I am using the tf.estimator to train and serve my tensorflow model. the training completed as expected, but fails in serving. I read my data in as a TFRecordDataset. My parsing function applies a transformation to feature "x2". "x2" is a string that is split. the tranformed feature is "x3".
def parse_function(example_proto):
features={"x1":tf.FixedLenFeature((), tf.string), "x2":tf.FixedLenFeature((),
tf.string),
"label":tf.FixedLenFeature((), tf.int64)}
parsed_features = tf.parse_example(example_proto, features)
x3=tf.string_split(parsed_features["string"],',')
parsed_features["x3"]=x3
return parsed_features, parsed_features["label"]
My serving fucnction is
def serving_input_fn():
receiver_tensor = {}
for feature_name in record_columns:
if feature_name in {"x1", "x2","x3"}:
dtype = tf.string
else:
dtype=tf.int32
receiver_tensor[feature_name] = tf.placeholder(dtype, shape=[None])
features = {
key: tf.expand_dims(tensor, -1)
for key, tensor in receiver_tensor.items()
}
return tf.estimator.export.ServingInputReceiver(features, receiver_tensor)
It always worked in the past when I didn't have any transformations in my parsing function, but it fails now with the error.
cloud.ml.prediction.prediction_utils.PredictionError: Failed to run the provided model: Exception during running the graph: Cannot feed value of shape (2, 1) for Tensor u'Placeholder_2:0', which has shape '(?,)' (Error code: 2)
I think I have to apply the transformation to "x2" in my serving function, but I don't know how. Any help would be greatly appreciated
Following this link
I processed feature "x3" after creating the receiver_tensor. Splitting the string in the serving fucntion required squeezing the tensor before splitting
def serving_input_fn():
receiver_tensor = {}
receiver_tensor["x1"] = tf.placeholder(tf.string, shape=[None], name="x1")
receiver_tensor["label"] = tf.placeholder(tf.int32, shape=[None], name="x2")
receiver_tensor["x2"] = tf.placeholder(tf.string, shape=[None],
name="string")
features = {
key: tf.expand_dims(tensor, -1)
for key, tensor in receiver_tensor.items()
}
features["x3"]=tf.string_split(tf.squeeze(features["x2"]),',')
return tf.estimator.export.ServingInputReceiver(features, receiver_tensor)
Related
I'm trying to build the model illustrated in this picture:
I obtained a pre-trained BERT and respective tokenizer from HuggingFace's transformers in the following way:
from transformers import AutoTokenizer, TFBertModel
model_name = "dbmdz/bert-base-italian-xxl-cased"
tokenizer = AutoTokenizer.from_pretrained(model_name)
bert = TFBertModel.from_pretrained(model_name)
The model will be fed a sequence of italian tweets and will need to determine if they are ironic or not.
I'm having problems building the initial part of the model, which takes the inputs and feeds them to the tokenizer in order to get a representation I can feed to BERT.
I can do it outside of the model-building context:
my_phrase = "Ciao, come va?"
# an equivalent version is tokenizer(my_phrase, other parameters)
bert_input = tokenizer.encode(my_phrase, add_special_tokens=True, return_tensors='tf', max_length=110, padding='max_length', truncation=True)
attention_mask = bert_input > 0
outputs = bert(bert_input, attention_mask)['pooler_output']
but I'm having troubles building a model that does this. Here is the code for building such a model (the problem is in the first 4 lines ):
def build_classifier_model():
text_input = tf.keras.layers.Input(shape=(), dtype=tf.string, name='text')
encoder_inputs = tokenizer(text_input, return_tensors='tf', add_special_tokens=True, max_length=110, padding='max_length', truncation=True)
outputs = bert(encoder_inputs)
net = outputs['pooler_output']
X = tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64, return_sequences=True, dropout=0.1, recurrent_dropout=0.1))(net)
X = tf.keras.layers.Concatenate(axis=-1)([X, input_layer])
X = tf.keras.layers.MaxPooling1D(20)(X)
X = tf.keras.layers.SpatialDropout1D(0.4)(X)
X = tf.keras.layers.Flatten()(X)
X = tf.keras.layers.Dense(128, activation="relu")(X)
X = tf.keras.layers.Dropout(0.25)(X)
X = tf.keras.layers.Dense(2, activation='softmax')(X)
model = tf.keras.Model(inputs=text_input, outputs = X)
return model
And when I call the function for creating this model I get this error:
text input must of type str (single example), List[str] (batch or single pretokenized example) or List[List[str]] (batch of pretokenized examples).
