I am trying to evaluate a model with 2 inputs and 1 output, each input goes to separate pretrained model and then the output from both the models get averaged. I am using the same data for both the inputs.
test_dir = 'D:\Graduation_project\Damage type not collected'
test_datagen = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255,)
test_set = test_datagen.flow_from_directory(test_dir,
class_mode = 'categorical',
batch_size = 16,
target_size=(150,150))
test_set1 = test_datagen.flow_from_directory(test_dir,
class_mode = 'categorical',
batch_size = 16,
target_size=(150,150))
loading first model and renaming the layers
def load_dense_model():
densenet = tf.keras.models.load_model('D:\Graduation_project\saved models\damage_type_model.h5', compile=False)
for i, layer in enumerate(densenet.layers):
layer._name = 'Densenet_layer' + str(i)
return densenet
loading second model
def load_vgg19_model():
vgg19 = tf.keras.models.load_model('D:\Graduation_project\saved models\damage_type_VGG19.h5', compile=False)
return vgg19
creating ensemble model
def ensamble_model(first_model, second_model):
densenet = first_model()
vgg19 = second_model()
output_1 = densenet.get_layer('Densenet_layer613')
output_2 = vgg19.get_layer('dense_4')
avg = tf.keras.layers.Average()([output_1.output, output_2.output])
model = Model(inputs=[densenet.input, vgg19.input], outputs=avg)
return model
METRICS = [
'accuracy',
tf.metrics.TruePositives(name='tp'),
tf.metrics.FalsePositives(name='fp'),
tf.metrics.TrueNegatives(name='tn'),
tf.metrics.FalseNegatives(name='fn'),
tf.metrics.Precision(name='precision'),
tf.metrics.Recall(name='recall'),
tfa.metrics.F1Score(name='F1_Score', num_classes=5),
tfa.metrics.MultiLabelConfusionMatrix(num_classes=5)
]
model = ensamble_model(load_dense_model, load_vgg19_model)
compiling and evaluating the model
model.compile(optimizer = 'adam' , loss ='binary_crossentropy',
metrics = 'accuracy')
model.evaluate({'Densenet_layer0':test_set1, 'input_2':test_set})
evaluate() fails to run
ValueError: Failed to find data adapter that can handle input: (<class 'dict'> containing {"<class 'str'>"} keys and {"<class 'tensorflow.python.keras.preprocessing.image.DirectoryIterator'>"} values), <class 'NoneType'>
My guess is that your model complaining because you are feeding a dict/list of iterators that yield an image each, instead of feeding an iterator that yields the image twice (once for each model).
What would happen if you wrap your DirectoryIterator on a generator that can feed the data correctly?
def gen_itertest(test_dir):
test_set = test_datagen.flow_from_directory(test_dir,
class_mode = 'categorical',
batch_size = 16,
target_size=(150,150))
for i in range(len(test_set)):
x = test_set.next()
yield [x[0], x[0]], x[1] # Twice the input, only once the label
and then you can feed this to the evaluate
testset = gen_itertest('D:\Graduation_project\Damage type not collected')
result = model.evaluate(testset)
I am not sure this will work but because you haven't provide us with a minimal, reproducible example, I am not going to do one to test it.
Try calling the evaluate() like this:
result = model.evaluate(x=[test_set1, test_set])
Then you could get the name of the metrics doing something like this:
dict(zip(model.metrics_names, result))
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)
Problem
As the title suggests I have been trying to create a pipeline for training an Autoencoder model using TFX. The problem I'm having is fitting the tf.Dataset returned by the DataAccessor.tf_dataset_factory object to the Autoencoder.
Below I summarise the steps I've taken through this project, and have some Questions at the bottom if you wish to skip the background information.
Intro
TFX Pipeline
The TFX components I have used so far have been:
CsvExampleGenerator (the dataset has 82 columns, all numeric, and the sample csv has 739 rows)
StatisticsGenerator / SchemaGenerator, the schema has been edited as is now loaded in using an Importer
Transform
Trainer (this is the component I am currently having problems with)
Model
The model that I am attempting to train is based off of the example laid out here https://www.tensorflow.org/tutorials/generative/autoencoder. However, my model is being trained on tabular data, searching for anomalous results, as opposed to image data.
