如何使用estimator.export_savedmode() 保存 TensorFlow模型？
特别是，我应该把什么放在serving_input_receiver_fn()里面？
我已经创建了一个基于VGGNet架构的自定义估算器，我正在使用自己的图像并在图像上进行一些转换（您可以在_parse_function()中看到它们）。
我已阅读文档here，但我完全不确定要为我的代码编写什么（请参阅下文）。最终我想保存模型并使用TensorFlow服务。
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow as tf
import numpy as np
from sklearn.model_selection import train_test_split
import os
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import scipy
from scipy import ndimage
import scipy.misc
tf.logging.set_verbosity(tf.logging.INFO)
def cnn_model_fn(features, labels, mode):
"""Model function for CNN."""
# Input Layer
input_layer = tf.reshape(features, [-1, 224, 224, 3])
# Convolutional Layer #1
conv1 = tf.layers.conv2d(
inputs=input_layer,
filters=64,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #2
conv2 = tf.layers.conv2d(
inputs=conv1,
filters=64,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Pooling Layer #1
pool1 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)
# Convolutional Layer #3
conv3 = tf.layers.conv2d(
inputs=pool1,
filters=128,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #4
conv4 = tf.layers.conv2d(
inputs=conv3,
filters=128,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
pool2 = tf.layers.max_pooling2d(inputs=conv4, pool_size=[2, 2], strides=2)
# Convolutional Layer #5
conv5 = tf.layers.conv2d(
inputs=pool2,
filters=256,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #6
conv6 = tf.layers.conv2d(
inputs=conv5,
filters=256,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #7
conv7 = tf.layers.conv2d(
inputs=conv6,
filters=256,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
pool3 = tf.layers.max_pooling2d(inputs=conv7, pool_size=[2, 2], strides=2)
# Convolutional Layer #8
conv8 = tf.layers.conv2d(
inputs=pool3,
filters=512,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #9
conv9 = tf.layers.conv2d(
inputs=conv8,
filters=512,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #10
conv10 = tf.layers.conv2d(
inputs=conv9,
filters=512,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
pool4 = tf.layers.max_pooling2d(inputs=conv10, pool_size=[2, 2], strides=2)
# Convolutional Layer #11
conv11 = tf.layers.conv2d(
inputs=pool4,
filters=512,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #12
conv12 = tf.layers.conv2d(
inputs=conv11,
filters=512,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #12
conv13 = tf.layers.conv2d(
inputs=conv12,
filters=512,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
pool5 = tf.layers.max_pooling2d(inputs=conv13, pool_size=[2, 2], strides=2)
# Dense Layer
pool5_flat = tf.reshape(pool5, [-1, 7 * 7 * 512])
dense1 = tf.layers.dense(inputs=pool5_flat, units=4096, activation=tf.nn.relu)
dense2 = tf.layers.dense(inputs=dense1, units=4096, activation=tf.nn.relu)
dense3 = tf.layers.dense(inputs=dense2, units=1024, activation=tf.nn.relu)
dropout = tf.layers.dropout(
inputs=dense3, rate=0.001, training=mode == tf.estimator.ModeKeys.TRAIN)
logits1 = tf.layers.dense(inputs=dropout, units=2)
logits2 = tf.layers.dense(inputs=dropout, units=4)
predictions = {
"classes1": tf.argmax(input=logits1, axis=1),
"classes2": tf.argmax(input=logits2, axis=1),
"probabilities1": tf.nn.softmax(logits1, name="softmax_tensor_1"),
"probabilities2": tf.nn.softmax(logits2, name="softmax_tensor_2")
}
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)
# Calculate Loss (for both TRAIN and EVAL modes)
loss1 = tf.losses.sparse_softmax_cross_entropy(labels=labels[:,0], logits=logits1)
loss2 = tf.losses.sparse_softmax_cross_entropy(labels=labels[:,1], logits=logits2)
loss = loss1 + loss2
