I am new to the machine learning concept, I am following a video from Udacity and I run into some problems.
I am trying to create a Transfer Learning model. When I try to 'fit' it it returns an error:
InvalidArgumentError: Graph execution error:
I don't know what I am doing wrong... I am following step by step (only changed some "outdated" code)
here is my code, if someone can help me solve this and explain a bit it'd be very helpful
!pip install -q -U "tensorflow-gpu==2.2.0"
!pip install -q -U tensorflow_hub
!pip install -q -U tensorflow_datasets
import time
import numpy as np
import matplotlib.pylab as plt
import tensorflow as tf
import tensorflow_hub as hub
import tensorflow_datasets as tfds
tfds.disable_progress_bar()
from tensorflow.keras import layers
#Here was supposed to be a split function to split the data 80% (train), 20% (validation), I don't know what I did but in the line below I did "split=['train[:80%]', 'train[20%:]']" is it ok? or should I change something there?
splits, info = tfds.load('cats_vs_dogs', with_info=True, as_supervised=True, split=['train[:80%]', 'train[20%:]'])
(train_examples, validation_examples) = splits
def format_image(image, label):
images = tf.image.resize(image, (IMAGE_RES, IMAGE_RES))//255.0
return image, label
num_examples = info.splits['train'].num_examples
BATCH_SIZE = 32
IMAGE_RES = 224
train_batches = train_examples.cache().shuffle(num_examples//4).map(format_image).batch(BATCH_SIZE).prefetch(1)
validation_batches = validation_examples.cache().map(format_image).batch(BATCH_SIZE).prefetch(1)
URL = "https://tfhub.dev/google/tf2-preview/mobilenet_v2/feature_vector/4"
feature_extractor = hub.KerasLayer(URL, input_shape=(IMAGE_RES,IMAGE_RES,3))
feature_extractor.trainable = False
model = tf.keras.Sequential([
feature_extractor,
layers.Dense(2, activation='softmax')
])
model.summary()
model.compile(
optimizer='adam',
loss=tf.losses.SparseCategoricalCrossentropy(),
metrics=['accuracy'])
EPOCHS = 2
history = model.fit(train_batches,
epochs=EPOCHS,
validation_data=validation_batches) #From here I get the problem
Related
I made a script in tensorflow 2.x but I had to downconvert it to tensorflow 1.x (tested in 1.14 and 1.15). However, the tf1 version performs very differently (10% accuracy lower on the test set). See also the plot for train and validation performance (diagram is attached below).
Looking at the operations needed for the migration from tf1 to tf2 it seems that only the Adam learning rate may be a problem but I'm defining it explicitly tensorflow migration
I've reproduced the same behavior both locally on GPU and CPU and on colab. The keras used was the one built-in in tensorflow (tf.keras). I've used the following functions (both for train,validation and test), using a sparse categorization (integers):
train_datagen = tf.keras.preprocessing.image.ImageDataGenerator(
horizontal_flip=horizontal_flip,
#rescale=None, #not needed for resnet50
preprocessing_function=None,
validation_split=None)
train_dataset = train_datagen.flow_from_directory(
directory=train_dir,
target_size=image_size,
class_mode='sparse',
batch_size=batch_size,
shuffle=True)
And the model is a simple resnet50 with a new layer on top:
IMG_SHAPE = img_size+(3,)
inputs = Input(shape=IMG_SHAPE, name='image_input',dtype = tf.uint8)
x = tf.cast(inputs, tf.float32)
# not working in this version of keras. inserted in imageGenerator
x = preprocess_input_resnet50(x)
base_model = tf.keras.applications.ResNet50(
include_top=False,
input_shape = IMG_SHAPE,
pooling=None,
weights='imagenet')
# Freeze the pretrained weights
base_model.trainable = False
x=base_model(x)
# Rebuild top
x = GlobalAveragePooling2D(data_format='channels_last',name="avg_pool")(x)
top_dropout_rate = 0.2
x = Dropout(top_dropout_rate, name="top_dropout")(x)
outputs = Dense(num_classes,activation="softmax", name="pred_out")(x)
model = Model(inputs=inputs, outputs=outputs,name="ResNet50_comp")
optimizer = tf.keras.optimizers.Adam(lr=learning_rate)
model.compile(optimizer=optimizer,
loss="sparse_categorical_crossentropy",
metrics=['accuracy'])
And then I'm calling the fit function:
history = model.fit_generator(train_dataset,
steps_per_epoch=n_train_batches,
validation_data=validation_dataset,
validation_steps=n_val_batches,
epochs=initial_epochs,
verbose=1,
callbacks=[stopping])
I've reproduced the same behavior for example with the following full script (applied to my dataset and changed to adam and removed intermediate final dense layer):
deep learning sandbox
The easiest way to replicate this behavior was to enable or disable the following line on a tf2 environment with the same script and add the following line to it. However, I've tested also on tf1 environments (1.14 and 1.15):
tf.compat.v1.disable_v2_behavior()
Sadly I cannot provide the dataset.
