OPS counts:
Squeeze : 1
Softmax : 1
BiasAdd : 1
Placeholder : 1
AvgPool : 1
Reshape : 2
ConcatV2 : 9
MaxPool : 13
Sub : 57
Rsqrt : 57
Relu : 57
Conv2D : 58
Add : 114
Mul : 114
Identity : 231
Const : 298
I am overall trying to convert a .pb model to a .coremlmodel and am following this article:
https://hackernoon.com/integrating-tensorflow-model-in-an-ios-app-cecf30b9068d
Getting a text summary from the .pb model is a step towards that. The code I try to run to create the text summary follows:
import tensorflow as tf
from tensorflow.core.framework import graph_pb2
import time
import operator
import sys
def inspect(model_pb, output_txt_file):
graph_def = graph_pb2.GraphDef()
with open(model_pb, "rb") as f:
graph_def.ParseFromString(f.read())
tf.import_graph_def(graph_def)
sess = tf.Session()
OPS = sess.graph.get_operations()
ops_dict = {}
sys.stdout = open(output_txt_file, 'w')
for i, op in enumerate(OPS):
print('---------------------------------------------------------------------------------------------------------------------------------------------')
print("{}: op name = {}, op type = ( {} ), inputs = {}, outputs = {}".format(i, op.name, op.type, ", ".join([x.name for x in op.inputs]), ", ".join([x.name for x in op.outputs])))
print('@input shapes:')
for x in op.inputs:
print("name = {} : {}".format(x.name, x.get_shape()))
print('@output shapes:')
for x in op.outputs:
print("name = {} : {}".format(x.name, x.get_shape()))
if op.type in ops_dict:
ops_dict[op.type] += 1
else:
ops_dict[op.type] = 1
print('---------------------------------------------------------------------------------------------------------------------------------------------')
sorted_ops_count = sorted(ops_dict.items(), key=operator.itemgetter(1))
print('OPS counts:')
for i in sorted_ops_count:
print("{} : {}".format(i[0], i[1]))
if __name__ == "__main__":
Write a summary of the frozen TF graph to a text file.
Summary includes op name, type, input and output names and shapes.
Arguments
----------
- path to the frozen .pb graph
- path to the output .txt file where the summary is written
Usage
----------
python inspect_pb.py frozen.pb text_file.txt
if len(sys.argv) != 3:
raise ValueError("Script expects two arguments. " +
"Usage: python inspect_pb.py /path/to/the/frozen.pb /path/to/the/output/text/file.txt")
inspect(sys.argv[1], sys.argv[2])
I ran this command:
python inspect_pb.py /Users/nikhil.c/Desktop/tensorflowModel.pb text_summary.txt
But instead of receiving the expected output, I receive this error message:
Traceback (most recent call last):
File "inspect_pb.py", line 58, in <module>
inspect(sys.argv[1], sys.argv[2])
File "inspect_pb.py", line 10, in inspect
graph_def.ParseFromString(f.read())
google.protobuf.message.DecodeError: Error parsing message
and do not really know where to start. Other similar questions that seem to receive the same error message do not make too much sense. What do I do?
TensorBoard
Protocol Buffer aka Protobuf (a replacement of XML and JSON file transfer for better performance and protect corruption of data - via some kind of hashing, thus the parsing decode error)
Bazel
I can reproduce the issue from a GCP (cloud) v.1.14 platform to a local TensorFlow (JitTeam Docker) v.1.13 - If I retrain a model it works, if I import, all scripts crash on this error.
You have other export options assuming you still have access to the original file and system
You can try to install other components version with this guide - The author recommend to use his scripts instead of pip3 install. (you can read comments for review of the scripts). It is based on official Tensorflow builds.
You can also try
pip3 install protobuf==3.6.0
This is related into tensorflow issue #21719
