Questa pagina è stata tradotta dall'API Cloud Translation.

Esempi di migrazione: stimatori preconfezionati

Visualizza su TensorFlow.org

Esegui in Google Colab

Visualizza l'origine su GitHub

Scarica quaderno

Gli stimatori preconfezionati (o prefabbricati) sono stati tradizionalmente utilizzati in TensorFlow 1 come metodi semplici e veloci per addestrare modelli per una varietà di casi d'uso tipici. TensorFlow 2 fornisce semplici sostituti approssimativi per un certo numero di essi tramite i modelli Keras. Per quegli estimatori preconfezionati che non dispongono di sostituti TensorFlow 2 integrati, puoi comunque creare il tuo sostituto abbastanza facilmente.

Questa guida illustra alcuni esempi di equivalenti diretti e sostituzioni personalizzate per dimostrare come è possibile migrare i modelli derivati da tf.estimator di TensorFlow 1 a TF2 con Keras.

Vale a dire, questa guida include esempi per la migrazione:

Da tf.estimator , Classifier o Regressor di LinearEstimator in TensorFlow 1 a Keras tf.compat.v1.keras.models.LinearModel in TensorFlow 2
Da tf.estimator , Classifier o Regressor di DNNEstimator in TensorFlow 1 a un modello Keras DNN Keras personalizzato in TensorFlow 2
Da tf.estimator , Classifier o Regressor di DNNLinearCombinedEstimator in TensorFlow 1 a tf.compat.v1.keras.models.WideDeepModel in TensorFlow 2
Da tf.estimator , Classifier o Regressor di BoostedTreesEstimator in TensorFlow 1 a tf.compat.v1.keras.models.WideDeepModel in TensorFlow 2

Un precursore comune per l'addestramento di un modello è la preelaborazione delle funzionalità, che viene eseguita per i modelli TensorFlow 1 Estimator con tf.feature_column . Per ulteriori informazioni sulla preelaborazione delle funzionalità in TensorFlow 2, vedere questa guida sulla migrazione delle colonne delle funzionalità .

Impostare

Inizia con un paio di importazioni TensorFlow necessarie,

pip install tensorflow_decision_forests

import keras
import pandas as pd
import tensorflow as tf
import tensorflow.compat.v1 as tf1
import tensorflow_decision_forests as tfdf

WARNING:root:TF Parameter Server distributed training not available (this is expected for the pre-build release).

preparare alcuni semplici dati per la dimostrazione dal set di dati Titanic standard,

x_train = pd.read_csv('https://storage.googleapis.com/tf-datasets/titanic/train.csv')
x_eval = pd.read_csv('https://storage.googleapis.com/tf-datasets/titanic/eval.csv')
x_train['sex'].replace(('male', 'female'), (0, 1), inplace=True)
x_eval['sex'].replace(('male', 'female'), (0, 1), inplace=True)

x_train['alone'].replace(('n', 'y'), (0, 1), inplace=True)
x_eval['alone'].replace(('n', 'y'), (0, 1), inplace=True)

x_train['class'].replace(('First', 'Second', 'Third'), (1, 2, 3), inplace=True)
x_eval['class'].replace(('First', 'Second', 'Third'), (1, 2, 3), inplace=True)

x_train.drop(['embark_town', 'deck'], axis=1, inplace=True)
x_eval.drop(['embark_town', 'deck'], axis=1, inplace=True)

y_train = x_train.pop('survived')
y_eval = x_eval.pop('survived')

# Data setup for TensorFlow 1 with `tf.estimator`
def _input_fn():
  return tf1.data.Dataset.from_tensor_slices((dict(x_train), y_train)).batch(32)


def _eval_input_fn():
  return tf1.data.Dataset.from_tensor_slices((dict(x_eval), y_eval)).batch(32)


FEATURE_NAMES = [
    'age', 'fare', 'sex', 'n_siblings_spouses', 'parch', 'class', 'alone'
]

feature_columns = []
for fn in FEATURE_NAMES:
  feat_col = tf1.feature_column.numeric_column(fn, dtype=tf.float32)
  feature_columns.append(feat_col)

e creare un metodo per creare un'istanza di un ottimizzatore di campioni semplicistico da utilizzare con i nostri vari modelli TensorFlow 1 Estimator e TensorFlow 2 Keras.