Update 26/11/2020
For full reproducibility I've obtained a similar behaviour by means of the food101 (101 categories) dataset enabling tf1 behaviour with 'tf.compat.v1.disable_v2_behavior()'. The following is the script executed with tensorflow-gpu 2.2.0:
#%% ref https://medium.com/deeplearningsandbox/how-to-use-transfer-learning-and-fine-tuning-in-keras-and-tensorflow-to-build-an-image-recognition-94b0b02444f2
import os
import sys
import glob
import argparse
import matplotlib.pyplot as plt
import tensorflow as tf
# enable and disable this to obtain tf1 behaviour
tf.compat.v1.disable_v2_behavior()
from tensorflow.keras import __version__
from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D
from tensorflow.keras.optimizers import Adam
# since i'm using resnet50 weights from imagenet, i'm using food101 for
# similar but different categorization tasks
# pip install tensorflow-datasets if tensorflow_dataset not found
import tensorflow_datasets as tfds
(train_ds,validation_ds),info= tfds.load('food101', split=['train','validation'], shuffle_files=True, with_info=True)
assert isinstance(train_ds, tf.data.Dataset)
print(train_ds)
#%%
IM_WIDTH, IM_HEIGHT = 224, 224
NB_EPOCHS = 10
BAT_SIZE = 32
def get_nb_files(directory):
"""Get number of files by searching directory recursively"""
if not os.path.exists(directory):
return 0
cnt = 0
for r, dirs, files in os.walk(directory):
for dr in dirs:
cnt += len(glob.glob(os.path.join(r, dr + "/*")))
return cnt
def setup_to_transfer_learn(model, base_model):
"""Freeze all layers and compile the model"""
for layer in base_model.layers:
layer.trainable = False
model.compile(optimizer='rmsprop', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
def add_new_last_layer(base_model, nb_classes):
"""Add last layer to the convnet
Args:
base_model: keras model excluding top
nb_classes: # of classes
Returns:
new keras model with last layer
"""
x = base_model.output
x = GlobalAveragePooling2D()(x)
#x = Dense(FC_SIZE, activation='relu')(x) #new FC layer, random init
predictions = Dense(nb_classes, activation='softmax')(x) #new softmax layer
model = Model(inputs=base_model.input, outputs=predictions)
return model
def train(nb_epoch, batch_size):
"""Use transfer learning and fine-tuning to train a network on a new dataset"""
#nb_train_samples = train_ds.cardinality().numpy()
nb_train_samples=info.splits['train'].num_examples
nb_classes = info.features['label'].num_classes
classes_names = info.features['label'].names
#nb_val_samples = validation_ds.cardinality().numpy()
nb_val_samples = info.splits['validation'].num_examples
#nb_epoch = int(args.nb_epoch)
#batch_size = int(args.batch_size)
def preprocess(features):
#print(features['image'], features['label'])
image = tf.image.resize(features['image'], [224,224])
#image = tf.divide(image, 255)
#print(image)
# data augmentation
image=tf.image.random_flip_left_right(image)
image = preprocess_input(image)
label = features['label']
# for categorical crossentropy
#label = tf.one_hot(label,101,axis=-1)
#return image, tf.cast(label, tf.float32)
return image, label
#pre-processing the dataset to fit a specific image size and 2D labelling
train_generator = train_ds.map(preprocess).batch(batch_size).repeat()
validation_generator = validation_ds.map(preprocess).batch(batch_size).repeat()
#train_generator=train_ds
#validation_generator=validation_ds
#fig = tfds.show_examples(validation_generator, info)
# setup model
base_model = ResNet50(weights='imagenet', include_top=False) #include_top=False excludes final FC layer
model = add_new_last_layer(base_model, nb_classes)
# transfer learning
setup_to_transfer_learn(model, base_model)
history = model.fit(
train_generator,
epochs=nb_epoch,
steps_per_epoch=nb_train_samples//BAT_SIZE,
