I have fine-tuned inception model with a new dataset and saved it as ".h5" model in Keras. now my goal is to run my model on android Tensorflow which accepts ".pb" extension only. question is that is there any library in Keras or tensorflow to do this conversion? I have seen this post so far :https://blog.keras.io/keras-as-a-simplified-interface-to-tensorflow-tutorial.html but can't figure out yet.
Keras does not include by itself any means to export a TensorFlow graph as a protocol buffers file, but you can do it using regular TensorFlow utilities. Here is a blog post explaining how to do it using the utility script freeze_graph.py included in TensorFlow, which is the "typical" way it is done.
However, I personally find a nuisance having to make a checkpoint and then run an external script to obtain a model, and instead prefer to do it from my own Python code, so I use a function like this:
def freeze_session(session, keep_var_names=None, output_names=None, clear_devices=True):
"""
Freezes the state of a session into a pruned computation graph.
Creates a new computation graph where variable nodes are replaced by
constants taking their current value in the session. The new graph will be
pruned so subgraphs that are not necessary to compute the requested
outputs are removed.
@param session The TensorFlow session to be frozen.
@param keep_var_names A list of variable names that should not be frozen,
or None to freeze all the variables in the graph.
@param output_names Names of the relevant graph outputs.
@param clear_devices Remove the device directives from the graph for better portability.
@return The frozen graph definition.
"""
graph = session.graph
with graph.as_default():
freeze_var_names = list(set(v.op.name for v in tf.global_variables()).difference(keep_var_names or []))
output_names = output_names or []
output_names += [v.op.name for v in tf.global_variables()]
input_graph_def = graph.as_graph_def()
if clear_devices:
for node in input_graph_def.node:
node.device = ""
frozen_graph = tf.graph_util.convert_variables_to_constants(
session, input_graph_def, output_names, freeze_var_names)
return frozen_graphWhich is inspired in the implementation of freeze_graph.py. The parameters are similar to the script too. session is the TensorFlow session object. keep_var_names is only needed if you want to keep some variable not frozen (e.g. for stateful models), so generally not. output_names is a list with the names of the operations that produce the outputs that you want. clear_devices just removes any device directives to make the graph more portable. So, for a typical Keras model with one output, you would do something like:
from keras import backend as K
# Create, compile and train model...
frozen_graph = freeze_session(K.get_session(),
output_names=[out.op.name for out in model.outputs])Then you can write the graph to a file as usual with tf.train.write_graph:
tf.train.write_graph(frozen_graph, "some_directory", "my_model.pb", as_text=False)The freeze_session method works fine. But compared to saving to a checkpoint file then using the freeze_graph tool that comes with TensorFlow seems simpler to me, as it's easier to maintain. All you need to do is the following two steps:
First, add after your Keras code model.fit(...) and train your model:
from keras import backend as K
import tensorflow as tf
print(model.output.op.name)
saver = tf.train.Saver()
saver.save(K.get_session(), '/tmp/keras_model.ckpt')Then cd to your TensorFlow root directory, run:
python tensorflow/python/tools/freeze_graph.py \
--input_meta_graph=/tmp/keras_model.ckpt.meta \
--input_checkpoint=/tmp/keras_model.ckpt \
--output_graph=/tmp/keras_frozen.pb \
--output_node_names="<output_node_name_printed_in_step_1>" \
--input_binary=true
- 2I had to set K.set_learning_phase(0) before saving the checkpoint. Otherwise I faced the error
Keras error “You must feed a value for placeholder tensor 'keras_learning_phase' with dtype bool”while running it on android. I set 0 because I only need the model for inference. – Tahlil May 2 '18 at 6:58 - 3
The following simple example (XOR example) shows how to export Keras models (in both h5 format and pb format), and using the model in Python and C++:
train.py:
import numpy as np
import tensorflow as tf
def freeze_session(session, keep_var_names=None, output_names=None, clear_devices=True):
"""
Freezes the state of a session into a pruned computation graph.
Creates a new computation graph where variable nodes are replaced by
constants taking their current value in the session. The new graph will be
pruned so subgraphs that are not necessary to compute the requested
outputs are removed.
@param session The TensorFlow session to be frozen.
@param keep_var_names A list of variable names that should not be frozen,
or None to freeze all the variables in the graph.
@param output_names Names of the relevant graph outputs.
@param clear_devices Remove the device directives from the graph for better portability.
@return The frozen graph definition.