def create_sample_optimizer(tf_version):
  if tf_version == 'tf1':
    optimizer = lambda: tf.keras.optimizers.Ftrl(
        l1_regularization_strength=0.001,
        learning_rate=tf1.train.exponential_decay(
            learning_rate=0.1,
            global_step=tf1.train.get_global_step(),
            decay_steps=10000,
            decay_rate=0.9))
  elif tf_version == 'tf2':
    optimizer = tf.keras.optimizers.Ftrl(
        l1_regularization_strength=0.001,
        learning_rate=tf.keras.optimizers.schedules.ExponentialDecay(
            initial_learning_rate=0.1, decay_steps=10000, decay_rate=0.9))
  return optimizer

Esempio 1: Migrazione da LinearEstimator

TF1: Utilizzo di LinearEstimator

In TensorFlow 1, puoi utilizzare tf.estimator.LinearEstimator per creare un modello lineare di base per problemi di regressione e classificazione.

linear_estimator = tf.estimator.LinearEstimator(
    head=tf.estimator.BinaryClassHead(),
    feature_columns=feature_columns,
    optimizer=create_sample_optimizer('tf1'))

INFO:tensorflow:Using default config.
INFO:tensorflow:Using default config.
WARNING:tensorflow:Using temporary folder as model directory: /tmp/tmpvoycvffz
WARNING:tensorflow:Using temporary folder as model directory: /tmp/tmpvoycvffz
INFO:tensorflow:Using config: {'_model_dir': '/tmp/tmpvoycvffz', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true
graph_options {
  rewrite_options {
    meta_optimizer_iterations: ONE
  }
}
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}
INFO:tensorflow:Using config: {'_model_dir': '/tmp/tmpvoycvffz', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true
graph_options {
  rewrite_options {
    meta_optimizer_iterations: ONE
  }
}
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}

linear_estimator.train(input_fn=_input_fn, steps=100)
linear_estimator.evaluate(input_fn=_eval_input_fn, steps=10)

WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/training/training_util.py:401: Variable.initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.
WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/training/training_util.py:401: Variable.initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Calling model_fn.
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/canned/linear.py:1478: UserWarning: `layer.add_variable` is deprecated and will be removed in a future version. Please use `layer.add_weight` method instead.
  getter=tf.compat.v1.get_variable)
WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/keras/optimizer_v2/ftrl.py:149: calling Constant.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/keras/optimizer_v2/ftrl.py:149: calling Constant.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0...
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0...
INFO:tensorflow:Saving checkpoints for 0 into /tmp/tmpvoycvffz/model.ckpt.
INFO:tensorflow:Saving checkpoints for 0 into /tmp/tmpvoycvffz/model.ckpt.
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
INFO:tensorflow:loss = 0.6931472, step = 0
INFO:tensorflow:loss = 0.6931472, step = 0
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 20...
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 20...
INFO:tensorflow:Saving checkpoints for 20 into /tmp/tmpvoycvffz/model.ckpt.
INFO:tensorflow:Saving checkpoints for 20 into /tmp/tmpvoycvffz/model.ckpt.
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 20...
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 20...
INFO:tensorflow:Loss for final step: 0.55268794.
INFO:tensorflow:Loss for final step: 0.55268794.
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Starting evaluation at 2022-01-29T02:21:45
INFO:tensorflow:Starting evaluation at 2022-01-29T02:21:45
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Restoring parameters from /tmp/tmpvoycvffz/model.ckpt-20
INFO:tensorflow:Restoring parameters from /tmp/tmpvoycvffz/model.ckpt-20
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Evaluation [1/10]
INFO:tensorflow:Evaluation [1/10]
INFO:tensorflow:Evaluation [2/10]
INFO:tensorflow:Evaluation [2/10]
INFO:tensorflow:Evaluation [3/10]
INFO:tensorflow:Evaluation [3/10]
INFO:tensorflow:Evaluation [4/10]
INFO:tensorflow:Evaluation [4/10]
INFO:tensorflow:Evaluation [5/10]
INFO:tensorflow:Evaluation [5/10]
INFO:tensorflow:Evaluation [6/10]
INFO:tensorflow:Evaluation [6/10]
INFO:tensorflow:Evaluation [7/10]
INFO:tensorflow:Evaluation [7/10]
INFO:tensorflow:Evaluation [8/10]
INFO:tensorflow:Evaluation [8/10]
INFO:tensorflow:Evaluation [9/10]
INFO:tensorflow:Evaluation [9/10]
INFO:tensorflow:Inference Time : 0.50224s
INFO:tensorflow:Inference Time : 0.50224s
INFO:tensorflow:Finished evaluation at 2022-01-29-02:21:45
INFO:tensorflow:Finished evaluation at 2022-01-29-02:21:45
INFO:tensorflow:Saving dict for global step 20: accuracy = 0.70075756, accuracy_baseline = 0.625, auc = 0.75472915, auc_precision_recall = 0.65362054, average_loss = 0.5759378, global_step = 20, label/mean = 0.375, loss = 0.5704812, precision = 0.6388889, prediction/mean = 0.41331062, recall = 0.46464646
INFO:tensorflow:Saving dict for global step 20: accuracy = 0.70075756, accuracy_baseline = 0.625, auc = 0.75472915, auc_precision_recall = 0.65362054, average_loss = 0.5759378, global_step = 20, label/mean = 0.375, loss = 0.5704812, precision = 0.6388889, prediction/mean = 0.41331062, recall = 0.46464646
INFO:tensorflow:Saving 'checkpoint_path' summary for global step 20: /tmp/tmpvoycvffz/model.ckpt-20
INFO:tensorflow:Saving 'checkpoint_path' summary for global step 20: /tmp/tmpvoycvffz/model.ckpt-20
{'accuracy': 0.70075756,
 'accuracy_baseline': 0.625,
 'auc': 0.75472915,
 'auc_precision_recall': 0.65362054,
 'average_loss': 0.5759378,
 'label/mean': 0.375,
 'loss': 0.5704812,
 'precision': 0.6388889,
 'prediction/mean': 0.41331062,
 'recall': 0.46464646,
 'global_step': 20}

