paths):
    models.append(load_model(config, save_path))

and be able to run them and compare their results, mix them, averages, etc. I do not need optimizer slot variables for these loaded models. I need only those variables that are inside the "MODEL" area.

Do I need to create multiple sessions?

? , . , :

saver.restore(sess, save_path)

?

: . . , : ?

2: , :

, , :

import tensorflow as tf
from util import *

OLD_SCOPE_NAME = 'scope1'

sess = tf.Session()

with tf.variable_scope(OLD_SCOPE_NAME) as topscope:
    model = create_model(tf, 6.0, 7.0)
    sc_vars = get_all_variables_from_top_scope(tf, topscope)

print([v.name for v in sc_vars])

sess.run(tf.initialize_all_variables())
print(sess.run(model))

saver = tf.train.Saver()
saver.save(sess, OLD_SCOPE_NAME)

, , :

#RENAMING PART, different file
#create the same model as above here
import tensorflow as tf
from util import *
OLD_SCOPE_NAME = 'scope1'
NEW_SCOPE_NAME = 'scope2'

sess = tf.Session()

with tf.variable_scope(OLD_SCOPE_NAME) as topscope:
    model = create_model(tf, 6.0, 7.0)
    sc_vars = get_all_variables_from_top_scope(tf, topscope)

print([v.name for v in sc_vars])

saver = tf.train.Saver()
saver.restore(sess, OLD_SCOPE_NAME)
print(sess.run(model))


#assuming that we change top scope, not something in the middle, functionality can be added without much trouble I think
#not sure why I need to remove ':0' part, but it seems to work okay
print([NEW_SCOPE_NAME + v.name[len(OLD_SCOPE_NAME):v.name.rfind(':')] for v in sc_vars])
new_saver = tf.train.Saver(var_list={NEW_SCOPE_NAME + v.name[len(OLD_SCOPE_NAME):v.name.rfind(':')]:v for v in sc_vars})
new_saver.save(sess, NEW_SCOPE_NAME)

, :

import tensorflow as tf
from util import *
NEW_SCOPE_NAME = 'scope2'
sess = tf.Session()

with tf.variable_scope(NEW_SCOPE_NAME) as topscope:
    model = create_model(tf, 5.0, 4.0)
    sc_vars = get_all_variables_from_top_scope(tf, topscope)
q = tf.Variable(tf.constant(0.0, shape=[1]), name='q')

print([v.name for v in sc_vars])

saver = tf.train.Saver(var_list=sc_vars)
saver.restore(sess, NEW_SCOPE_NAME)
print(sess.run(model))

util.py:

def get_all_variables_from_top_scope(tf, scope):
    #scope is a top scope here, otherwise change startswith part
    return [v for v in tf.all_variables() if v.name.startswith(scope.name)]

def create_model(tf, param1, param2):
    w = tf.get_variable('W', shape=[1], initializer=tf.constant_initializer(param1))
    b = tf.get_variable('b', shape=[1], initializer=tf.constant_initializer(param2))
    y = tf.mul(w, b, name='mul_op')#no need to save this
    return y

Answer 1

:

• :
• . . , . . , .
• • , ,
  • , .. .

:

• , , , : .
• , /, .

, , . , , :

with tf.variable_scope("some_scope_name"):
    # created model nodes here...  

Tensorboard.

, . , / .

/ / , / , .

, , , , ..

, session.run(...) o /, , , .