# Configure the Training Op (for TRAIN mode)
if mode == tf.estimator.ModeKeys.TRAIN:
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01)
train_op = optimizer.minimize(
loss=loss,
global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)
# Add evaluation metrics (for EVAL mode)
eval_metric_ops = {
"accuracy1": tf.metrics.accuracy(
labels=labels[:,0], predictions=predictions["classes1"]),
"accuracy2": tf.metrics.accuracy(
labels=labels[:,1], predictions=predictions["classes2"]),
"precision1": tf.metrics.precision(labels=labels[:,0], predictions=predictions["classes1"]),
"precision2": tf.metrics.precision(labels=labels[:,1], predictions=predictions["classes2"]),
"recall1": tf.metrics.recall(labels=labels[:,0], predictions=predictions["classes1"]),
"recall2": tf.metrics.recall(labels=labels[:,1], predictions=predictions["classes2"])
}
return tf.estimator.EstimatorSpec(
mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
def _parse_function(filename, label):
image_string = tf.read_file(filename)
image_decoded = tf.image.decode_image(image_string)
image_typecasted = tf.cast(image_decoded, tf.float32)
image_reshaped = tf.reshape(image_typecasted, [-1, 224, 224, 3])
return image_reshaped, label
def _parse_function(filename):
image_string = tf.read_file(filename)
image_decoded = tf.image.decode_image(image_string)
image_typecasted = tf.cast(image_decoded, tf.float32)
image_reshaped = tf.reshape(image_typecasted, [-1, 224, 224, 3])
return image_reshaped
def stratified_train_test_split_():
filenamelist = []
labelslist = []
DIRECTORY = 'path_to'
for filename in os.listdir(DIRECTORY):
fullfilename = DIRECTORY + filename
if filename.endswith('.back.0.jpg'):
#back image, original orientation
filenamelist.append(fullfilename)
temp = [0,0]
labelslist.append(temp)
elif filename.endswith('.back.90.jpg'):
#back image, rotated clockwise 90
filenamelist.append(fullfilename)
temp = [0,1]
labelslist.append(temp)
elif filename.endswith('.back.180.jpg'):
#back image, rotated clockwise 180
filenamelist.append(fullfilename)
temp = [0,2]
labelslist.append(temp)
elif filename.endswith('.back.270.jpg'):
#back image, rotated clockwise 270
filenamelist.append(fullfilename)
temp = [0,3]
labelslist.append(temp)
elif filename.endswith('.front.0.jpg'):
#front image, rotated clockwise 0
filenamelist.append(fullfilename)
temp = [1,0]
labelslist.append(temp)
elif filename.endswith('.front.90.jpg'):
#front image, rotated clockwise 90
filenamelist.append(fullfilename)
temp = [1,1]
labelslist.append(temp)
elif filename.endswith('.front.180.jpg'):
#front image, rotated clockwise 180
filenamelist.append(fullfilename)
temp = [1,2]
labelslist.append(temp)
elif filename.endswith('.front.270.jpg'):
#front image, rotated clockwise 270
filenamelist.append(fullfilename)
temp = [1,3]
labelslist.append(temp)
X_train, X_test, y_train, y_test = train_test_split(filenamelist, labelslist, test_size=0.20, random_state=42, shuffle=True, stratify=labelslist)
return X_train, X_test, y_train, y_test
def my_input_fn_train(X_train, y_train):
filenames = tf.constant(X_train)
labels = tf.constant(y_train)
dataset = tf.data.Dataset.from_tensor_slices((filenames, labels))
dataset = dataset.map(_parse_function)
# # Shuffle, repeat, and batch the examples.
dataset = dataset.shuffle(5000).repeat().batch(64)
# # Build the Iterator, and return the read end of the pipeline.
return dataset.make_one_shot_iterator().get_next()
def my_input_fn_test(X_test, y_test):
filenames = tf.constant(X_test)
labels = tf.constant(y_test)
dataset = tf.data.Dataset.from_tensor_slices((filenames, labels))
dataset = dataset.map(_parse_function)