One thing I thought was that maybe I had to use the tokenizer.batch_encode_plus function which works with lists of strings:
class BertPreprocessingLayer(tf.keras.layers.Layer):
def __init__(self, tokenizer, maxlength):
super().__init__()
self._tokenizer = tokenizer
self._maxlength = maxlength
def call(self, inputs):
print(type(inputs))
print(inputs)
tokenized = tokenizer.batch_encode_plus(inputs, add_special_tokens=True, return_tensors='tf', max_length=self._maxlength, padding='max_length', truncation=True)
return tokenized
def build_classifier_model():
text_input = tf.keras.layers.Input(shape=(), dtype=tf.string, name='text')
encoder_inputs = BertPreprocessingLayer(tokenizer, 100)(text_input)
outputs = bert(encoder_inputs)
net = outputs['pooler_output']
# ... same as above
but I get this error:
batch_text_or_text_pairs has to be a list (got <class 'keras.engine.keras_tensor.KerasTensor'>)
and beside the fact I haven't found a way to convert that tensor to a list with a quick google search, it seems weird that I have to go in and out of tensorflow in this way.
I've also looked up on the huggingface's documentation but there is only a single usage example, with a single phrase, and what they do is analogous at my "out of model-building context" example.
EDIT:
I also tried with Lambdas in this way:
tf.executing_eagerly()
def tokenize_tensor(tensor):
t = tensor.numpy()
t = np.array([str(s, 'utf-8') for s in t])
return tokenizer(t.tolist(), return_tensors='tf', add_special_tokens=True, max_length=110, padding='max_length', truncation=True)
def build_classifier_model():
text_input = tf.keras.layers.Input(shape=(1,), dtype=tf.string, name='text')
encoder_inputs = tf.keras.layers.Lambda(tokenize_tensor, name='tokenize')(text_input)
...
outputs = bert(encoder_inputs)
but I get the following error:
'Tensor' object has no attribute 'numpy'
EDIT 2:
I also tried the approach suggested by #mdaoust of wrapping everything in a tf.py_function and got this error.
def py_func_tokenize_tensor(tensor):
return tf.py_function(tokenize_tensor, [tensor], Tout=[tf.int32, tf.int32, tf.int32])
eager_py_func() missing 1 required positional argument: 'Tout'
Then I defined Tout as the type of the value returned by the tokenizer:
transformers.tokenization_utils_base.BatchEncoding
and got the following error:
Expected DataType for argument 'Tout' not <class
'transformers.tokenization_utils_base.BatchEncoding'>
Finally I unpacked the value in the BatchEncoding in the following way:
def tokenize_tensor(tensor):
t = tensor.numpy()
t = np.array([str(s, 'utf-8') for s in t])
dictionary = tokenizer(t.tolist(), return_tensors='tf', add_special_tokens=True, max_length=110, padding='max_length', truncation=True)
#unpacking
input_ids = dictionary['input_ids']
tok_type = dictionary['token_type_ids']
attention_mask = dictionary['attention_mask']
return input_ids, tok_type, attention_mask
And get an error in the line below:
...
outputs = bert(encoder_inputs)
ValueError: Cannot take the length of shape with unknown rank.
