Conversion of .pb file to .ckpt (tensorflow)

Question

I have managed to convert a pre-trained .ckpt model to .pb (protobuf) format using this script :

import os
import tensorflow as tf

# Get the current directory
dir_path = os.path.dirname(os.path.realpath(__file__))
print "Current directory : ", dir_path
save_dir = dir_path + '/Protobufs'

graph = tf.get_default_graph()

# Create a session for running Ops on the Graph.
sess = tf.Session()

print("Restoring the model to the default graph ...")
saver = tf.train.import_meta_graph(dir_path + '/model.ckpt.meta')
saver.restore(sess,tf.train.latest_checkpoint(dir_path))
print("Restoring Done .. ")

print "Saving the model to Protobuf format: ", save_dir

#Save the model to protobuf  (pb and pbtxt) file.
tf.train.write_graph(sess.graph_def, save_dir, "Binary_Protobuf.pb", False)
tf.train.write_graph(sess.graph_def, save_dir, "Text_Protobuf.pbtxt", True)
print("Saving Done .. ")

Now, what I want is the vice-verca procedure. How can I load the protobuf file and convert it to .ckpt (checkpoint) format?

I am trying to do that with the following script but it always fails :

import tensorflow as tf
import argparse 

# Pass the filename as an argument
parser = argparse.ArgumentParser()
parser.add_argument("--frozen_model_filename", default="/path-to-pb-file/Binary_Protobuf.pb", type=str, help="Pb model file to import")
args = parser.parse_args()

    # We load the protobuf file from the disk and parse it to retrieve the 
    # unserialized graph_def
with tf.gfile.GFile(args.frozen_model_filename, "rb") as f:
    graph_def = tf.GraphDef()
    graph_def.ParseFromString(f.read())

    #saver=tf.train.Saver()
    with tf.Graph().as_default() as graph:

        tf.import_graph_def(
            graph_def,
            input_map=None,
            return_elements=None,
            name="prefix",
            op_dict=None,
            producer_op_list=None
        )
        sess = tf.Session(graph=graph)
        saver=tf.train.Saver()
        save_path = saver.save(sess, "path-to-ckpt/model.ckpt")
         print("Model saved to chkp format")

I believe that it would be very helpful to have these conversion scripts.

P.S : The weights are already embedded to the .pb file.

Thanks.

Answer 1

it seems you only got the graph definition in both of the files, not the frozen model.

# This two lines only save the graph as proto file; it doesn't save the variables and their values. 
tf.train.write_graph(sess.graph_def, save_dir, "Binary_Protobuf.pb", False)
tf.train.write_graph(sess.graph_def, save_dir, "Text_Protobuf.pbtxt", True)

frozen graph is obtained using the freeze_graph file