validation_data=validation_generator,
validation_steps=nb_val_samples//BAT_SIZE)
#class_weight='auto')
#execute
history = train(nb_epoch=NB_EPOCHS, batch_size=BAT_SIZE)
And the performance on food101 dataset:
update 27/11/2020
It's possible to see the discrepancy also in the way smaller oxford_flowers102 dataset:
(train_ds,validation_ds,test_ds),info= tfds.load('oxford_flowers102', split=['train','validation','test'], shuffle_files=True, with_info=True)
Nb: the above plot shows confidences given by running the same training multiple times and evaluatind mean and std to check for the effects on random weights initialization and data augmentation.
Moreover I've tried some hyperparameter tuning on tf2 resulting in the following picture:
changing optimizer (adam and rmsprop)
not applying horizontal flipping aumgentation
deactivating keras resnet50 preprocess_input
Thanks in advance for every suggestion. Here are the accuracy and validation performance on tf1 and tf2 on my dataset:
Update 14/12/2020
I'm sharing the colab for reproducibility on oxford_flowers at the clic of a button:
colab script
I came across something similar, when doing the opposite migration (from TF1+Keras to TF2).
Running this code below:
# using TF2
import numpy as np
from tensorflow.keras.applications.resnet50 import ResNet50
fe = ResNet50(include_top=False, pooling="avg")
out = fe.predict(np.ones((1,224,224,3))).flatten()
sum(out)
>>> 212.3205274187726
# using TF1+Keras
import numpy as np
from keras.applications.resnet50 import ResNet50
fe = ResNet50(include_top=False, pooling="avg")
out = fe.predict(np.ones((1,224,224,3))).flatten()
sum(out)
>>> 187.23898954353717
you can see the same model from the same library on different versions does not return the same value (using sum as a quick check-up). I found the answer to this mysterious behavior in this other SO answer: ResNet model in keras and tf.keras give different output for the same image
Another recommendation I'd give you is, try using pooling from inside applications.resnet50.ResNet50 class, instead of the additional layer in your function, for simplicity, and to remove possible problem-generators :)
I have a simple code to run on Google Colab (I use CPU mode):
import numpy as np
import pandas as pd
## LOAD DATASET
datatrain = pd.read_csv("gdrive/My Drive/iris_train.csv").values
xtrain = datatrain[:,:-1]
ytrain = datatrain[:,-1]
datatest = pd.read_csv("gdrive/My Drive/iris_test.csv").values
xtest = datatest[:,:-1]
ytest = datatest[:,-1]
import tensorflow as tf
from tensorflow.keras.layers import Dense, Activation
from tensorflow.keras.utils import to_categorical
## SET ALL SEED
import os
os.environ['PYTHONHASHSEED']=str(66)
import random
random.seed(66)
np.random.seed(66)
tf.set_random_seed(66)
from tensorflow.keras import backend as K
session_conf = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1)
sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)
K.set_session(sess)
## MAIN PROGRAM
ycat = to_categorical(ytrain)
# build model
model = tf.keras.Sequential()
model.add(Dense(10, input_shape=(4,)))
model.add(Activation("sigmoid"))
model.add(Dense(3))
model.add(Activation("softmax"))
#choose optimizer and loss function
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
# train
model.fit(xtrain, ycat, epochs=15, batch_size=32)
#get prediction
classes = model.predict_classes(xtest)
#get accuration
accuration = np.sum(classes == ytest)/len(ytest) * 100
I have read the setup to create a reproducibility code here Reproducible results using Keras with TensorFlow backend and I put all code in the same cell. But the result (e.g. the loss) is always different every time I run that cell (run the cell using shift + enter).