For now I solved by taking the tokenization step out of the model:
def tokenize(sentences, tokenizer):
input_ids, input_masks, input_segments = [],[],[]
for sentence in sentences:
inputs = tokenizer.encode_plus(sentence, add_special_tokens=True, max_length=128, pad_to_max_length=True, return_attention_mask=True, return_token_type_ids=True)
input_ids.append(inputs['input_ids'])
input_masks.append(inputs['attention_mask'])
input_segments.append(inputs['token_type_ids'])
return np.asarray(input_ids, dtype='int32'), np.asarray(input_masks, dtype='int32'), np.asarray(input_segments, dtype='int32')
The model takes two inputs which are the first two values returned by the tokenize funciton.
def build_classifier_model():
input_ids_in = tf.keras.layers.Input(shape=(128,), name='input_token', dtype='int32')
input_masks_in = tf.keras.layers.Input(shape=(128,), name='masked_token', dtype='int32')
embedding_layer = bert(input_ids_in, attention_mask=input_masks_in)[0]
...
model = tf.keras.Model(inputs=[input_ids_in, input_masks_in], outputs = X)
for layer in model.layers[:3]:
layer.trainable = False
return model
I'd still like to know if someone has a solution which integrates the tokenization step inside the model-building context so that an user of the model can simply feed phrases to it to get a prediction or to train the model.
text input must of type str (single example), List[str] (batch or single pretokenized example) or List[List[str]] (batch of pretokenized examples).
Solution to the above error:
Just use text_input = 'text'
instead of
text_input = tf.keras.layers.Input(shape=(), dtype=tf.string, name='text')
It looks like this is not TensorFlow compatible.
https://huggingface.co/dbmdz/bert-base-italian-xxl-cased#model-weights
Currently only PyTorch-Transformers compatible weights are available. If you need access to TensorFlow checkpoints, please raise an issue!
But remember that some things are easier if you don't use keras's functional-model-api. That's what got <class 'keras.engine.keras_tensor.KerasTensor'> is complaining about.
Try passing a tf.Tensor to see if that works.
What happens when you try:
text_input = tf.constant('text')
Try writing your model as a subclass of model.
Yeah, my first answer was wrong.
The problem is that tensorflow has two types of tensors. Eager tensors (these have a value). And "symbolic tensors" or "graph tensors" that don't have a value, and are just used to build up a calculation.
Your tokenize_tensor function expects an eager tensor. Only eager tensors have a .numpy() method.
def tokenize_tensor(tensor):
t = tensor.numpy()
t = np.array([str(s, 'utf-8') for s in t])
return tokenizer(t.tolist(), return_tensors='tf', add_special_tokens=True, max_length=110, padding='max_length', truncation=True)
But keras Input is a symbolic tensor.
text_input = tf.keras.layers.Input(shape=(1,), dtype=tf.string, name='text')
encoder_inputs = tf.keras.layers.Lambda(tokenize_tensor, name='tokenize')(text_input)
To fix this, you can use tf.py_function. It works in graph mode, and will call the wrapped function with eager tensors when the graph is executed, instead of passing it the graph-tensors while the graph is being constructed.
def py_func_tokenize_tensor(tensor):
return tf.py_function(tokenize_tensor, [tensor])
...
encoder_inputs = tf.keras.layers.Lambda(py_func_tokenize_tensor, name='tokenize')(text_input)
Found this Use `sentence-transformers` inside of a keras model and this amazing articles https://www.philschmid.de/tensorflow-sentence-transformers, which explain you how to do what you're trying to achieve.
The first one is using the py_function approach, the second uses tf.Model to wrap everything into model classes.
Hope this helps anyone arriving here in the future.