TF2: Utilizzo di Keras LinearModel

In TensorFlow 2, puoi creare un'istanza di Keras tf.compat.v1.keras.models.LinearModel che è il sostituto di tf.estimator.LinearEstimator . Il percorso tf.compat.v1.keras viene utilizzato per indicare che il modello predefinito esiste per la compatibilità.

linear_model = tf.compat.v1.keras.experimental.LinearModel()
linear_model.compile(loss='mse', optimizer=create_sample_optimizer('tf2'), metrics=['accuracy'])
linear_model.fit(x_train, y_train, epochs=10)
linear_model.evaluate(x_eval, y_eval, return_dict=True)

Epoch 1/10
20/20 [==============================] - 0s 2ms/step - loss: 2.8157 - accuracy: 0.6300
Epoch 2/10
20/20 [==============================] - 0s 2ms/step - loss: 0.2758 - accuracy: 0.6427
Epoch 3/10
20/20 [==============================] - 0s 2ms/step - loss: 0.2470 - accuracy: 0.6699
Epoch 4/10
20/20 [==============================] - 0s 2ms/step - loss: 0.1954 - accuracy: 0.7177
Epoch 5/10
20/20 [==============================] - 0s 2ms/step - loss: 0.1931 - accuracy: 0.7145
Epoch 6/10
20/20 [==============================] - 0s 2ms/step - loss: 0.1816 - accuracy: 0.7496
Epoch 7/10
20/20 [==============================] - 0s 2ms/step - loss: 0.1766 - accuracy: 0.7751
Epoch 8/10
20/20 [==============================] - 0s 2ms/step - loss: 0.2198 - accuracy: 0.7560
Epoch 9/10
20/20 [==============================] - 0s 2ms/step - loss: 0.1657 - accuracy: 0.7959
Epoch 10/10
20/20 [==============================] - 0s 2ms/step - loss: 0.1738 - accuracy: 0.7959
9/9 [==============================] - 0s 2ms/step - loss: 0.2278 - accuracy: 0.6780
{'loss': 0.22778697311878204, 'accuracy': 0.6780303120613098}

Esempio 2: Migrazione da DNNEstimator

TF1: Utilizzo di DNNEstimator

In TensorFlow 1, è possibile utilizzare tf.estimator.DNNEstimator per creare un modello DNN di base per problemi di regressione e classificazione.

