前処理レイヤーを使用する

import numpy as np
import tensorflow as tf
from tensorflow.keras import layers

data = np.array([[0.1, 0.2, 0.3], [0.8, 0.9, 1.0], [1.5, 1.6, 1.7],])
layer = layers.Normalization()
layer.adapt(data)
normalized_data = layer(data)

print("Features mean: %.2f" % (normalized_data.numpy().mean()))
print("Features std: %.2f" % (normalized_data.numpy().std()))

2022-12-14 21:28:56.053993: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory
2022-12-14 21:28:56.054084: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory
2022-12-14 21:28:56.054094: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
Features mean: -0.00
Features std: 1.00

data = [
    "ξεῖν᾽, ἦ τοι μὲν ὄνειροι ἀμήχανοι ἀκριτόμυθοι",
    "γίγνοντ᾽, οὐδέ τι πάντα τελείεται ἀνθρώποισι.",
    "δοιαὶ γάρ τε πύλαι ἀμενηνῶν εἰσὶν ὀνείρων:",
    "αἱ μὲν γὰρ κεράεσσι τετεύχαται, αἱ δ᾽ ἐλέφαντι:",
    "τῶν οἳ μέν κ᾽ ἔλθωσι διὰ πριστοῦ ἐλέφαντος,",
    "οἵ ῥ᾽ ἐλεφαίρονται, ἔπε᾽ ἀκράαντα φέροντες:",
    "οἱ δὲ διὰ ξεστῶν κεράων ἔλθωσι θύραζε,",
    "οἵ ῥ᾽ ἔτυμα κραίνουσι, βροτῶν ὅτε κέν τις ἴδηται.",
]
layer = layers.TextVectorization()
layer.adapt(data)
vectorized_text = layer(data)
print(vectorized_text)

tf.Tensor(
[[37 12 25  5  9 20 21  0  0]
 [51 34 27 33 29 18  0  0  0]
 [49 52 30 31 19 46 10  0  0]
 [ 7  5 50 43 28  7 47 17  0]
 [24 35 39 40  3  6 32 16  0]
 [ 4  2 15 14 22 23  0  0  0]
 [36 48  6 38 42  3 45  0  0]
 [ 4  2 13 41 53  8 44 26 11]], shape=(8, 9), dtype=int64)

vocab = ["a", "b", "c", "d"]
data = tf.constant([["a", "c", "d"], ["d", "z", "b"]])
layer = layers.StringLookup(vocabulary=vocab)
vectorized_data = layer(data)
print(vectorized_data)

tf.Tensor(
[[1 3 4]
 [4 0 2]], shape=(2, 3), dtype=int64)

inputs = keras.Input(shape=input_shape)
x = preprocessing_layer(inputs)
outputs = rest_of_the_model(x)
model = keras.Model(inputs, outputs)

dataset = dataset.map(lambda x, y: (preprocessing_layer(x), y))

dataset = dataset.map(lambda x, y: (preprocessing_layer(x), y))
dataset = dataset.prefetch(tf.data.AUTOTUNE)
model.fit(dataset, ...)

inputs = keras.Input(shape=input_shape)
x = preprocessing_layer(inputs)
outputs = training_model(x)
inference_model = keras.Model(inputs, outputs)

from tensorflow import keras
from tensorflow.keras import layers

# Create a data augmentation stage with horizontal flipping, rotations, zooms
data_augmentation = keras.Sequential(
    [
        layers.RandomFlip("horizontal"),
        layers.RandomRotation(0.1),
        layers.RandomZoom(0.1),
    ]
)

# Load some data
(x_train, y_train), _ = keras.datasets.cifar10.load_data()
input_shape = x_train.shape[1:]
classes = 10

# Create a tf.data pipeline of augmented images (and their labels)
train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
train_dataset = train_dataset.batch(16).map(lambda x, y: (data_augmentation(x), y))