This is how to use tf.py_function correctly to create a model that takes string as an input:
model_name = "dbmdz/bert-base-italian-xxl-cased"
tokenizer = AutoTokenizer.from_pretrained(model_name)
bert = TFBertModel.from_pretrained(model_name)
def build_model():
text_input = tf.keras.layers.Input(shape=(), dtype=tf.string, name='text')
def encode_text(text):
inputs = [tf.compat.as_str(x) for x in text.numpy().tolist()]
tokenized = tokenizer(
inputs,
return_tensors='tf',
add_special_tokens=True,
max_length=110,
padding='max_length',
truncation=True)
return tokenized['input_ids'], tokenized['attention_mask']
input_ids, attention_mask = tf.py_function(encode_text, inp=[text_input], Tout=[tf.int32, tf.int32])
input_ids = tf.ensure_shape(input_ids, [None, 110])
attention_mask = tf.ensure_shape(attention_mask, [None, 110])
outputs = bert(input_ids, attention_mask)
net = outputs['last_hidden_state']
# Some other layers, this part is not important
x = tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64, return_sequences=True))(net)
x = tf.keras.layers.TimeDistributed(tf.keras.layers.Dense(1, name='classifier'))(x)
return tf.keras.Model(inputs=text_input, outputs=x)
I use last_hidden_state instead of pooler_output, that's where outputs for each token in the sequence are located. (See discussion here on difference between last_hidden_state and pooler_output). We usually use last_hidden_state when doing token level classification (e.g. named entity recognition).
To use pooler_output would be even simpler, e.g:
net = outputs['pooler_output']
x = tf.keras.layers.Dense(1, name='classifier')(net)
return tf.keras.Model(inputs=text_input, outputs=x)
pooler_output can be used in simpler classification problems (like irony detection), but of course it's still possible to use last_hidden_state to create more powerful models. (When you use bert(input_ids_in, attention_mask=input_masks_in)[0] in your solution, it actually returns last_hidden_state.)
Making sure the model works:
model = build_model()
my_phrase = "Ciao, come va?"
model(tf.constant([my_phrase]))
>>> <tf.Tensor: shape=(1, 110, 1), dtype=float32, numpy=...>,
Making sure HuggingFace part of the model is trainable:
model.summary(show_trainable=True)
I'm using this Colab for BERT model.
In last cells in order to make predictions we have:
def getPrediction(in_sentences):
labels = ["Negative", "Positive"]
input_examples = [run_classifier.InputExample(guid="", text_a = x, text_b = None, label = 0) for x in in_sentences] # here, "" is just a dummy label
input_features = run_classifier.convert_examples_to_features(input_examples, label_list, MAX_SEQ_LENGTH, tokenizer)
predict_input_fn = run_classifier.input_fn_builder(features=input_features, seq_length=MAX_SEQ_LENGTH, is_training=False, drop_remainder=False)
predictions = estimator.predict(predict_input_fn)
return [(sentence, prediction['probabilities'], labels[prediction['labels']]) for sentence, prediction in zip(in_sentences, predictions)]
pred_sentences = [
"That movie was absolutely awful",
"The acting was a bit lacking",
"The film was creative and surprising",
"Absolutely fantastic!"
]
predictions = getPrediction(pred_sentences)
I want to create a 'SavedModel' to be used with TF serving. How to create a SavedModel for this model?
Normally I would define the following:
def serving_input_fn():
"""Create serving input function to be able to serve predictions later
using provided inputs
:return:
"""
feature_placeholders = {
'sentence': tf.placeholder(tf.string, [None]),
}
return tf.estimator.export.ServingInputReceiver(feature_placeholders,
feature_placeholders)
latest_ckpt = tf.train.latest_checkpoint(OUTPUT_DIR)
last_eval = estimator.evaluate(input_fn=test_input_fn, steps=None, checkpoint_path=latest_ckpt)
# Export the model to GCS for serving.
exporter = tf.estimator.LatestExporter('exporter', serving_input_fn, exports_to_keep=None)
exporter.export(estimator, OUTPUT_DIR, latest_ckpt, last_eval, is_the_final_export=True)
Not sure how to define my tf.estimator.export.ServingInputReceiver
If you look at create_model function present in notebook. It takes some arguments. These are the features which will be passed to the model.