In my case, the result from the code above can be reproduced, if only:
I run using "runtime" > "restart and run all" or,
I put that code in a single file and run it using the command line (python3 file.py)
is there something I miss to make the result reproducible without restart the runtime?
You should also fix the seed for kernel_initializer in your Dense layers. So, your model will be like:
model = tf.keras.Sequential()
model.add(Dense(10, kernel_initializer=keras.initializers.glorot_uniform(seed=66), input_shape=(4,)))
model.add(Activation("sigmoid"))
model.add(Dense(3, kernel_initializer=keras.initializers.glorot_uniform(seed=66)))
model.add(Activation("softmax"))
I tried most of the solutions on the web and just the following codes worked for me :
seed=0
import os
os.environ['PYTHONHASHSEED'] = str(seed)
# For working on GPUs from "TensorFlow Determinism"
os.environ["TF_DETERMINISTIC_OPS"] = str(seed)
import numpy as np
np.random.seed(seed)
import random
random.seed(seed)
import tensorflow as tf
tf.random.set_seed(seed)
note that you should call this code before every run(at least for me)
if you want run your code on CPU:
seed=0
import os
os.environ['PYTHONHASHSEED'] = str(seed)
# For working on GPUs from "TensorFlow Determinism"
os.environ['CUDA_VISBLE_DEVICE'] = ''
import numpy as np
np.random.seed(seed)
import random
random.seed(seed)
import tensorflow as tf
tf.random.set_seed(seed)
I've tried to get Tensorflow 2.0 working reproducibly using Keras and Google Colab (CPU), with a version of the Iris dataset processing similar to that described above by #malioboro. This seems to work - might be useful:
# Install TensorFlow
try:
# %tensorflow_version only exists in Colab.
%tensorflow_version 2.x
except Exception:
pass
# Setup repro section from Keras FAQ with TF1 to TF2 adjustments
import numpy as np
import tensorflow as tf
import random as rn
# The below is necessary for starting Numpy generated random numbers
# in a well-defined initial state.
np.random.seed(42)
# The below is necessary for starting core Python generated random numbers
# in a well-defined state.
rn.seed(12345)
# Force TensorFlow to use single thread.
# Multiple threads are a potential source of non-reproducible results.
# For further details, see: https://stackoverflow.com/questions/42022950/
session_conf = tf.compat.v1.ConfigProto(intra_op_parallelism_threads=1,
inter_op_parallelism_threads=1)
# The below tf.set_random_seed() will make random number generation
# in the TensorFlow backend have a well-defined initial state.
# For further details, see:
# https://www.tensorflow.org/api_docs/python/tf/set_random_seed
tf.compat.v1.set_random_seed(1234)
sess = tf.compat.v1.Session(graph=tf.compat.v1.get_default_graph(), config=session_conf)
tf.compat.v1.keras.backend.set_session(sess)
# Rest of code follows ...
# Some adopted from: https://janakiev.com/notebooks/keras-iris/
# Some adopted from the question.
#
# Load Data
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder, StandardScaler
iris = load_iris()
X = iris['data']
y = iris['target']
names = iris['target_names']
feature_names = iris['feature_names']
# One hot encoding
enc = OneHotEncoder()
Y = enc.fit_transform(y[:, np.newaxis]).toarray()
# Scale data to have mean 0 and variance 1
# which is importance for convergence of the neural network
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
# Split the data set into training and testing
X_train, X_test, Y_train, Y_test = train_test_split(
X_scaled, Y, test_size=0.5, random_state=2)
n_features = X.shape[1]
n_classes = Y.shape[1]
## MAIN PROGRAM
from tensorflow.keras.layers import Dense, Activation
# build model
model = tf.keras.Sequential()
model.add(Dense(10, input_shape=(4,)))
model.add(Activation("sigmoid"))
model.add(Dense(3))
model.add(Activation("softmax"))
#choose optimizer and loss function
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
# train
model.fit(X_train, Y_train, epochs=20, batch_size=32)
#get prediction
classes = model.predict_classes(X_test)
Follwing the tutorial at https://www.tensorflow.org/tutorials/images/hub_with_keras resulted in a file model.h5. Converting to tensorflow-js with the command
tensorflowjs_converter --input_format keras ./model.h5 /tmp/jsmodel/
failed with
Exception: Error dumping weights, duplicate weight name Variable
Why is this and how can it be fixed?