# Create a model and train it on the augmented image data
inputs = keras.Input(shape=input_shape)
x = layers.Rescaling(1.0 / 255)(inputs)  # Rescale inputs
outputs = keras.applications.ResNet50(  # Add the rest of the model
    weights=None, input_shape=input_shape, classes=classes
)(x)
model = keras.Model(inputs, outputs)
model.compile(optimizer="rmsprop", loss="sparse_categorical_crossentropy")
model.fit(train_dataset, steps_per_epoch=5)

Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz
170498071/170498071 [==============================] - 2s 0us/step
WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.9/site-packages/tensorflow/python/autograph/pyct/static_analysis/liveness.py:83: Analyzer.lamba_check (from tensorflow.python.autograph.pyct.static_analysis.liveness) is deprecated and will be removed after 2023-09-23.
Instructions for updating:
Lambda fuctions will be no more assumed to be used in the statement where they are used, or at least in the same block. https://github.com/tensorflow/tensorflow/issues/56089
WARNING:tensorflow:Using a while_loop for converting RngReadAndSkip cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting Bitcast cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting Bitcast cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting StatelessRandomUniformV2 cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting ImageProjectiveTransformV3 cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting RngReadAndSkip cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting Bitcast cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting Bitcast cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting StatelessRandomUniformV2 cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting ImageProjectiveTransformV3 cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting RngReadAndSkip cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting Bitcast cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting Bitcast cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting StatelessRandomUniformV2 cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting ImageProjectiveTransformV3 cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting RngReadAndSkip cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting Bitcast cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting Bitcast cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting StatelessRandomUniformV2 cause there is no registered converter for this op.
WARNING:tensorflow:Using a while_loop for converting ImageProjectiveTransformV3 cause there is no registered converter for this op.
5/5 [==============================] - 23s 38ms/step - loss: 10.3676
<keras.callbacks.History at 0x7f10440baa30>

# Load some data
(x_train, y_train), _ = keras.datasets.cifar10.load_data()
x_train = x_train.reshape((len(x_train), -1))
input_shape = x_train.shape[1:]
classes = 10

# Create a Normalization layer and set its internal state using the training data
normalizer = layers.Normalization()
normalizer.adapt(x_train)

# Create a model that include the normalization layer
inputs = keras.Input(shape=input_shape)
x = normalizer(inputs)
outputs = layers.Dense(classes, activation="softmax")(x)
model = keras.Model(inputs, outputs)

# Train the model
model.compile(optimizer="adam", loss="sparse_categorical_crossentropy")
model.fit(x_train, y_train)

1563/1563 [==============================] - 4s 2ms/step - loss: 2.1255
<keras.callbacks.History at 0x7f0fb423d760>

# Define some toy data
data = tf.constant([["a"], ["b"], ["c"], ["b"], ["c"], ["a"]])

# Use StringLookup to build an index of the feature values and encode output.
lookup = layers.StringLookup(output_mode="one_hot")
lookup.adapt(data)

# Convert new test data (which includes unknown feature values)
test_data = tf.constant([["a"], ["b"], ["c"], ["d"], ["e"], [""]])
encoded_data = lookup(test_data)
print(encoded_data)

tf.Tensor(
[[0. 0. 0. 1.]
 [0. 0. 1. 0.]
 [0. 1. 0. 0.]
 [1. 0. 0. 0.]
 [1. 0. 0. 0.]
 [1. 0. 0. 0.]], shape=(6, 4), dtype=float32)

# Define some toy data
data = tf.constant([[10], [20], [20], [10], [30], [0]])

# Use IntegerLookup to build an index of the feature values and encode output.
lookup = layers.IntegerLookup(output_mode="one_hot")
lookup.adapt(data)

# Convert new test data (which includes unknown feature values)
test_data = tf.constant([[10], [10], [20], [50], [60], [0]])
encoded_data = lookup(test_data)
print(encoded_data)

tf.Tensor(
[[0. 0. 1. 0. 0.]
 [0. 0. 1. 0. 0.]
 [0. 1. 0. 0. 0.]
 [1. 0. 0. 0. 0.]
 [1. 0. 0. 0. 0.]
 [0. 0. 0. 0. 1.]], shape=(6, 5), dtype=float32)