# # Shuffle, repeat, and batch the examples.
dataset = dataset.shuffle(5000).repeat(1).batch(64)
# # Build the Iterator, and return the read end of the pipeline.
return dataset.make_one_shot_iterator().get_next()
def my_input_fn_predict(filename):
filenames = tf.constant(filename)
dataset = tf.data.Dataset.from_tensors((filenames))
dataset = dataset.map(_parse_function)
return dataset.make_one_shot_iterator().get_next()
def main(unused_argv):
# Create the Estimator
mnist_classifier = tf.estimator.Estimator(
model_fn=cnn_model_fn,
model_dir="path_to_model_directory",
config = tf.estimator.RunConfig( save_checkpoints_steps=None, save_checkpoints_secs=600, save_summary_steps=5))
# Set up logging for predictions
tensors_to_log_1 = {"probabilities1": "softmax_tensor_1"}
tensors_to_log_2 = {"probabilities2": "softmax_tensor_2"}
logging_hook_1 = tf.train.LoggingTensorHook(
tensors=tensors_to_log_1, every_n_iter=100)
logging_hook_2 = tf.train.LoggingTensorHook(
tensors=tensors_to_log_2, every_n_iter=100)
#Splitting the train test split seperately
X_train, X_test, y_train, y_test = stratified_train_test_split_()
#Removed the training, testing and prediction calls.
#Code for exporting the models using
def serving_input_receiver_fn():
#????
mnist_classifier.export_savedmodel(export_dir_base, serving_input_fn)
if __name__ == "__main__":
tf.app.run()
答案 0 :(得分：0)
是的，export_savedmode()就是您所需要的。
serving_input_receiver_fn应返回ServingInputReceiver，其中第一个参数指定要传递给模型的要素，第二个参数用于输入节点，此接收器希望默认情况下输入（引用文档）。
在你的情况下，它看起来像这样：
def serving_input_fn():
serialized_tf_example = tf.placeholder(dtype=tf.string, shape=None,
name='input_example_tensor')
receiver_tensors = {'examples': serialized_tf_example}
features = tf.parse_example(serialized_tf_example, tf.placeholder(tf.float32, [None, 224, 224]))
return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)
我建议您查看this thread中的答案，并使用this和this示例作为参考。
最后但并非最不重要的是，考虑使用Keras进行POC。
答案 1 :(得分：0)
这是上述问题的答案，我能够解决所以我正在为需要它的人发布答案..
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow as tf
import numpy as np
from sklearn.model_selection import train_test_split
import os
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import scipy
from scipy import ndimage
import scipy.misc
tf.logging.set_verbosity(tf.logging.INFO)
# Our application logic will be added here
def cnn_model_fn(features, labels, mode):
"""Model function for CNN."""
#tf.print("shape of features",features.shape)
#print("type of feature ", type(features))
#Added this for solving the issue
features = features["feature"]
features = tf.Print(features, [tf.shape(features), "shape of features before second reshape"], summarize=10)
#tf.print("shape of labels ", labels.shape)
# Input Layer
input_layer = tf.reshape(features, [-1, 224, 224, 3])
#print(type(input_layer))
input_layer = tf.Print(input_layer, [tf.shape(input_layer), "shape of input_layer after second reshape"], summarize=10)
#print("Successfully performed reshape operation")
# Convolutional Layer #1
conv1 = tf.layers.conv2d(
inputs=input_layer,