dnn_estimator = tf.estimator.DNNEstimator(
    head=tf.estimator.BinaryClassHead(),
    feature_columns=feature_columns,
    hidden_units=[128],
    activation_fn=tf.nn.relu,
    optimizer=create_sample_optimizer('tf1'))

INFO:tensorflow:Using default config.
INFO:tensorflow:Using default config.
WARNING:tensorflow:Using temporary folder as model directory: /tmp/tmphckb8f81
WARNING:tensorflow:Using temporary folder as model directory: /tmp/tmphckb8f81
INFO:tensorflow:Using config: {'_model_dir': '/tmp/tmphckb8f81', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true
graph_options {
  rewrite_options {
    meta_optimizer_iterations: ONE
  }
}
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}
INFO:tensorflow:Using config: {'_model_dir': '/tmp/tmphckb8f81', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true
graph_options {
  rewrite_options {
    meta_optimizer_iterations: ONE
  }
}
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}

dnn_estimator.train(input_fn=_input_fn, steps=100)
dnn_estimator.evaluate(input_fn=_eval_input_fn, steps=10)

INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0...
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0...
INFO:tensorflow:Saving checkpoints for 0 into /tmp/tmphckb8f81/model.ckpt.
INFO:tensorflow:Saving checkpoints for 0 into /tmp/tmphckb8f81/model.ckpt.
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
INFO:tensorflow:loss = 2.1811047, step = 0
INFO:tensorflow:loss = 2.1811047, step = 0
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 20...
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 20...
INFO:tensorflow:Saving checkpoints for 20 into /tmp/tmphckb8f81/model.ckpt.
INFO:tensorflow:Saving checkpoints for 20 into /tmp/tmphckb8f81/model.ckpt.
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 20...
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 20...
INFO:tensorflow:Loss for final step: 0.5881681.
INFO:tensorflow:Loss for final step: 0.5881681.
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Starting evaluation at 2022-01-29T02:21:48
INFO:tensorflow:Starting evaluation at 2022-01-29T02:21:48
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Restoring parameters from /tmp/tmphckb8f81/model.ckpt-20
INFO:tensorflow:Restoring parameters from /tmp/tmphckb8f81/model.ckpt-20
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Evaluation [1/10]
INFO:tensorflow:Evaluation [1/10]
INFO:tensorflow:Evaluation [2/10]
INFO:tensorflow:Evaluation [2/10]
INFO:tensorflow:Evaluation [3/10]
INFO:tensorflow:Evaluation [3/10]
INFO:tensorflow:Evaluation [4/10]
INFO:tensorflow:Evaluation [4/10]
INFO:tensorflow:Evaluation [5/10]
INFO:tensorflow:Evaluation [5/10]
INFO:tensorflow:Evaluation [6/10]
INFO:tensorflow:Evaluation [6/10]
INFO:tensorflow:Evaluation [7/10]
INFO:tensorflow:Evaluation [7/10]
INFO:tensorflow:Evaluation [8/10]
INFO:tensorflow:Evaluation [8/10]
INFO:tensorflow:Evaluation [9/10]
INFO:tensorflow:Evaluation [9/10]
INFO:tensorflow:Inference Time : 0.47075s
INFO:tensorflow:Inference Time : 0.47075s
INFO:tensorflow:Finished evaluation at 2022-01-29-02:21:49
INFO:tensorflow:Finished evaluation at 2022-01-29-02:21:49
INFO:tensorflow:Saving dict for global step 20: accuracy = 0.7083333, accuracy_baseline = 0.625, auc = 0.70716256, auc_precision_recall = 0.6146256, average_loss = 0.60399944, global_step = 20, label/mean = 0.375, loss = 0.5986442, precision = 0.6486486, prediction/mean = 0.41256863, recall = 0.4848485
INFO:tensorflow:Saving dict for global step 20: accuracy = 0.7083333, accuracy_baseline = 0.625, auc = 0.70716256, auc_precision_recall = 0.6146256, average_loss = 0.60399944, global_step = 20, label/mean = 0.375, loss = 0.5986442, precision = 0.6486486, prediction/mean = 0.41256863, recall = 0.4848485
INFO:tensorflow:Saving 'checkpoint_path' summary for global step 20: /tmp/tmphckb8f81/model.ckpt-20
INFO:tensorflow:Saving 'checkpoint_path' summary for global step 20: /tmp/tmphckb8f81/model.ckpt-20
{'accuracy': 0.7083333,
 'accuracy_baseline': 0.625,
 'auc': 0.70716256,
 'auc_precision_recall': 0.6146256,
 'average_loss': 0.60399944,
 'label/mean': 0.375,
 'loss': 0.5986442,
 'precision': 0.6486486,
 'prediction/mean': 0.41256863,
 'recall': 0.4848485,
 'global_step': 20}