As I have tried a couple of solutions I have tried using both the Keras.layers and Keras.model format for defining the model and I outline both below:
Subclassing Keras.Model
class Autoencoder(keras.models.Model):
def __init__(self, features):
super(Autoencoder, self).__init__()
self.encoder = tf.keras.Sequential([
keras.layers.Dense(82, activation = 'relu'),
keras.layers.Dense(32, activation = 'relu'),
keras.layers.Dense(16, activation = 'relu'),
keras.layers.Dense(8, activation = 'relu')
])
self.decoder = tf.keras.Sequential([
keras.layers.Dense(16, activation = 'relu'),
keras.layers.Dense(32, activation = 'relu'),
keras.layers.Dense(len(features), activation = 'sigmoid')
])
def call(self, x):
inputs = [keras.layers.Input(shape = (1,), name = f) for f in features]
dense = keras.layers.concatenate(inputs)
encoded = self.encoder(dense)
decoded = self.decoder(encoded)
return decoded
Subclassing Keras.Layers
def _build_keras_model(features: List[str]) -> tf.keras.Model:
inputs = [keras.layers.Input(shape = (1,), name = f) for f in features]
dense = keras.layers.concatenate(inputs)
dense = keras.layers.Dense(32, activation = 'relu')(dense)
dense = keras.layers.Dense(16, activation = 'relu')(dense)
dense = keras.layers.Dense(8, activation = 'relu')(dense)
dense = keras.layers.Dense(16, activation = 'relu')(dense)
dense = keras.layers.Dense(32, activation = 'relu')(dense)
outputs = keras.layers.Dense(len(features), activation = 'sigmoid')(dense)
model = keras.Model(inputs = inputs, outputs = outputs)
model.compile(
optimizer = 'adam',
loss = 'mae'
)
return model
TFX Trainer Component
For creating the Trainer Component I have been mainly following the implementation details laid out here: https://www.tensorflow.org/tfx/guide/trainer
As well as following the default penguins example: https://www.tensorflow.org/tfx/tutorials/tfx/penguin_simple#write_model_training_code
run_fn defintion
def run_fn(fn_args: tfx.components.FnArgs) -> None:
tft_output = tft.TFTransformOutput(fn_args.transform_output)
train_dataset = _input_fn(
file_pattern = fn_args.train_files,
data_accessor = fn_args.data_accessor,
tf_transform_output = tft_output,
batch_size = fn_args.train_steps
)
eval_dataset = _input_fn(
file_pattern = fn_args.eval_files,
data_accessor = fn_args.data_accessor,
tf_transform_output = tft_output,
batch_size = fn_args.custom_config['eval_batch_size']
)
# model = Autoencoder(
# features = fn_args.custom_config['features']
# )
model = _build_keras_model(features = fn_args.custom_config['features'])
model.compile(optimizer = 'adam', loss = 'mse')
model.fit(
train_dataset,
steps_per_epoch = fn_args.train_steps,
validation_data = eval_dataset,
validation_steps = fn_args.eval_steps
)
...
_input_fn definition
def _apply_preprocessing(raw_features, tft_layer):
transformed_features = tft_layer(raw_features)
return transformed_features
def _input_fn(
file_pattern,
data_accessor: tfx.components.DataAccessor,
tf_transform_output: tft.TFTransformOutput,
batch_size: int) -> tf.data.Dataset:
"""
Generates features and label for tuning/training.
Args:
file_pattern: List of paths or patterns of input tfrecord files.
data_accessor: DataAccessor for converting input to RecordBatch.
tf_transform_output: A TFTransformOutput.
batch_size: representing the number of consecutive elements of returned
dataset to combine in a single batch
Returns:
A dataset that contains features where features is a
dictionary of Tensors.
"""
dataset = data_accessor.tf_dataset_factory(
file_pattern,
tfxio.TensorFlowDatasetOptions(batch_size = batch_size),
tf_transform_output.transformed_metadata.schema
)
transform_layer = tf_transform_output.transform_features_layer()
def apply_transform(raw_features):
return _apply_preprocessing(raw_features, transform_layer)
return dataset.map(apply_transform).repeat()
This differs from the _input_fn example given above as I was following the example in the next tfx tutorial found here: https://www.tensorflow.org/tfx/tutorials/tfx/penguin_tft#run_fn
Also for reference, there is no Target within the example data so there is no label_key to be passed to the tfxio.TensorFlowDatasetOptions object.