filters=64,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #2
conv2 = tf.layers.conv2d(
inputs=conv1,
filters=64,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
#print("output of convolutional layer 1 : ",type(conv1))
# Pooling Layer #1
pool1 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)
#print(" Successfully done with 1st layer and shape is : ", pool1.shape)
# Convolutional Layer #3
conv3 = tf.layers.conv2d(
inputs=pool1,
filters=128,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #4
conv4 = tf.layers.conv2d(
inputs=conv3,
filters=128,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
pool2 = tf.layers.max_pooling2d(inputs=conv4, pool_size=[2, 2], strides=2)
#print(" Successfully done with 2nd layer and shape is : ", pool2.shape)
# Convolutional Layer #5
conv5 = tf.layers.conv2d(
inputs=pool2,
filters=256,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #6
conv6 = tf.layers.conv2d(
inputs=conv5,
filters=256,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #7
conv7 = tf.layers.conv2d(
inputs=conv6,
filters=256,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
pool3 = tf.layers.max_pooling2d(inputs=conv7, pool_size=[2, 2], strides=2)
#print(" Successfully done with 3rd layer and shape is : ", pool3.shape)
# Convolutional Layer #8
conv8 = tf.layers.conv2d(
inputs=pool3,
filters=512,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #9
conv9 = tf.layers.conv2d(
inputs=conv8,
filters=512,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #10
conv10 = tf.layers.conv2d(
inputs=conv9,
filters=512,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
pool4 = tf.layers.max_pooling2d(inputs=conv10, pool_size=[2, 2], strides=2)
#print(" Successfully done with 4th layer and shape is : ", pool4.shape)
# Convolutional Layer #11
conv11 = tf.layers.conv2d(
inputs=pool4,
filters=512,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #12
conv12 = tf.layers.conv2d(
inputs=conv11,
filters=512,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
# Convolutional Layer #12
conv13 = tf.layers.conv2d(
inputs=conv12,
filters=512,
kernel_size=[3, 3],
padding="same",
activation=tf.nn.relu)
pool5 = tf.layers.max_pooling2d(inputs=conv13, pool_size=[2, 2], strides=2)
#print(" Successfully done with 5th layer and shape is : ", pool5.shape)
# Dense Layer
pool5_flat = tf.reshape(pool5, [-1, 7 * 7 * 512])
dense1 = tf.layers.dense(inputs=pool5_flat, units=4096, activation=tf.nn.relu)
dense2 = tf.layers.dense(inputs=dense1, units=4096, activation=tf.nn.relu)
dense3 = tf.layers.dense(inputs=dense2, units=1024, activation=tf.nn.relu)
#print(dense3.shape)
dropout = tf.layers.dropout(
inputs=dense3, rate=0.001, training=mode == tf.estimator.ModeKeys.TRAIN)
#print(" Completed all the layers ")
#This is the place where we will have two flows of different layers which are used for
# Logits Layer for Front Back Prediction
#logits = tf.layers.dense(inputs=dropout, units=2)
logits1 = tf.layers.dense(inputs=dropout, units=2)
logits2 = tf.layers.dense(inputs=dropout, units=4)