TF2: utilizzo di Keras per creare un modello DNN personalizzato

In TensorFlow 2, puoi creare un modello DNN personalizzato da sostituire a quello generato da tf.estimator.DNNEstimator , con livelli simili di personalizzazione specificati dall'utente (ad esempio, come nell'esempio precedente, la possibilità di personalizzare un ottimizzatore di modello scelto) .

Un flusso di lavoro simile può essere utilizzato per sostituire tf.estimator.experimental.RNNEstimator con un modello RNN Keras. Keras fornisce una serie di scelte integrate e personalizzabili tramite tf.keras.layers.RNN , tf.keras.layers.LSTM e tf.keras.layers.GRU - vedere qui per maggiori dettagli.

dnn_model = tf.keras.models.Sequential(
    [tf.keras.layers.Dense(128, activation='relu'),
     tf.keras.layers.Dense(1)])

dnn_model.compile(loss='mse', optimizer=create_sample_optimizer('tf2'), metrics=['accuracy'])

dnn_model.fit(x_train, y_train, epochs=10)
dnn_model.evaluate(x_eval, y_eval, return_dict=True)

Epoch 1/10
20/20 [==============================] - 0s 2ms/step - loss: 551.2993 - accuracy: 0.5997
Epoch 2/10
20/20 [==============================] - 0s 2ms/step - loss: 16.8562 - accuracy: 0.6427
Epoch 3/10
20/20 [==============================] - 0s 2ms/step - loss: 0.3048 - accuracy: 0.7161
Epoch 4/10
20/20 [==============================] - 0s 2ms/step - loss: 0.2475 - accuracy: 0.7416
Epoch 5/10
20/20 [==============================] - 0s 2ms/step - loss: 0.2334 - accuracy: 0.7512
Epoch 6/10
20/20 [==============================] - 0s 2ms/step - loss: 0.2200 - accuracy: 0.7416
Epoch 7/10
20/20 [==============================] - 0s 2ms/step - loss: 0.2012 - accuracy: 0.7656
Epoch 8/10
20/20 [==============================] - 0s 2ms/step - loss: 0.2025 - accuracy: 0.7624
Epoch 9/10
20/20 [==============================] - 0s 2ms/step - loss: 0.2185 - accuracy: 0.7703
Epoch 10/10
20/20 [==============================] - 0s 2ms/step - loss: 0.2046 - accuracy: 0.7687
9/9 [==============================] - 0s 2ms/step - loss: 0.2227 - accuracy: 0.6856
{'loss': 0.2227054387331009, 'accuracy': 0.685606062412262}

Esempio 3: Migrazione da DNNLinearCombinedEstimator

TF1: Utilizzo di DNNLinearCombinedEstimator

In TensorFlow 1, puoi utilizzare tf.estimator.DNNLinearCombinedEstimator per creare un modello combinato di base per problemi di regressione e classificazione con capacità di personalizzazione sia per i suoi componenti lineari che DNN.

optimizer = create_sample_optimizer('tf1')

combined_estimator = tf.estimator.DNNLinearCombinedEstimator(
    head=tf.estimator.BinaryClassHead(),
    # Wide settings
    linear_feature_columns=feature_columns,
    linear_optimizer=optimizer,
    # Deep settings
    dnn_feature_columns=feature_columns,
    dnn_hidden_units=[128],
    dnn_optimizer=optimizer)

INFO:tensorflow:Using default config.
INFO:tensorflow:Using default config.
WARNING:tensorflow:Using temporary folder as model directory: /tmp/tmpwl5e5eaq
WARNING:tensorflow:Using temporary folder as model directory: /tmp/tmpwl5e5eaq
INFO:tensorflow:Using config: {'_model_dir': '/tmp/tmpwl5e5eaq', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true
graph_options {
  rewrite_options {
    meta_optimizer_iterations: ONE
  }
}
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}
INFO:tensorflow:Using config: {'_model_dir': '/tmp/tmpwl5e5eaq', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true
graph_options {
  rewrite_options {
    meta_optimizer_iterations: ONE
  }
}
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}

combined_estimator.train(input_fn=_input_fn, steps=100)
combined_estimator.evaluate(input_fn=_eval_input_fn, steps=10)

INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Calling model_fn.
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/canned/linear.py:1478: UserWarning: `layer.add_variable` is deprecated and will be removed in a future version. Please use `layer.add_weight` method instead.
  getter=tf.compat.v1.get_variable)
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0...
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0...
INFO:tensorflow:Saving checkpoints for 0 into /tmp/tmpwl5e5eaq/model.ckpt.
INFO:tensorflow:Saving checkpoints for 0 into /tmp/tmpwl5e5eaq/model.ckpt.
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
INFO:tensorflow:loss = 2.5475807, step = 0
INFO:tensorflow:loss = 2.5475807, step = 0
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 20...
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 20...
INFO:tensorflow:Saving checkpoints for 20 into /tmp/tmpwl5e5eaq/model.ckpt.
INFO:tensorflow:Saving checkpoints for 20 into /tmp/tmpwl5e5eaq/model.ckpt.
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 20...
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 20...
INFO:tensorflow:Loss for final step: 0.58060575.
INFO:tensorflow:Loss for final step: 0.58060575.
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Starting evaluation at 2022-01-29T02:21:53
INFO:tensorflow:Starting evaluation at 2022-01-29T02:21:53
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Restoring parameters from /tmp/tmpwl5e5eaq/model.ckpt-20
INFO:tensorflow:Restoring parameters from /tmp/tmpwl5e5eaq/model.ckpt-20
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Evaluation [1/10]
INFO:tensorflow:Evaluation [1/10]
INFO:tensorflow:Evaluation [2/10]
INFO:tensorflow:Evaluation [2/10]
INFO:tensorflow:Evaluation [3/10]
INFO:tensorflow:Evaluation [3/10]
INFO:tensorflow:Evaluation [4/10]
INFO:tensorflow:Evaluation [4/10]
INFO:tensorflow:Evaluation [5/10]
INFO:tensorflow:Evaluation [5/10]
INFO:tensorflow:Evaluation [6/10]
INFO:tensorflow:Evaluation [6/10]
INFO:tensorflow:Evaluation [7/10]
INFO:tensorflow:Evaluation [7/10]
INFO:tensorflow:Evaluation [8/10]
INFO:tensorflow:Evaluation [8/10]
INFO:tensorflow:Evaluation [9/10]
INFO:tensorflow:Evaluation [9/10]
INFO:tensorflow:Inference Time : 0.54029s
INFO:tensorflow:Inference Time : 0.54029s
INFO:tensorflow:Finished evaluation at 2022-01-29-02:21:53
INFO:tensorflow:Finished evaluation at 2022-01-29-02:21:53
INFO:tensorflow:Saving dict for global step 20: accuracy = 0.6931818, accuracy_baseline = 0.625, auc = 0.73532283, auc_precision_recall = 0.630229, average_loss = 0.65179086, global_step = 20, label/mean = 0.375, loss = 0.63768697, precision = 0.60714287, prediction/mean = 0.4162652, recall = 0.5151515
INFO:tensorflow:Saving dict for global step 20: accuracy = 0.6931818, accuracy_baseline = 0.625, auc = 0.73532283, auc_precision_recall = 0.630229, average_loss = 0.65179086, global_step = 20, label/mean = 0.375, loss = 0.63768697, precision = 0.60714287, prediction/mean = 0.4162652, recall = 0.5151515
INFO:tensorflow:Saving 'checkpoint_path' summary for global step 20: /tmp/tmpwl5e5eaq/model.ckpt-20
INFO:tensorflow:Saving 'checkpoint_path' summary for global step 20: /tmp/tmpwl5e5eaq/model.ckpt-20
{'accuracy': 0.6931818,
 'accuracy_baseline': 0.625,
 'auc': 0.73532283,
 'auc_precision_recall': 0.630229,
 'average_loss': 0.65179086,
 'label/mean': 0.375,
 'loss': 0.63768697,
 'precision': 0.60714287,
 'prediction/mean': 0.4162652,
 'recall': 0.5151515,
 'global_step': 20}

TF2: Utilizzo di Keras WideDeepModel

In TensorFlow 2, puoi creare un'istanza di Keras tf.compat.v1.keras.models.WideDeepModel per sostituire quella generata da tf.estimator.DNNLinearCombinedEstimator , con livelli simili di personalizzazione specificati dall'utente (ad esempio, come in esempio precedente, la possibilità di personalizzare un ottimizzatore di modello scelto).

