أمثلة على الترحيل: المقدّرون المعلبون

عرض على TensorFlow.org تشغيل في Google Colab عرض المصدر على جيثب تحميل دفتر

تم استخدام المُقدِرات المعلبة (أو مسبقة الصنع) تقليديًا في TensorFlow 1 كطرق سريعة وسهلة لتدريب النماذج لمجموعة متنوعة من حالات الاستخدام النموذجية. يوفر TensorFlow 2 بدائل تقريبية مباشرة لعدد منها عن طريق نماذج Keras. بالنسبة لأولئك المقدرين المعلبين الذين ليس لديهم بدائل TensorFlow 2 المضمنة ، لا يزال بإمكانك بناء البديل الخاص بك بسهولة إلى حد ما.

يستعرض هذا الدليل بعض الأمثلة للمكافئات المباشرة والبدائل المخصصة لتوضيح كيف يمكن ترحيل النماذج المستمدة من tf.estimator 1 إلى TF2 باستخدام Keras.

وبالتحديد ، يتضمن هذا الدليل أمثلة على الترحيل:

مقدمة شائعة لتدريب النموذج هي المعالجة المسبقة للميزات ، والتي يتم إجراؤها لنماذج TensorFlow 1 Estimator باستخدام tf.feature_column . لمزيد من المعلومات حول المعالجة المسبقة للميزات في TensorFlow 2 ، راجع هذا الدليل حول ترحيل أعمدة الميزات .

يثبت

ابدأ بزوج من واردات TensorFlow الضرورية ،

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).

تحضير بعض البيانات البسيطة للشرح من مجموعة بيانات تيتانيك القياسية ،

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)

وإنشاء طريقة لإنشاء مثيل مُحسِّن نموذجي مبسط لاستخدامه مع نماذج TensorFlow 1 المقدر المتنوعة و 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

مثال 1: الترحيل من المحفز الخطي

TF1: استخدام المحفز الخطي

في TensorFlow 1 ، يمكنك استخدام tf.estimator.LinearEstimator لإنشاء نموذج خطي أساسي لمشاكل الانحدار والتصنيف.

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: استخدام Keras LinearModel

في TensorFlow 2 ، يمكنك إنشاء مثيل لـ Keras tf.compat.v1.keras.models.LinearModel وهو البديل لـ tf.estimator.LinearEstimator . يتم استخدام مسار tf.compat.v1.keras للإشارة إلى أن النموذج المعد مسبقًا موجود للتوافق.

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}

مثال 2: الترحيل من DNNEstimator

TF1: استخدام DNNEstimator

في TensorFlow 1 ، يمكنك استخدام tf.estimator.DNNEstimator لإنشاء نموذج DNN أساسي لمشاكل الانحدار والتصنيف.

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: استخدام Keras لإنشاء نموذج DNN مخصص

في TensorFlow 2 ، يمكنك إنشاء نموذج DNN مخصص لاستبدال نموذج تم إنشاؤه بواسطة tf.estimator.DNNEstimator ، مع مستويات مماثلة من التخصيص المحدد من قبل المستخدم (على سبيل المثال ، كما في المثال السابق ، القدرة على تخصيص نموذج مُحسِّن مختار) .

يمكن استخدام سير عمل مماثل لاستبدال tf.estimator.experimental.RNNEstimator بنموذج Keras RNN. يوفر Keras عددًا من الخيارات المضمنة والقابلة للتخصيص عن طريق tf.keras.layers.RNN و tf.keras.layers.LSTM و tf.keras.layers.GRU - انظر هنا لمزيد من التفاصيل.

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}

مثال 3: الترحيل من DNNLinearCombinedEstimator

TF1: استخدام DNNLinearCombinedEstimator

في TensorFlow 1 ، يمكنك استخدام tf.estimator.DNNLinearCombinedEstimator لإنشاء نموذج أساسي مشترك لمشاكل الانحدار والتصنيف مع سعة التخصيص لكل من مكوناته الخطية و 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: استخدام Keras WideDeepModel

في TensorFlow 2 ، يمكنك إنشاء مثيل لـ Keras tf.compat.v1.keras.models.WideDeepModel لاستبدال واحد تم إنشاؤه بواسطة tf.estimator.DNNLinearCombinedEstimator ، مع مستويات مماثلة من التخصيص المحدد من قبل المستخدم (على سبيل المثال ، كما في المثال السابق ، القدرة على تخصيص مُحسِّن نموذج مُختار).

تم إنشاء WideDeepModel هذا على أساس LinearModel المكون ونموذج DNN المخصص ، وكلاهما تمت مناقشته في المثالين السابقين. يمكن أيضًا استخدام نموذج خطي مخصص بدلاً من نموذج LinearModel إذا رغبت في ذلك.

إذا كنت ترغب في بناء النموذج الخاص بك بدلاً من المقدر المعلب ، فتحقق من كيفية بناء نموذج keras.Sequential . لمزيد من المعلومات حول التدريب المخصص والمحسّنين ، يمكنك أيضًا مراجعة هذا الدليل .

# 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}

مثال 4: الترحيل من BoostedTreesEstimator

TF1: استخدام المحفز BoostedTrees

في TensorFlow 1 ، يمكنك استخدام tf.estimator.BoostedTreesEstimator لإنشاء خط أساس لإنشاء نموذج تعزيز التدرج الأساسي باستخدام مجموعة من أشجار القرار لمشاكل الانحدار والتصنيف. لم تعد هذه الوظيفة مضمنة في 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: استخدام غابات القرار TensorFlow

في TensorFlow 2 ، أقرب بديل مُعبأ مسبقًا لنموذج تم إنشاؤه بواسطة tf.estimator.BoostedTreesEstimator هو واحد تم إنشاؤه باستخدام tfdf.keras.GradientBoostedTreesModel ، والذي ينشئ تسلسلاً مُدرَّبًا بشكل تسلسلي من أشجار القرار الضحلة ، كل منها مصمم "للتعلم" من الأخطاء التي أدلى بها أسلافها في التسلسل.

يوفر GradientBoostedTreesModel المزيد من الخيارات للتخصيص ، مما يسمح بمواصفات كل شيء بدءًا من قيود العمق الأساسية إلى ظروف التوقف المبكر. انظر هنا لمزيد من تفاصيل سمة 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}

في TensorFlow 2 ، يوجد أيضًا بديل آخر متاح لـ TFDF للنموذج الذي تم إنشاؤه بواسطة tf.estimator.BoostedTreesEstimator - tfdf.keras.RandomForestModel . يُنشئ RandomForestModel قويًا ومقاومًا للإفراط في التجهيز يتكون من جمهور تصويت من أشجار القرار العميق ، يتم تدريب كل منهم على مجموعات فرعية عشوائية من مجموعة بيانات تدريب الإدخال.

RandomForestModel و GradientBoostedTreesModel مستويات واسعة مماثلة من التخصيص. الاختيار بينهما يتعلق بالمشكلة ويعتمد على مهمتك أو تطبيقك.

تحقق من مستندات API للحصول على مزيد من المعلومات حول السمة RandomForestModel و 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}