"""
graph = session.graph
with graph.as_default():
freeze_var_names = list(set(v.op.name for v in tf.global_variables()).difference(keep_var_names or []))
output_names = output_names or []
output_names += [v.op.name for v in tf.global_variables()]
input_graph_def = graph.as_graph_def()
if clear_devices:
for node in input_graph_def.node:
node.device = ''
frozen_graph = tf.graph_util.convert_variables_to_constants(
session, input_graph_def, output_names, freeze_var_names)
return frozen_graph
X = np.array([[0,0], [0,1], [1,0], [1,1]], 'float32')
Y = np.array([[0], [1], [1], [0]], 'float32')
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Dense(64, input_dim=2, activation='relu'))
model.add(tf.keras.layers.Dense(64, activation='relu'))
model.add(tf.keras.layers.Dense(64, activation='relu'))
model.add(tf.keras.layers.Dense(64, activation='relu'))
model.add(tf.keras.layers.Dense(1, activation='sigmoid'))
model.compile(loss='mean_squared_error', optimizer='adam', metrics=['binary_accuracy'])
model.fit(X, Y, batch_size=1, nb_epoch=100, verbose=0)
# inputs: ['dense_input']
print('inputs: ', [input.op.name for input in model.inputs])
# outputs: ['dense_4/Sigmoid']
print('outputs: ', [output.op.name for output in model.outputs])
model.save('./xor.h5')
frozen_graph = freeze_session(tf.keras.backend.get_session(), output_names=[out.op.name for out in model.outputs])
tf.train.write_graph(frozen_graph, './', 'xor.pbtxt', as_text=True)
tf.train.write_graph(frozen_graph, './', 'xor.pb', as_text=False)predict.py:
import numpy as np
import tensorflow as tf
model = tf.keras.models.load_model('./xor.h5')
# 0 ^ 0 = [[0.01974997]]
print('0 ^ 0 = ', model.predict(np.array([[0, 0]])))
# 0 ^ 1 = [[0.99141496]]
print('0 ^ 1 = ', model.predict(np.array([[0, 1]])))
# 1 ^ 0 = [[0.9897714]]
print('1 ^ 0 = ', model.predict(np.array([[1, 0]])))
# 1 ^ 1 = [[0.00406971]]
print('1 ^ 1 = ', model.predict(np.array([[1, 1]])))opencv-predict.py:
import numpy as np
import cv2 as cv
model = cv.dnn.readNetFromTensorflow('./xor.pb')
# 0 ^ 0 = [[0.01974997]]
model.setInput(np.array([[0, 0]]), name='dense_input')
print('0 ^ 0 = ', model.forward(outputName='dense_4/Sigmoid'))
# 0 ^ 1 = [[0.99141496]]
model.setInput(np.array([[0, 1]]), name='dense_input')
print('0 ^ 1 = ', model.forward(outputName='dense_4/Sigmoid'))
# 1 ^ 0 = [[0.9897714]]
model.setInput(np.array([[1, 0]]), name='dense_input')
print('1 ^ 0 = ', model.forward(outputName='dense_4/Sigmoid'))
# 1 ^ 1 = [[0.00406971]]
model.setInput(np.array([[1, 1]]), name='dense_input')
print('1 ^ 1 = ', model.forward(outputName='dense_4/Sigmoid'))predict.cpp:
#include <cstdlib>
#include <iostream>
#include <opencv2/opencv.hpp>
int main(int argc, char **argv)
{
cv::dnn::Net net;
net = cv::dnn::readNetFromTensorflow("./xor.pb");
// 0 ^ 0 = [0.018541215]
float x0[] = { 0, 0 };
net.setInput(cv::Mat(1, 2, CV_32F, x0), "dense_input");
std::cout << "0 ^ 0 = " << net.forward("dense_4/Sigmoid") << std::endl;
// 0 ^ 1 = [0.98295897]
float x1[] = { 0, 1 };
net.setInput(cv::Mat(1, 2, CV_32F, x1), "dense_input");
std::cout << "0 ^ 1 = " << net.forward("dense_4/Sigmoid") << std::endl;
// 1 ^ 0 = [0.98810625]
float x2[] = { 1, 0 };
net.setInput(cv::Mat(1, 2, CV_32F, x2), "dense_input");
std::cout << "1 ^ 0 = " << net.forward("dense_4/Sigmoid") << std::endl;
// 1 ^ 1 = [0.010002014]
float x3[] = { 1, 1 };
net.setInput(cv::Mat(1, 2, CV_32F, x3), "dense_input");
std::cout << "1 ^ 1 = " << net.forward("dense_4/Sigmoid") << std::endl;
return EXIT_SUCCESS;
}
- Thank you very much for a complete example. Could I ask you to include an additional sentence? If people use directly keras instead of tf.keras, they also need to use "keras.backend.get_session()" instead of "tf.keras.backend.get_session()" in the function call, otherwise you will get an error concerning uninitialized variables. I didn't realize you were using the prefix "tf.keras" before and that small difference cost me an hour... – gebbissimo Dec 5 '18 at 8:55