#Modified this for solving the issue
predictions1 = {
# Generate predictions (for PREDICT and EVAL mode)
"classes1": tf.argmax(input=logits1, axis=1),
# Add `softmax_tensor` to the graph. It is used for PREDICT and by the
# `logging_hook`.
"probabilities1": tf.nn.softmax(logits1, name="softmax_tensor_1"),
}
#Modified this for solving the issue
predictions2 = {
# Generate predictions (for PREDICT and EVAL mode)
"classes2": tf.argmax(input=logits2, axis=1),
# Add `softmax_tensor` to the graph. It is used for PREDICT and by the
# `logging_hook`.
"probabilities2": tf.nn.softmax(logits2, name="softmax_tensor_2")
}
#Modified this for solving the issue
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions1, export_outputs={tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY: tf.estimator.export.ClassificationOutput(classes=tf.as_string(predictions1['classes1'])), 'class2': tf.estimator.export.ClassificationOutput(classes=tf.as_string(predictions2['classes2']))})
# Calculate Loss (for both TRAIN and EVAL modes)
loss1 = tf.losses.sparse_softmax_cross_entropy(labels=labels[:,0], logits=logits1)
loss2 = tf.losses.sparse_softmax_cross_entropy(labels=labels[:,1], logits=logits2)
loss1 = tf.Print(loss1, ["loss1 : ", loss1])
loss2 = tf.Print(loss2, ["loss2 : ", loss2])
loss = loss1 + loss2
loss = tf.Print(loss, ["loss : ", loss])
tf.summary.scalar('Loss1', loss1)
tf.summary.scalar('Loss2', loss2)
tf.summary.scalar('Loss', loss)
#print("Loss of this step is : ",loss)
# Configure the Training Op (for TRAIN mode)
if mode == tf.estimator.ModeKeys.TRAIN:
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01)
train_op = optimizer.minimize(
loss=loss,
global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)
#print("completed training")
# Add evaluation metrics (for EVAL mode)
eval_metric_ops = {
"accuracy1": tf.metrics.accuracy(
labels=labels[:,0], predictions=predictions1["classes1"]),
"accuracy2": tf.metrics.accuracy(
labels=labels[:,1], predictions=predictions2["classes2"]),
"precision1": tf.metrics.precision(labels=labels[:,0], predictions=predictions1["classes1"]),
"precision2": tf.metrics.precision(labels=labels[:,1], predictions=predictions2["classes2"]),
"recall1": tf.metrics.recall(labels=labels[:,0], predictions=predictions1["classes1"]),
"recall2": tf.metrics.recall(labels=labels[:,1], predictions=predictions2["classes2"])
}
tf.summary.scalar('Accuracy_for_Front/Back', eval_metric_ops.get('accuracy1'))
tf.summary.scalar('Accuracy_for_Orientation', eval_metric_ops.get('accuracy2'))
tf.summary.scalar('Precision_for_Front/Back', eval_metric_ops.get('precision1'))
tf.summary.scalar('Precision_for_Orientation', eval_metric_ops.get('precision2'))
tf.summary.scalar('Recall_for_Front/Back', eval_metric_ops.get('recall1'))
tf.summary.scalar('Recall_for_Orientation', eval_metric_ops.get('recall2'))
#print("Accuracy of this step is : ", eval_metric_ops.get('accuracy1'))
return tf.estimator.EstimatorSpec(
mode=mode, loss=loss, eval_metric_ops=eval_metric_ops )
def _parse_function(filename, label):
filename = tf.Print(filename, [filename, " Names of files "])
image_string = tf.read_file(filename)
image_decoded = tf.image.decode_image(image_string)
image_typecasted = tf.cast(image_decoded, tf.float32)
#print("type of the image : ",type(image_typecasted))
#image_resized = tf.image.resize_images(image_decoded, [28, 28])
image_typecasted = tf.Print(image_typecasted, [tf.shape(image_typecasted), " shape of image_typecasted before first reshape"],summarize=10)
image_reshaped = tf.reshape(image_typecasted, [-1, 224, 224, 3])
image_reshaped = tf.Print(image_reshaped, [tf.shape(image_reshaped), " shape of image_reshaped after first reshape"], summarize=10)
return image_reshaped, label
def _parse_function(filename):
image_string = tf.read_file(filename)
image_decoded = tf.image.decode_image(image_string)
image_typecasted = tf.cast(image_decoded, tf.float32)
#print("type of the image : ",type(image_typecasted))
#image_resized = tf.image.resize_images(image_decoded, [28, 28])
image_reshaped = tf.reshape(image_typecasted, [-1, 224, 224, 3])
return image_reshaped