Error
When trying to run the Trainer component using a TFX InteractiveContext object I receive the following error.
ValueError: No gradients provided for any variable: ['dense_460/kernel:0', 'dense_460/bias:0', 'dense_461/kernel:0', 'dense_461/bias:0', 'dense_462/kernel:0', 'dense_462/bias:0', 'dense_463/kernel:0', 'dense_463/bias:0', 'dense_464/kernel:0', 'dense_464/bias:0', 'dense_465/kernel:0', 'dense_465/bias:0'].
From my own attempts to solve this I believe the problem lies in the way that an Autoencoder is trained. From the Autoencoder example linked here https://www.tensorflow.org/tutorials/generative/autoencoder the data is fitted like so:
autoencoder.fit(x_train, x_train,
epochs=10,
shuffle=True,
validation_data=(x_test, x_test))
therefore it stands to reason that the tf.Dataset should also mimic this behaviour and when testing with plain Tensor objects I have been able to recreate the error above and then solve it when adding the target to be the same as the training data in the .fit() function.
Things I've Tried So Far
Duplicating Train Dataset
model.fit(
train_dataset,
train_dataset,
steps_per_epoch = fn_args.train_steps,
validation_data = eval_dataset,
validation_steps = fn_args.eval_steps
)
Raises error due to Keras not accepting a 'y' value when a dataset is passed.
ValueError: `y` argument is not supported when using dataset as input.
Returning a dataset that is a tuple with itself
def _input_fn(...
dataset = data_accessor.tf_dataset_factory(
file_pattern,
tfxio.TensorFlowDatasetOptions(batch_size = batch_size),
tf_transform_output.transformed_metadata.schema
)
transform_layer = tf_transform_output.transform_features_layer()
def apply_transform(raw_features):
return _apply_preprocessing(raw_features, transform_layer)
dataset = dataset.map(apply_transform)
return dataset.map(lambda x: (x, x))
This raises an error where the keys from the features dictionary don't match the output of the model.
ValueError: Found unexpected keys that do not correspond to any Model output: dict_keys(['feature_string', ...]). Expected: ['dense_477']
At this point I switched to using the keras.model Autoencoder subclass and tried to add output keys to the Model using an output which I tried to create dynamically in the same way as the inputs.
def call(self, x):
inputs = [keras.layers.Input(shape = (1,), name = f) for f in x]
dense = keras.layers.concatenate(inputs)
encoded = self.encoder(dense)
decoded = self.decoder(encoded)
outputs = {}
for feature_name in x:
outputs[feature_name] = keras.layers.Dense(1, activation = 'sigmoid')(decoded)
return outputs
This raises the following error:
TypeError: Cannot convert a symbolic Keras input/output to a numpy array. This error may indicate that you're trying to pass a symbolic value to a NumPy call, which is not supported. Or, you may be trying to pass Keras symbolic inputs/outputs to a TF API that does not register dispatching, preventing Keras from automatically converting the API call to a lambda layer in the Functional Model.
I've been looking into solving this issue but am no longer sure if the data is being passed correctly and am beginning to think I'm getting side-tracked from the actual problem.
Questions
Has anyone managed to get an Autoencoder working when connected via TFX examples?
Did you alter the tf.Dataset or handled the examples in a different way to the _input_fn demonstrated?
So I managed to find an answer to this and wanted to leave what I found here in case anyone else stumbles onto a similar problem.
It turns out my feelings around the error were correct and the solution did indeed lie in how the tf.Dataset object was presented.
This can be demonstrated when I ran some code which simulated the incoming data using randomly generated tensors.
tensors = [tf.random.uniform(shape = (1, 82)) for i in range(739)]
# This gives us a list of 739 tensors which hold 1 value for 82 'features' simulating the dataset I had
dataset = tf.data.Dataset.from_tensor_slices(tensors)
dataset = dataset.map(lambda x : (x, x))
# This returns a dataset which marks the training set and target as the same
# which is what the Autoecnoder model is looking for
model.fit(dataset ...)
Following this I proceeded to do the same thing with the dataset returned by the _input_fn. Given that the tfx DataAccessor object returns a features_dict however I needed to combine the tensors in that dict together to create a single tensor.