# Sample data: 10,000 random integers with values between 0 and 100,000
data = np.random.randint(0, 100000, size=(10000, 1))

# Use the Hashing layer to hash the values to the range [0, 64]
hasher = layers.Hashing(num_bins=64, salt=1337)

# Use the CategoryEncoding layer to multi-hot encode the hashed values
encoder = layers.CategoryEncoding(num_tokens=64, output_mode="multi_hot")
encoded_data = encoder(hasher(data))
print(encoded_data.shape)

(10000, 64)

# Define some text data to adapt the layer
adapt_data = tf.constant(
    [
        "The Brain is wider than the Sky",
        "For put them side by side",
        "The one the other will contain",
        "With ease and You beside",
    ]
)

# Create a TextVectorization layer
text_vectorizer = layers.TextVectorization(output_mode="int")
# Index the vocabulary via `adapt()`
text_vectorizer.adapt(adapt_data)

# Try out the layer
print(
    "Encoded text:\n", text_vectorizer(["The Brain is deeper than the sea"]).numpy(),
)

# Create a simple model
inputs = keras.Input(shape=(None,), dtype="int64")
x = layers.Embedding(input_dim=text_vectorizer.vocabulary_size(), output_dim=16)(inputs)
x = layers.GRU(8)(x)
outputs = layers.Dense(1)(x)
model = keras.Model(inputs, outputs)

# Create a labeled dataset (which includes unknown tokens)
train_dataset = tf.data.Dataset.from_tensor_slices(
    (["The Brain is deeper than the sea", "for if they are held Blue to Blue"], [1, 0])
)

# Preprocess the string inputs, turning them into int sequences
train_dataset = train_dataset.batch(2).map(lambda x, y: (text_vectorizer(x), y))
# Train the model on the int sequences
print("\nTraining model...")
model.compile(optimizer="rmsprop", loss="mse")
model.fit(train_dataset)

# For inference, you can export a model that accepts strings as input
inputs = keras.Input(shape=(1,), dtype="string")
x = text_vectorizer(inputs)
outputs = model(x)
end_to_end_model = keras.Model(inputs, outputs)

# Call the end-to-end model on test data (which includes unknown tokens)
print("\nCalling end-to-end model on test string...")
test_data = tf.constant(["The one the other will absorb"])
test_output = end_to_end_model(test_data)
print("Model output:", test_output)

Encoded text:
 [[ 2 19 14  1  9  2  1]]

Training model...
1/1 [==============================] - 2s 2s/step - loss: 0.4559

Calling end-to-end model on test string...
Model output: tf.Tensor([[0.02034554]], shape=(1, 1), dtype=float32)

# Define some text data to adapt the layer
adapt_data = tf.constant(
    [
        "The Brain is wider than the Sky",
        "For put them side by side",
        "The one the other will contain",
        "With ease and You beside",
    ]
)
# Instantiate TextVectorization with "multi_hot" output_mode
# and ngrams=2 (index all bigrams)
text_vectorizer = layers.TextVectorization(output_mode="multi_hot", ngrams=2)
# Index the bigrams via `adapt()`
text_vectorizer.adapt(adapt_data)

# Try out the layer
print(
    "Encoded text:\n", text_vectorizer(["The Brain is deeper than the sea"]).numpy(),
)

# Create a simple model
inputs = keras.Input(shape=(text_vectorizer.vocabulary_size(),))
outputs = layers.Dense(1)(inputs)
model = keras.Model(inputs, outputs)

# Create a labeled dataset (which includes unknown tokens)
train_dataset = tf.data.Dataset.from_tensor_slices(
    (["The Brain is deeper than the sea", "for if they are held Blue to Blue"], [1, 0])
)

# Preprocess the string inputs, turning them into int sequences
train_dataset = train_dataset.batch(2).map(lambda x, y: (text_vectorizer(x), y))
# Train the model on the int sequences
print("\nTraining model...")
model.compile(optimizer="rmsprop", loss="mse")
model.fit(train_dataset)