MCVE
from __future__ import absolute_import, division, print_function
import tensorflow as tf
import tensorflow_hub as hub
from tensorflow.keras import layers
import numpy as np
data_root = tf.keras.utils.get_file(
'flower_photos','https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz',
untar=True)
image_generator = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1/255)
IMAGE_SHAPE = (224, 224)
image_data = image_generator.flow_from_directory(str(data_root), target_size=IMAGE_SHAPE)
feature_extractor_url = "https://tfhub.dev/google/tf2-preview/mobilenet_v2/feature_vector/2" ##param {type:"string"}
feature_extractor_layer = hub.KerasLayer(feature_extractor_url,
input_shape=(224,224,3))
for image_batch, label_batch in image_data:
print("Image batch shape: ", image_batch.shape)
print("Labe batch shape: ", label_batch.shape)
break
feature_extractor_layer.trainable = False
model = tf.keras.Sequential([
feature_extractor_layer,
layers.Dense(image_data.num_classes, activation='softmax')
])
model.compile(
optimizer=tf.keras.optimizers.Adam(),
loss='categorical_crossentropy',
metrics=['acc'])
steps_per_epoch = np.ceil(image_data.samples/image_data.batch_size)
history = model.fit(image_data, epochs=2,
steps_per_epoch=steps_per_epoch) # removed callback
model.save("/tmp/so_model.h5")
This fails with a
RuntimeError: Unable to create link (name already exists)
but the model is created. Calling the above tensorflowjs_converter --input_format keras /tmp/model.h5 /tmp/jsmodel fails with the above
Exception: Error dumping weights, duplicate weight name Variable
UPDATE: see also Retrain image detection with MobileNet
Right now we are successfully able to serve models using Tensorflow Serving. We have used following method to export the model and host it with Tensorflow Serving.
------------
For exporting
------------------
from tensorflow.contrib.session_bundle import exporter
K.set_learning_phase(0)
export_path = ... # where to save the exported graph
export_version = ... # version number (integer)
saver = tf.train.Saver(sharded=True)
model_exporter = exporter.Exporter(saver)
signature = exporter.classification_signature(input_tensor=model.input,
scores_tensor=model.output)
model_exporter.init(sess.graph.as_graph_def(),
default_graph_signature=signature)
model_exporter.export(export_path, tf.constant(export_version), sess)
--------------------------------------
For hosting
-----------------------------------------------
bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server --port=9000 --model_name=default --model_base_path=/serving/models
However our issue is - we want keras to be integrated with Tensorflow serving. We would like to serve the model through Tensorflow serving using Keras.
The reason we would like to have that is because - in our architecture we follow couple of different ways to train our model like deeplearning4j + Keras ,
Tensorflow + Keras, but for serving we would like to use only one servable engine that's Tensorflow Serving. We don't see any straight forward way to achieve that. Any comments ?
Thank you.
Very recently TensorFlow changed the way it exports the model, so the majority of the tutorials available on web are outdated. I honestly don't know how deeplearning4j works, but I use Keras quite often. I managed to create a simple example that I already posted on this issue in TensorFlow Serving Github.
I'm not sure whether this will help you, but I'd like to share how I did and maybe it will give you some insights. My first trial prior to creating my custom model was to use a trained model available on Keras such as VGG19. I did this as follows.