- This was very helpful to me. An alternative to opencv-predict.py that doesn't use cv2:
import tensorflow as tffrom tensorflow.python.platform import gfilef = gfile.FastGFile(r'.\xor\xor.pb', 'rb')graph_def = tf.GraphDef()graph_def.ParseFromString(f.read())f.close()tfSession = tf.InteractiveSession()tfSession.graph.as_default()tf.import_graph_def(graph_def)out = tfSession.graph.get_tensor_by_name('import/dense_4/Sigmoid:0')tfSession.run(out, {'import/dense_input:0': np.array([[0,0]])})– BitPusher16 Jul 2 at 4:46
There is a very important point when you want to convert to tensorflow. If you use dropout, batch normalization or any other layers like these (which have not trainable but calculating values), you should change the learning phase of keras backend. Here is a discussion about it.
import keras.backend as K
k.set_learning_phase(0) # 0 testing, 1 training mode
If you want the model only for inference, you should first freeze the graph and then write it as a .pbfile. The code snippet looks like this (code borrowed from here):
import tensorflow as tf
from tensorflow.python.framework import graph_util
from tensorflow.python.framework import graph_io
import keras
from keras import backend as K
sess = K.get_session()
constant_graph = graph_util.convert_variables_to_constants(
sess,
sess.graph.as_graph_def(),
["name_of_the_output_graph_node"])
graph_io.write_graph(constant_graph, "path/to/output/folder",
"output_model_name", as_text=False)You can do the above using the keras_to_tensorflow tool: https://github.com/amir-abdi/keras_to_tensorflow
The keras_to_tensorflow tool takes care of the above operations, with some extra features for a more diverse solution. Just call it with the correct input arguments (e.g. input_model and output_model flags).
If you want to retrain the model in tensorflow, use the above tool with the output_meta_ckpt flag to export checkpoints and meta graphs.
Please use tf.saved_model.simple_save, some example codes:
with tf.keras.backend.get_session() as sess:
tf.saved_model.simple_save(
sess,
export_path,
inputs={'input': keras_model.input},
outputs={'output': keras_model.output})===update====
You can use as_a_saved_model, example codes:
saved_model_path = tf.contrib.saved_model.save_keras_model(model, "./saved_models")
- 1
using estimator.export_savedmodel we can easily convert h5 model to saved model. check doc here https://www.tensorflow.org/api_docs/python/tf/estimator/Estimator
def prepare_image(image_str_tensor):
image_contents = tf.read_file(image_str_tensor)
image = tf.image.decode_jpeg(image_contents, channels=3)
image = tf.image.resize_images(image, [224, 224])
image = tf.cast(image, tf.float32)
return preprocess_input(image)
def serving_input_receiver_fn():
input_ph = tf.placeholder(tf.string, shape=[None])
images_tensor = tf.map_fn(
prepare_image, input_ph, back_prop=False, dtype=tf.float32)
images_tensor = tf.image.convert_image_dtype(images_tensor,
dtype=tf.float32)
return tf.estimator.export.ServingInputReceiver({"input": images_tensor},
{'image_url': input_ph})
estimator = tf.keras.estimator.model_to_estimator(
keras_model_path=h5_model_path
)
estimator.export_savedmodel(saved_model_path, serving_input_receiver_fn=serving_input_receiver_fn)
'Python Library > TensorFlow' 카테고리의 다른 글
| How To Convert Keras Model To .Pb format Example (0) | 2019.08.18 |
|---|---|
| Colab Tensorboard API (0) | 2019.08.18 |
| how to off Learning_phase for dropout and batch_norm when export .pb (0) | 2019.08.18 |
| How to Freeze Variables to Export keras model as .pb - 2 (0) | 2019.08.18 |
| tf.graph_util.convert_variables_to_constants 예제 (0) | 2019.08.14 |
convert_variables_to_constants(which "freezes" the variables and prunes the graph). – jdehesa Dec 7 '18 at 12:46