# For inference, you can export a model that accepts strings as input
inputs = keras.Input(shape=(1,), dtype="string")
x = text_vectorizer(inputs)
outputs = model(x)
end_to_end_model = keras.Model(inputs, outputs)

# Call the end-to-end model on test data (which includes unknown tokens)
print("\nCalling end-to-end model on test string...")
test_data = tf.constant(["The one the other will absorb"])
test_output = end_to_end_model(test_data)
print("Model output:", test_output)

WARNING:tensorflow:5 out of the last 1567 calls to <function PreprocessingLayer.make_adapt_function.<locals>.adapt_step at 0x7f0fb46204c0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
Encoded text:
 [[1. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1. 1. 1. 0. 0. 0. 0. 0.

  0. 0. 0. 0. 1. 0. 0. 0. 0. 0. 0. 0. 1. 1. 0. 0. 0.]]

Training model...
1/1 [==============================] - 0s 375ms/step - loss: 1.1152

Calling end-to-end model on test string...
Model output: tf.Tensor([[-0.26651537]], shape=(1, 1), dtype=float32)

# Define some text data to adapt the layer
adapt_data = tf.constant(
    [
        "The Brain is wider than the Sky",
        "For put them side by side",
        "The one the other will contain",
        "With ease and You beside",
    ]
)
# Instantiate TextVectorization with "tf-idf" output_mode
# (multi-hot with TF-IDF weighting) and ngrams=2 (index all bigrams)
text_vectorizer = layers.TextVectorization(output_mode="tf-idf", ngrams=2)
# Index the bigrams and learn the TF-IDF weights via `adapt()`

with tf.device("CPU"):
    # A bug that prevents this from running on GPU for now.
    text_vectorizer.adapt(adapt_data)

# Try out the layer
print(
    "Encoded text:\n", text_vectorizer(["The Brain is deeper than the sea"]).numpy(),
)

# Create a simple model
inputs = keras.Input(shape=(text_vectorizer.vocabulary_size(),))
outputs = layers.Dense(1)(inputs)
model = keras.Model(inputs, outputs)

# Create a labeled dataset (which includes unknown tokens)
train_dataset = tf.data.Dataset.from_tensor_slices(
    (["The Brain is deeper than the sea", "for if they are held Blue to Blue"], [1, 0])
)

# Preprocess the string inputs, turning them into int sequences
train_dataset = train_dataset.batch(2).map(lambda x, y: (text_vectorizer(x), y))
# Train the model on the int sequences
print("\nTraining model...")
model.compile(optimizer="rmsprop", loss="mse")
model.fit(train_dataset)

# For inference, you can export a model that accepts strings as input
inputs = keras.Input(shape=(1,), dtype="string")
x = text_vectorizer(inputs)
outputs = model(x)
end_to_end_model = keras.Model(inputs, outputs)

# Call the end-to-end model on test data (which includes unknown tokens)
print("\nCalling end-to-end model on test string...")
test_data = tf.constant(["The one the other will absorb"])
test_output = end_to_end_model(test_data)
print("Model output:", test_output)

WARNING:tensorflow:6 out of the last 1568 calls to <function PreprocessingLayer.make_adapt_function.<locals>.adapt_step at 0x7f11fc0f68b0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
Encoded text:
 [[5.461647  1.6945957 0.        0.        0.        0.        0.

  0.        0.        0.        0.        0.        0.        0.
  0.        0.        1.0986123 1.0986123 1.0986123 0.        0.
  0.        0.        0.        0.        0.        0.        0.
  1.0986123 0.        0.        0.        0.        0.        0.
  0.        1.0986123 1.0986123 0.        0.        0.       ]]

Training model...
1/1 [==============================] - 0s 348ms/step - loss: 2.9832

Calling end-to-end model on test string...
Model output: tf.Tensor([[1.6719354]], shape=(1, 1), dtype=float32)