Questo WideDeepModel è costruito sulla base di un LinearModel costituente e di un modello DNN personalizzato, entrambi discussi nei due esempi precedenti. Se lo si desidera, è possibile utilizzare un modello lineare personalizzato al posto del Keras LinearModel integrato.

Se desideri costruire il tuo modello invece di uno stimatore fisso, dai un'occhiata a come costruire un modello keras.Sequential . Per ulteriori informazioni sulla formazione personalizzata e sugli ottimizzatori puoi anche consultare questa guida .

# Create LinearModel and DNN Model as in Examples 1 and 2
optimizer = create_sample_optimizer('tf2')

linear_model = tf.compat.v1.keras.experimental.LinearModel()
linear_model.compile(loss='mse', optimizer=optimizer, metrics=['accuracy'])
linear_model.fit(x_train, y_train, epochs=10, verbose=0)

dnn_model = tf.keras.models.Sequential(
    [tf.keras.layers.Dense(128, activation='relu'),
     tf.keras.layers.Dense(1)])
dnn_model.compile(loss='mse', optimizer=optimizer, metrics=['accuracy'])

combined_model = tf.compat.v1.keras.experimental.WideDeepModel(linear_model,
                                                               dnn_model)
combined_model.compile(
    optimizer=[optimizer, optimizer], loss='mse', metrics=['accuracy'])
combined_model.fit([x_train, x_train], y_train, epochs=10)
combined_model.evaluate(x_eval, y_eval, return_dict=True)

Epoch 1/10
20/20 [==============================] - 0s 2ms/step - loss: 1118.0448 - accuracy: 0.6715
Epoch 2/10
20/20 [==============================] - 0s 2ms/step - loss: 0.5682 - accuracy: 0.7305
Epoch 3/10
20/20 [==============================] - 0s 2ms/step - loss: 0.2719 - accuracy: 0.7671
Epoch 4/10
20/20 [==============================] - 0s 2ms/step - loss: 0.2032 - accuracy: 0.7831
Epoch 5/10
20/20 [==============================] - 0s 2ms/step - loss: 0.1911 - accuracy: 0.7783
Epoch 6/10
20/20 [==============================] - 0s 2ms/step - loss: 0.1895 - accuracy: 0.7863
Epoch 7/10
20/20 [==============================] - 0s 2ms/step - loss: 0.1882 - accuracy: 0.7863
Epoch 8/10
20/20 [==============================] - 0s 2ms/step - loss: 0.1717 - accuracy: 0.7974
Epoch 9/10
20/20 [==============================] - 0s 2ms/step - loss: 0.1701 - accuracy: 0.7927
Epoch 10/10
20/20 [==============================] - 0s 2ms/step - loss: 0.1684 - accuracy: 0.7990
9/9 [==============================] - 0s 2ms/step - loss: 0.1930 - accuracy: 0.7424
{'loss': 0.19299836456775665, 'accuracy': 0.7424242496490479}

Esempio 4: Migrazione da BoostedTreesEstimator

TF1: Utilizzo di BoostedTreesEstimator

In TensorFlow 1, è possibile utilizzare tf.estimator.BoostedTreesEstimator per creare una linea di base per creare un modello di incremento del gradiente di base utilizzando un insieme di alberi decisionali per problemi di regressione e classificazione. Questa funzionalità non è più inclusa in TensorFlow 2.

bt_estimator = tf1.estimator.BoostedTreesEstimator(
    head=tf.estimator.BinaryClassHead(),
    n_batches_per_layer=1,
    max_depth=10,
    n_trees=1000,
    feature_columns=feature_columns)

bt_estimator.train(input_fn=_input_fn, steps=1000)
bt_estimator.evaluate(input_fn=_eval_input_fn, steps=100)

TF2: Utilizzo delle foreste decisionali di TensorFlow

In TensorFlow 2, il sostituto preconfezionato più vicino per un modello generato da tf.estimator.BoostedTreesEstimator è quello creato utilizzando tfdf.keras.GradientBoostedTreesModel , che crea una sequenza addestrata in sequenza di alberi decisionali poco profondi, ciascuno progettato per "imparare" dagli errori fatto dai suoi predecessori nella sequenza.