Model creation
import keras.backend as K
from keras.applications import VGG19
from keras.models import Model
# very important to do this as a first thing
K.set_learning_phase(0)
model = VGG19(include_top=True, weights='imagenet')
# The creation of a new model might be optional depending on the goal
config = model.get_config()
weights = model.get_weights()
new_model = Model.from_config(config)
new_model.set_weights(weights)
Exporting the model
from tensorflow.python.saved_model import builder as saved_model_builder
from tensorflow.python.saved_model import utils
from tensorflow.python.saved_model import tag_constants, signature_constants
from tensorflow.python.saved_model.signature_def_utils_impl import build_signature_def, predict_signature_def
from tensorflow.contrib.session_bundle import exporter
export_path = 'folder_to_export'
builder = saved_model_builder.SavedModelBuilder(export_path)
signature = predict_signature_def(inputs={'images': new_model.input},
outputs={'scores': new_model.output})
with K.get_session() as sess:
builder.add_meta_graph_and_variables(sess=sess,
tags=[tag_constants.SERVING],
signature_def_map={'predict': signature})
builder.save()
Some side notes
It can vary depending on Keras, TensorFlow, and TensorFlow Serving
version. I used the latest ones.
Beware of the names of the signatures, since they should be used in the client as well.
When creating the client, all preprocessing steps that are needed for the
model (preprocess_input() for example) must be executed. I didn't try
to add such step in the graph itself as Inception client example.
With respect to serving different models within the same server, I think that something similar to the creation of a model_config_file might help you. To do so, you can create a config file similar to this:
model_config_list: {
config: {
name: "my_model_1",
base_path: "/tmp/model_1",
model_platform: "tensorflow"
},
config: {
name: "my_model_2",
base_path: "/tmp/model_2",
model_platform: "tensorflow"
}
}
Finally, you can run the client like this:
bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server --port=9000 --config_file=model_config.conf
try this script i wrote, you can convert keras models into tensorflow frozen graphs, ( i saw that some models give rise to strange behaviours when you export them without freezing the variables).
import sys
from keras.models import load_model
import tensorflow as tf
from keras import backend as K
from tensorflow.python.framework import graph_util
from tensorflow.python.framework import graph_io
from tensorflow.python.saved_model import signature_constants
from tensorflow.python.saved_model import tag_constants
K.set_learning_phase(0)
K.set_image_data_format('channels_last')
INPUT_MODEL = sys.argv[1]
NUMBER_OF_OUTPUTS = 1
OUTPUT_NODE_PREFIX = 'output_node'
OUTPUT_FOLDER= 'frozen'
OUTPUT_GRAPH = 'frozen_model.pb'
OUTPUT_SERVABLE_FOLDER = sys.argv[2]
INPUT_TENSOR = sys.argv[3]
try:
model = load_model(INPUT_MODEL)
except ValueError as err:
print('Please check the input saved model file')
raise err
output = [None]*NUMBER_OF_OUTPUTS
output_node_names = [None]*NUMBER_OF_OUTPUTS
for i in range(NUMBER_OF_OUTPUTS):
output_node_names[i] = OUTPUT_NODE_PREFIX+str(i)
output[i] = tf.identity(model.outputs[i], name=output_node_names[i])
print('Output Tensor names: ', output_node_names)
sess = K.get_session()
try:
frozen_graph = graph_util.convert_variables_to_constants(sess, sess.graph.as_graph_def(), output_node_names)
graph_io.write_graph(frozen_graph, OUTPUT_FOLDER, OUTPUT_GRAPH, as_text=False)
print(f'Frozen graph ready for inference/serving at {OUTPUT_FOLDER}/{OUTPUT_GRAPH}')
except:
print('Error Occured')
builder = tf.saved_model.builder.SavedModelBuilder(OUTPUT_SERVABLE_FOLDER)
with tf.gfile.GFile(f'{OUTPUT_FOLDER}/{OUTPUT_GRAPH}', "rb") as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
sigs = {}
OUTPUT_TENSOR = output_node_names
with tf.Session(graph=tf.Graph()) as sess:
tf.import_graph_def(graph_def, name="")
g = tf.get_default_graph()
inp = g.get_tensor_by_name(INPUT_TENSOR)
out = g.get_tensor_by_name(OUTPUT_TENSOR[0] + ':0')
sigs[signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY] = \
tf.saved_model.signature_def_utils.predict_signature_def(
{"input": inp}, {"outout": out})
builder.add_meta_graph_and_variables(sess,
[tag_constants.SERVING],
signature_def_map=sigs)
try:
builder.save()
print(f'Model ready for deployment at {OUTPUT_SERVABLE_FOLDER}/saved_model.pb')
print('Prediction signature : ')
print(sigs['serving_default'])
except:
print('Error Occured, please checked frozen graph')
I have recently added this blogpost that explain how to save a Keras model and serve it with Tensorflow Serving.