You need to update the serving_input_fn function to include them.
def serving_input_fn():
feature_spec = {
"input_ids" : tf.FixedLenFeature([MAX_SEQ_LENGTH], tf.int64),
"input_mask" : tf.FixedLenFeature([MAX_SEQ_LENGTH], tf.int64),
"segment_ids" : tf.FixedLenFeature([MAX_SEQ_LENGTH], tf.int64),
"label_ids" : tf.FixedLenFeature([], tf.int64)
}
serialized_tf_example = tf.placeholder(dtype=tf.string,
shape=[None],
name='input_example_tensor')
receiver_tensors = {'example': serialized_tf_example}
features = tf.parse_example(serialized_tf_example, feature_spec)
return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)
I'm currently working with tensorflow Estimator API and have problems with the confusing serving options that are available. My confusion comes from the very undetailed tensorflow documentation.
This is my goal:
Use tensorflow-serving prediction_service_pb2 by sending a serialized proto message as string to the ServingInputReceiver function of my exported Estimator model. I expect the ServingInputReceiver function to receive the serialized proto string on the "input" tensor which then will deserialize it to the features "ink" (=varlength float array) and "shape" (=fixedlength int64).
This is my (implementation of google quickdraw model) estimator Input function:
def _parse_tfexample_fn(example_proto, mode):
"""Parse a single record which is expected to be a tensorflow.Example."""
feature_to_type = {
"ink": tf.VarLenFeature(dtype=tf.float32),
"shape": tf.FixedLenFeature([2], dtype=tf.int64)
}
if mode != tf.estimator.ModeKeys.PREDICT:
# The labels won't be available at inference time, so don't add them
# to the list of feature_columns to be read.
feature_to_type["class_index"] = tf.FixedLenFeature([1], dtype=tf.int64)
parsed_features = tf.parse_single_example(example_proto, feature_to_type)
parsed_features["ink"] = tf.sparse_tensor_to_dense(parsed_features["ink"])
if mode != tf.estimator.ModeKeys.PREDICT:
labels = parsed_features["class_index"]
return parsed_features, labels
else:
return parsed_features # In prediction, we have no labels
This is my Serving Input Function:
def serving_input_receiver_fn():
"""An input receiver that expects a serialized tf.Example."""
feature_to_type = {"ink": tf.VarLenFeature(dtype=tf.float32), "shape": tf.FixedLenFeature([2], dtype=tf.int64)}
serialized_tf_example = tf.placeholder(dtype=tf.string, shape=[None], name='input')
parsed_features = tf.parse_example(serialized_tf_example, feature_to_type)
parsed_features["ink"] = tf.sparse_tensor_to_dense(parsed_features["ink"])
return tf.estimator.export.ServingInputReceiver(parsed_features, serialized_tf_example)
This is my client.py request:
features = {}
features["ink"] = tf.train.Feature(float_list=tf.train.FloatList(value=np_ink.flatten()))
features["shape"] = tf.train.Feature(int64_list=tf.train.Int64List(value=np_ink.shape))
f = tf.train.Features(feature=features)
data = tf.train.Example(features=f)
serialized=data.SerializeToString() # tensor to byte string
request.inputs['input'].ParseFromString(tf.contrib.util.make_tensor_proto(serialized, shape=[1], verify_shape=True))
And this is the error I get after calling the Predict function in client.py
grpc.framework.interfaces.face.face.AbortionError: AbortionError(code=StatusCode.INVALID_ARGUMENT, details="input tensor alias not found in signature: ink. Inputs expected to be in the set {input}.")
I tried the following Servingfunctions:
ServingInputReceiver and build_raw_serving_input_receiver_fn give me the same grpc error. When I use build_parsing_serving_input_receiver_fn it wont even export my model. I tried to wrap my head around the documentation but it is very undetailed and I don't understand when to use which serving input function.