GradientBoostedTreesModel offre più opzioni per la personalizzazione, consentendo la specifica di qualsiasi cosa, dai vincoli di profondità di base alle condizioni di arresto anticipato. Vedi qui per ulteriori dettagli sugli attributi GradientBoostedTreesModel .

gbt_model = tfdf.keras.GradientBoostedTreesModel(
    task=tfdf.keras.Task.CLASSIFICATION)
gbt_model.compile(metrics=['mse', 'accuracy'])

Use /tmp/tmpbr1acn2_ as temporary training directory

train_df, eval_df = x_train.copy(), x_eval.copy()
train_df['survived'], eval_df['survived'] = y_train, y_eval

train_dataset = tfdf.keras.pd_dataframe_to_tf_dataset(train_df, label='survived')
eval_dataset = tfdf.keras.pd_dataframe_to_tf_dataset(eval_df, label='survived')

gbt_model.fit(train_dataset)
gbt_model.evaluate(eval_dataset, return_dict=True)

Starting reading the dataset
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow_decision_forests/keras/core.py:2036: FutureWarning: In a future version of pandas all arguments of DataFrame.drop except for the argument 'labels' will be keyword-only
  features_dataframe = dataframe.drop(label, 1)
1/1 [==============================] - ETA: 0s
Dataset read in 0:00:03.161776
Training model
Model trained in 0:00:00.102649
Compiling model
1/1 [==============================] - 3s 3s/step
[INFO kernel.cc:1153] Loading model from path
[INFO abstract_model.cc:1063] Engine "GradientBoostedTreesQuickScorerExtended" built
[INFO kernel.cc:1001] Use fast generic engine
WARNING:tensorflow:AutoGraph could not transform <function simple_ml_inference_op_with_handle at 0x7f95e9db4e60> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.
Cause: could not get source code
To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert
WARNING:tensorflow:AutoGraph could not transform <function simple_ml_inference_op_with_handle at 0x7f95e9db4e60> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.
Cause: could not get source code
To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert
WARNING: AutoGraph could not transform <function simple_ml_inference_op_with_handle at 0x7f95e9db4e60> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.
Cause: could not get source code
To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert
1/1 [==============================] - 0s 388ms/step - loss: 0.0000e+00 - mse: 0.1308 - accuracy: 0.8144
{'loss': 0.0, 'mse': 0.13076548278331757, 'accuracy': 0.814393937587738}

In TensorFlow 2, c'è anche un altro sostituto TFDF disponibile per un modello generato da tf.estimator.BoostedTreesEstimator - tfdf.keras.RandomForestModel . RandomForestModel crea uno studente robusto e resistente all'overfitting costituito da una popolazione votante di alberi decisionali profondi, ciascuno addestrato su sottoinsiemi casuali del set di dati di addestramento di input.

RandomForestModel e GradientBoostedTreesModel forniscono livelli di personalizzazione altrettanto ampi. La scelta tra di loro è specifica del problema e dipende dall'attività o dall'applicazione.

Consulta i documenti API per ulteriori informazioni sugli attributi RandomForestModel e GradientBoostedTreesModel .

rf_model = tfdf.keras.RandomForestModel(
    task=tfdf.keras.Task.CLASSIFICATION)
rf_model.compile(metrics=['mse', 'accuracy'])

Use /tmp/tmpluh2ebcj as temporary training directory

rf_model.fit(train_dataset)
rf_model.evaluate(eval_dataset, return_dict=True)

Starting reading the dataset
1/1 [==============================] - ETA: 0s
Dataset read in 0:00:00.094262
Training model
Model trained in 0:00:00.083656
Compiling model
1/1 [==============================] - 0s 260ms/step
[INFO kernel.cc:1153] Loading model from path
[INFO kernel.cc:1001] Use fast generic engine
1/1 [==============================] - 0s 123ms/step - loss: 0.0000e+00 - mse: 0.1270 - accuracy: 0.8636
{'loss': 0.0, 'mse': 0.12698587775230408, 'accuracy': 0.8636363744735718}