This is how my _input_fn looks now:
def create_target_values(features_dict: Dict[str, tf.Tensor]) -> tuple:
value_tensor = tf.concat(list(features_dict.values()), axis = 1)
return (features_dict, value_tensor)
def _input_fn(
file_pattern,
data_accessor: tfx.components.DataAccessor,
tf_transform_output: tft.TFTransformOutput,
batch_size: int) -> tf.data.Dataset:
"""
Generates features and label for tuning/training.
Args:
file_pattern: List of paths or patterns of input tfrecord files.
data_accessor: DataAccessor for converting input to RecordBatch.
tf_transform_output: A TFTransformOutput.
batch_size: representing the number of consecutive elements of returned
dataset to combine in a single batch
Returns:
A dataset that contains (features, target_tensor) tuple where features is a
dictionary of Tensors, and target_tensor is a single Tensor that is a concatenated tensor of all the
feature values.
"""
dataset = data_accessor.tf_dataset_factory(
file_pattern,
tfxio.TensorFlowDatasetOptions(batch_size = batch_size),
tf_transform_output.transformed_metadata.schema
)
dataset = dataset.map(lambda x: create_target_values(features_dict = x))
return dataset.repeat()
I am trying to use the output of a neural network to transform data inside tf.data.dataset. Specifically, I am using a Delta-Encoder to manipulate embeddings inside the tf.data pipeline. In so doing, however, I get the following error:
OperatorNotAllowedInGraphError: iterating over `tf.Tensor` is not allowed in Graph execution. Use Eager execution or decorate this function with #tf.function.
I have searched the dataset pipeline page and stack overflow, but I could not find something that addresses my question. In the code below I am using an Autoencoder, as it yields an identical error with more concise code.
The offending part seems to be
[[x,]] = tf.py_function(Auto_Func, [x], [tf.float32])
inside
tf_auto_transform.
num_embeddings = 100
input_dims = 1000
embeddings = np.random.normal(size = (num_embeddings, input_dims)).astype(np.float32)
target = np.zeros(num_embeddings)
#creating Autoencoder
inp = Input(shape = (input_dims,), name ='input')
hidden = Dense(10, activation = 'relu', name = 'hidden')(inp)
out = Dense(input_dims, activation = 'relu', name='output')(hidden)
auto_encoder = tf.keras.models.Model(inputs =inp, outputs=out)
Auto_Func = tf.keras.backend.function(inputs = Autoencoder.get_layer(name='input').input,
outputs = Autoencoder.get_layer(name='output').input )
#Autoencoder transform for dataset.map
def tf_auto_transform(x, target):
x_shape = x.shape
##tf.function
#def func(x):
# return tf.py_function(Auto_Func, [x], [tf.float32])
#[[x,]] = func(x)
[[x,]] = tf.py_function(Auto_Func, [x], [tf.float32])
x.set_shape(x_shape)
return x, target
def get_dataset(X,y, batch_size = 32):
train_ds = tf.data.Dataset.from_tensor_slices((X, y))
train_ds = train_ds.map(tf_auto_transform)
train_ds = train_ds.batch(batch_size)
return train_ds
dataset = get_dataset(embeddings, target, 2)
The above code yields the following error:
OperatorNotAllowedInGraphError: iterating over `tf.Tensor` is not allowed in Graph execution. Use Eager execution or decorate this function with #tf.function.
I tried to eliminate the error by running the commented out section of the tf_auto_transform function, but the error persisted.
SideNote: While it is true that the Delta encoder paper has code, it is written in tf 1.x. I am trying to use tf 2.x with the tf functional API instead. Thank you for your help!
At the risk of outing myself as a n00b, the answer is to switch the order of the map and batch functions. I am trying to apply a neural network to make some changes on data. tf.keras models take batches as input, not individual samples. By batching the data first, I can run batches through my nn.
def get_dataset(X,y, batch_size = 32):
train_ds = tf.data.Dataset.from_tensor_slices((X, y))
#The changed order
train_ds = train_ds.batch(batch_size)
train_ds = train_ds.map(tf_auto_transform)**strong text**
return train_ds
It really is that simple.
I am trying to implement a model in keras that will have multiple inputs:
image (200x200)
some numbers (1x50)
three 1d signals (1x50000, 2x100000)
To feed that model, I want to write a generator to use with tf.data.Dataset.from_generator. From the docs of from_generator, its not clear to me how I should provide its parameters output_types, output_shapes. Can anyone help me with this?