TL;DR:
Saving an Inception3 pretrained model:
### Load a pretrained inception_v3
inception_model = keras.applications.inception_v3.InceptionV3(weights='imagenet')
# Define a destination path for the model
MODEL_EXPORT_DIR = '/tmp/inception_v3'
MODEL_VERSION = 1
MODEL_EXPORT_PATH = os.path.join(MODEL_EXPORT_DIR, str(MODEL_VERSION))
# We'll need to create an input mapping, and name each of the input tensors.
# In the inception_v3 Keras model, there is only a single input and we'll name it 'image'
input_names = ['image']
name_to_input = {name: t_input for name, t_input in zip(input_names, inception_model.inputs)}
# Save the model to the MODEL_EXPORT_PATH
# Note using 'name_to_input' mapping, the names defined here will also be used for querying the service later
tf.saved_model.simple_save(
keras.backend.get_session(),
MODEL_EXPORT_PATH,
inputs=name_to_input,
outputs={t.name: t for t in inception_model.outputs})
And then starting a TF serving Docker:
Copy the saved model to the hosts' specified directory. (source=/tmp/inception_v3 in this example)
Run the docker:
docker run -d -p 8501:8501 --name keras_inception_v3 --mount type=bind,source=/tmp/inception_v3,target=/models/inception_v3 -e MODEL_NAME=inception_v3 -t tensorflow/serving
Verify that there's network access to the Tensorflow service. In order to get the local docker ip (172.*.*.*) for testing run:
docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' keras_inception_v3
I'm trying to do a small test with my dataset on Keras Regressor (using TensorFlow), but I'm having a small issue. The error seems to be on the function cross_val_score from scikit. It starts on it and the last error message is:
File "/usr/local/lib/python2.7/dist-packages/Keras-2.0.2-py2.7.egg/keras/backend/tensorflow_backend.py", line 298, in _initialize_variables
variables = tf.global_variables()
AttributeError: 'module' object has no attribute 'global_variables'
My full code is basically the example found in http://machinelearningmastery.com/regression-tutorial-keras-deep-learning-library-python/ with small changes.
I've looked upon the " 'module' object has no attribute 'global_variables' " error and it seems to be about the Tensorflow version, but I'm using the most recent one (1.0) and there is no function in the code that works directly with tf that I can change. Below is my full code, is there anyway i can change it so it works? Thanks for the help
import numpy
import pandas
import sys
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.datasets import load_svmlight_file
# define base mode
def baseline_model():
# create model
model = Sequential()
model.add(Dense(68, activation="relu", kernel_initializer="normal", input_dim=68))
model.add(Dense(1, kernel_initializer="normal"))
# Compile model
model.compile(loss='mean_squared_error', optimizer='adam')
return model
X, y, query_id = load_svmlight_file(str(sys.argv[1]), query_id=True)
scaler = StandardScaler()
X = scaler.fit_transform(X.toarray())
# fix random seed for reproducibility
seed = 1
numpy.random.seed(seed)
# evaluate model with standardized dataset
estimator = KerasRegressor(build_fn=baseline_model, nb_epoch=100, batch_size=5, verbose=0)
kfold = KFold(n_splits=5, random_state=seed)
results = cross_val_score(estimator, X, y, cv=kfold)
print("Results: %.2f (%.2f) MSE" % (results.mean(), results.std()))
You are probably using an older Tensorflow version install tensorflow 1.2.0rc2 and you should be fine.