def stratified_train_test_split_():
filenamelist = []
labelslist = []
DIRECTORY = 'path_to_directory'
for filename in os.listdir(DIRECTORY):
fullfilename = DIRECTORY + filename
if filename.endswith('.back.0.jpg'):
#back image, original orientation
filenamelist.append(fullfilename)
temp = [0,0]
labelslist.append(temp)
elif filename.endswith('.back.90.jpg'):
#back image, rotated clockwise 90
filenamelist.append(fullfilename)
temp = [0,1]
labelslist.append(temp)
elif filename.endswith('.back.180.jpg'):
#back image, rotated clockwise 180
filenamelist.append(fullfilename)
temp = [0,2]
labelslist.append(temp)
elif filename.endswith('.back.270.jpg'):
#back image, rotated clockwise 270
filenamelist.append(fullfilename)
temp = [0,3]
labelslist.append(temp)
elif filename.endswith('.front.0.jpg'):
#front image, rotated clockwise 0
filenamelist.append(fullfilename)
temp = [1,0]
labelslist.append(temp)
elif filename.endswith('.front.90.jpg'):
#front image, rotated clockwise 90
filenamelist.append(fullfilename)
temp = [1,1]
labelslist.append(temp)
elif filename.endswith('.front.180.jpg'):
#front image, rotated clockwise 180
filenamelist.append(fullfilename)
temp = [1,2]
labelslist.append(temp)
elif filename.endswith('.front.270.jpg'):
#front image, rotated clockwise 270
filenamelist.append(fullfilename)
temp = [1,3]
labelslist.append(temp)
#splitting the train test data
#currently we are doing stratified sampling but still we are ignoring the
X_train, X_test, y_train, y_test = train_test_split(filenamelist, labelslist, test_size=0.20, random_state=42, shuffle=True, stratify=labelslist)
#print("data is split into test and train set")
# # Build the Iterator, and return the read end of the pipeline.
return X_train, X_test, y_train, y_test
def my_input_fn_train(X_train, y_train):
filenames = tf.constant(X_train)
labels = tf.constant(y_train)
dataset = tf.data.Dataset.from_tensor_slices((filenames, labels))
dataset = dataset.map(_parse_function)
# # Shuffle, repeat, and batch the examples.
dataset = dataset.shuffle(5000).repeat().batch(64)
# # Build the Iterator, and return the read end of the pipeline.
return dataset.make_one_shot_iterator().get_next()
def my_input_fn_test(X_test, y_test):
filenames = tf.constant(X_test)
labels = tf.constant(y_test)
dataset = tf.data.Dataset.from_tensor_slices((filenames, labels))
dataset = dataset.map(_parse_function)
# # Shuffle, repeat, and batch the examples.
dataset = dataset.shuffle(5000).repeat(1).batch(64)
# # Build the Iterator, and return the read end of the pipeline.
return dataset.make_one_shot_iterator().get_next()
def my_input_fn_predict(filename):
filenames = tf.constant(filename)
dataset = tf.data.Dataset.from_tensors((filenames))
dataset = dataset.map(_parse_function)
return dataset.make_one_shot_iterator().get_next()
def main(unused_argv):
# Create the Estimator
mnist_classifier = tf.estimator.Estimator(
model_fn=cnn_model_fn,
model_dir="path_to_model_directory",
config = tf.estimator.RunConfig( save_checkpoints_steps=None, save_checkpoints_secs=600, save_summary_steps=5))
export_dir_base = 'path_to_folder'
# Set up logging for predictions
tensors_to_log_1 = {"probabilities1": "softmax_tensor_1"}
tensors_to_log_2 = {"probabilities2": "softmax_tensor_2"}
logging_hook_1 = tf.train.LoggingTensorHook(
tensors=tensors_to_log_1, every_n_iter=100)
logging_hook_2 = tf.train.LoggingTensorHook(
tensors=tensors_to_log_2, every_n_iter=100)
#print("Successfully created Estimator")
#Added this for solving the issue
def serving_input_receiver_fn():
feature_spec = {'image/encoded': tf.FixedLenFeature(shape=[],
dtype=tf.string)}
serialized_tf_example = tf.placeholder(dtype=tf.string,
name='input_example_tensor')
receiver_tensors = {'examples': serialized_tf_example}
features = tf.parse_example(serialized_tf_example, feature_spec)
jpegs = features['image/encoded']
images = tf.map_fn(_parse_function, jpegs, dtype=tf.float32)
return tf.estimator.export.ServingInputReceiver(images, receiver_tensors)
mnist_classifier.export_savedmodel(export_dir_base, serving_input_receiver_fn)
if __name__ == "__main__":
tf.app.run()