I had a similar issue, and it took me many tries to get the structure right for those inputs. Here's an example of a network with 3 inputs and 2 outputs, complete to the .fit call.
The following works in tensorflow 2.1.0
import tensorflow as tf
import numpy as np
def generator(N=10):
"""
Returns tuple of (inputs,outputs) where
inputs = (inp1,inp2,inp2)
outputs = (out1,out2)
"""
dt=np.float32
for i in range(N):
inputs = (np.random.rand(N,3,3,1).astype(dt),
np.random.rand(N,3,3,1).astype(dt),
np.random.rand(N,3,3,1).astype(dt))
outputs = (np.random.rand(N,3,3,1).astype(dt),
np.random.rand(N,3,3,1).astype(dt))
yield inputs,outputs
# Create dataset from generator
types = ( (tf.float32,tf.float32,tf.float32),
(tf.float32,tf.float32) )
shapes = (([None,3,3,1],[None,3,3,1],[None,3,3,1]),
([None,3,3,1],[None,3,3,1]))
data = tf.data.Dataset.from_generator(generator,
output_types=types,
output_shapes=shapes
)
# Define a model
inp1 = tf.keras.Input(shape=(3,3,1),name='inp1')
inp2 = tf.keras.Input(shape=(3,3,1),name='inp2')
inp3 = tf.keras.Input(shape=(3,3,1),name='inp3')
out1 = tf.keras.layers.Conv2D(1,kernel_size=3,padding='same')(inp1)
out2 = tf.keras.layers.Conv2D(1,kernel_size=3,padding='same')(inp2)
model = tf.keras.Model(inputs=[inp1,inp2,inp3],outputs=[out1,out2])
model.compile(loss=['mse','mse'])
# Train
model.fit(data)
So assuming you have a generator that is similar to this mock:
def dummy_generator():
number_of_records = 100
for i in range(100):
an_image = tf.random.uniform((200,200,3))
some_numbers = tf.random.uniform((50,))
signal1 = tf.random.uniform((50000,))
signal2 = tf.random.uniform((100000,))
signal3 = tf.random.uniform((100000,))
yield an_image, some_numbers, signal1, signal2, signal3
each record is of datatype float32 so the output types are easy:
out_types = (tf.float32, tf.float32, tf.float32, tf.float32, tf.float32)
for the output shapes we just list the shapes in the same order:
out_shapes = ((200,200,3), (50,), (50000,), (100000,), (100000,))
so now we can just call from_generator:
ds = tf.data.Dataset.from_generator(dummy_generator,
output_types=out_types,
output_shapes=out_shapes)
model.fit([input_1, input_2, input_3], y, epochs=EPOCHS)
You got to have n(3 in the case above) input layers in your model.
from keras.models import load_model
import h5py
# sq_model.save_weights('sq_model_weights.h5')
# res_model.save_weights('res_model_weights.h5')
# model.save('my_model.h5')
# dense_model.save_weights('dense_model_v3_weights.h5')
sq_model.load_weights('sq_model_weights.h5')
res_model.load_weights('res_model_weights.h5')
dense_model.load_weights('dense_model_v2_weights.h5')
models = [sq_model, res_model, dense_model]
model_input = Input((3,32,32))
def ensemble(models, model_input):
outputs = [model.outputs[0] for model in models]
y = Average()(outputs)
model = Model(inputs = model_input, outputs = y, name='ensemble')
return model
ensemble_model = ensemble(models,model_input)
I am getting the following error when I run the above code:
RuntimeError: Graph disconnected: cannot obtain value for tensor Tensor("input_2:0", shape=(?, 3, 32, 32), dtype=float32) at layer "input_2". The following previous layers were accessed without issue: []
You have three models, each of them with a separate input. In your call to
model = Model(inputs = model_input, outputs = y, name='ensemble')
you specify a new Model. Its input should be your model_input, and the outputs should be your averaged outputs.
But you forgot to actually connect your three models to your input. So you have a disconnected model containing the loose input layer model_input and the ensemble, with each of the three models contained in the ensemble waiting for an input on its own input layer (so 4 input layers in total).
Changing
outputs = [model.outputs[0] for model in models]
to
outputs = [model(model_inputs) for model in models]
should do the trick. It calls each of the models on model_input and gives the corresponding outputs.
Changing
outputs = [model.outputs[0] for model in models]
to
outputs = [model(model_input) for model in models]
worked for me