I want to know how to process images before being fed as an input to a Bidirectional LSTM. I always get this error whenever I run me code:
AttributeError: 'list' object has no attribute 'get_shape'
from this line:
outputs, _, _ = tf.nn.bidirectional_dynamic_rnn(lstm_fw_cell, lstm_bw_cell, x, dtype=tf.float32)
Here's a part of my code relevant to the problem:
def bi_rnn(features, labels, mode):
x = tf.unstack(features, num_inputs, 1)
... # cell initialization
# Get lstm cell output
try:
outputs, _, _ = tf.nn.bidirectional_dynamic_rnn(lstm_fw_cell, lstm_bw_cell, x, dtype=tf.float32)
...
def serving_input_fn():
feature_placeholders = {
'features': tf.placeholder(tf.float32, [None, num_inputs])
}
features = {
key: tf.expand_dims(tensor, -1) for key, tensor in feature_placeholders.items()
}
features = tf.squeeze(features, axis=[2])
return InputFnOps(features, None, feature_placeholders)
def read_dataset(img_paths, labels):
def _input_fn():
... # reading image paths omitted
image_files = tf.image.decode_png(image_files)
image_files = tf.image.resize_images(image_files, [1024, 128])
image_files = evaluate_images(image_files)
... # labels part omitted
return tf.convert_to_tensor(np.array(image_files)), labels2
return _input_fn
I pretty much gave up on this one already and made something else work. It doesn't use the TFLearn features unlike this one. The recent one I'm working on has a problem which you can view here.
I know about the "Serving a Tensorflow Model" page
https://www.tensorflow.org/serving/serving_basic
but those functions assume you're using tf.Session() which the DNNClassifier tutorial does not... I then looked at the api doc for DNNClassifier and it has an export_savedmodel function (the export function is deprecated) and it seems simple enough but I am getting a "'NoneType' object is not iterable" error... which is suppose to mean I'm passing in an empty variable but I'm unsure what I need to change... I've essentially copied and pasted the code from the get_started/tflearn page on tensorflow.org but then added
directoryName = "temp"
def serving_input_fn():
print("asdf")
classifier.export_savedmodel(
directoryName,
serving_input_fn
)
just after the classifier.fit function call... the other parameters for export_savedmodel are optional I believe... any ideas?
Tutorial with Code:
https://www.tensorflow.org/get_started/tflearn#construct_a_deep_neural_network_classifier
API Doc for export_savedmodel
https://www.tensorflow.org/api_docs/python/tf/contrib/learn/DNNClassifier#export_savedmodel
There are two kind of TensorFlow applications:
The functions that assume you are using tf.Session() are functions from "low level" Tensorflow examples, and
the DNNClassifier tutorial is a "high level" Tensorflow application.
I'm going to explain how to export "high level" Tensorflow models (using export_savedmodel).
The function export_savedmodel requires the argument serving_input_receiver_fn, that is a function without arguments, which defines the input from the model and the predictor. Therefore, you must create your own serving_input_receiver_fn, where the model input type match with the model input in the training script, and the predictor input type match with the predictor input in the testing script.
On the other hand, if you create a custom model, you must define the export_outputs, defined by the function tf.estimator.export.PredictOutput, which input is a dictionary that define the name that has to match with the name of the predictor output in the testing script.
For example:
TRAINING SCRIPT
def serving_input_receiver_fn():
serialized_tf_example = tf.placeholder(dtype=tf.string, shape=[None], name='input_tensors')
receiver_tensors = {"predictor_inputs": serialized_tf_example}
feature_spec = {"words": tf.FixedLenFeature([25],tf.int64)}
features = tf.parse_example(serialized_tf_example, feature_spec)
return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)
def estimator_spec_for_softmax_classification(logits, labels, mode):
predicted_classes = tf.argmax(logits, 1)
if (mode == tf.estimator.ModeKeys.PREDICT):
export_outputs = {'predict_output': tf.estimator.export.PredictOutput({"pred_output_classes": predicted_classes, 'probabilities': tf.nn.softmax(logits)})}
return tf.estimator.EstimatorSpec(mode=mode, predictions={'class': predicted_classes, 'prob': tf.nn.softmax(logits)}, export_outputs=export_outputs) # IMPORTANT!!!
onehot_labels = tf.one_hot(labels, 31, 1, 0)
loss = tf.losses.softmax_cross_entropy(onehot_labels=onehot_labels, logits=logits)
if (mode == tf.estimator.ModeKeys.TRAIN):
optimizer = tf.train.AdamOptimizer(learning_rate=0.01)
train_op = optimizer.minimize(loss, global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op)
eval_metric_ops = {'accuracy': tf.metrics.accuracy(labels=labels, predictions=predicted_classes)}
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
def model_custom(features, labels, mode):
bow_column = tf.feature_column.categorical_column_with_identity("words", num_buckets=1000)
bow_embedding_column = tf.feature_column.embedding_column(bow_column, dimension=50)
bow = tf.feature_column.input_layer(features, feature_columns=[bow_embedding_column])
logits = tf.layers.dense(bow, 31, activation=None)
return estimator_spec_for_softmax_classification(logits=logits, labels=labels, mode=mode)
def main():
# ...
# preprocess-> features_train_set and labels_train_set
# ...
classifier = tf.estimator.Estimator(model_fn = model_custom)
train_input_fn = tf.estimator.inputs.numpy_input_fn(x={"words": features_train_set}, y=labels_train_set, batch_size=batch_size_param, num_epochs=None, shuffle=True)
classifier.train(input_fn=train_input_fn, steps=100)
full_model_dir = classifier.export_savedmodel(export_dir_base="C:/models/directory_base", serving_input_receiver_fn=serving_input_receiver_fn)
TESTING SCRIPT
def main():
# ...
# preprocess-> features_test_set
# ...
with tf.Session() as sess:
tf.saved_model.loader.load(sess, [tf.saved_model.tag_constants.SERVING], full_model_dir)
predictor = tf.contrib.predictor.from_saved_model(full_model_dir)
model_input = tf.train.Example(features=tf.train.Features( feature={"words": tf.train.Feature(int64_list=tf.train.Int64List(value=features_test_set)) }))
model_input = model_input.SerializeToString()
output_dict = predictor({"predictor_inputs":[model_input]})
y_predicted = output_dict["pred_output_classes"][0]
(Code tested in Python 3.6.3, Tensorflow 1.4.0)
If you try to use predictor with tensorflow > 1.6 you can get this Error :
signature_def_key "serving_default". Available signatures are ['predict']. Original error:
No SignatureDef with key 'serving_default' found in MetaGraphDef.
Here is working example which is tested on 1.7.0 :
SAVING :
First you need to define features length in dict format like this:
feature_spec = {'x': tf.FixedLenFeature([4],tf.float32)}
Then you have to build a function which have placeholder with same shape of features and return using tf.estimator.export.ServingInputReceiver
def serving_input_receiver_fn():
serialized_tf_example = tf.placeholder(dtype=tf.string,
shape=[None],
name='input_tensors')
receiver_tensors = {'inputs': serialized_tf_example}
features = tf.parse_example(serialized_tf_example, feature_spec)
return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)
Then just save with export_savedmodel :
classifier.export_savedmodel(dir_path, serving_input_receiver_fn)
full example code:
import os
from six.moves.urllib.request import urlopen
import numpy as np
import tensorflow as tf
dir_path = os.path.dirname('.')
IRIS_TRAINING = os.path.join(dir_path, "iris_training.csv")
IRIS_TEST = os.path.join(dir_path, "iris_test.csv")
feature_spec = {'x': tf.FixedLenFeature([4],tf.float32)}
def serving_input_receiver_fn():
serialized_tf_example = tf.placeholder(dtype=tf.string,
shape=[None],
name='input_tensors')
receiver_tensors = {'inputs': serialized_tf_example}
features = tf.parse_example(serialized_tf_example, feature_spec)
return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)
def main():
training_set = tf.contrib.learn.datasets.base.load_csv_with_header(
filename=IRIS_TRAINING,
target_dtype=np.int,
features_dtype=np.float32)
test_set = tf.contrib.learn.datasets.base.load_csv_with_header(
filename=IRIS_TEST,
target_dtype=np.int,
features_dtype=np.float32)
feature_columns = [tf.feature_column.numeric_column("x", shape=[4])]
classifier = tf.estimator.DNNClassifier(feature_columns=feature_columns,
hidden_units=[10, 20, 10],
n_classes=3,
model_dir=dir_path)
# Define the training inputs
train_input_fn = tf.estimator.inputs.numpy_input_fn(
x={"x": np.array(training_set.data)},
y=np.array(training_set.target),
num_epochs=None,
shuffle=True)
# Train model.
classifier.train(input_fn=train_input_fn, steps=200)
classifier.export_savedmodel(dir_path, serving_input_receiver_fn)
if __name__ == "__main__":
main()
Restoring
Now let's restore the model :
import tensorflow as tf
import os
dir_path = os.path.dirname('.') #current directory
exported_path= os.path.join(dir_path, "1536315752")
def main():
with tf.Session() as sess:
tf.saved_model.loader.load(sess, [tf.saved_model.tag_constants.SERVING], exported_path)
model_input= tf.train.Example(features=tf.train.Features(feature={
'x': tf.train.Feature(float_list=tf.train.FloatList(value=[6.4, 3.2, 4.5, 1.5]))
}))
predictor= tf.contrib.predictor.from_saved_model(exported_path)
input_tensor=tf.get_default_graph().get_tensor_by_name("input_tensors:0")
model_input=model_input.SerializeToString()
output_dict= predictor({"inputs":[model_input]})
print(" prediction is " , output_dict['scores'])
if __name__ == "__main__":
main()
Here is Ipython notebook demo example with data and explanation :
There are two possible questions and answers possible. First you encounter a missing session for the DNNClassifier which uses the more higher level estimators API (as opposed to the more low level API's where you manipulate the ops yourself). The nice thing about tensorflow is that all high and low level APIs are more-or-less interoperable, so if you want a session and do something with that session, it is as simple as adding:
sess = tf.get_default_session()
The you can start hooking in the remainder of the tutorial.
The second interpretation of your question is, what about the export_savedmodel, well actually export_savedmodel and the sample code from the serving tutorial try to achieve the same goal. When you are training your graph you set up some infrastructure to feed input to the graph (typically batches from a training dataset) however when you switch to 'serving' you will often read your input from somewhere else, and you need some separate infrastructure which replaces the input of the graph used for training. The bottomline is that the serving_input_fn() which you filled with a print should in essence return an input op. This is also said in the documentation:
serving_input_fn: A function that takes no argument and returns an
InputFnOps.
Hence instead of print("asdf") it should do something similar as adding an input chain (which should be similar to what builder.add_meta_graph_and_variables is also adding).
Examples of serving_input_fn()'s can for example be found (in the cloudml sample)[https://github.com/GoogleCloudPlatform/cloudml-samples/blob/master/census/customestimator/trainer/model.py#L240]. Such as the following which serves input from JSON:
def json_serving_input_fn():
"""Build the serving inputs."""
inputs = {}
for feat in INPUT_COLUMNS:
inputs[feat.name] = tf.placeholder(shape=[None], dtype=feat.dtype)
return tf.estimator.export.ServingInputReceiver(inputs, inputs)