Question

我按照教程“TF图层指南：构建卷积神经网络”（这里是代码：https://github.com/tensorflow/tensorflow/blob/r1.1/tensorflow/examples/tutorials/layers/cnn_mnist.py）。

我根据自己的需要调整了教程，即手动检测。

据我所知，本教程创建了估算器（它是CNN），然后进行拟合，最后评估估算器的性能。现在，我的问题是我想在另一个文件中使用estimator，这将是我的主程序。如何从其他文件访问估算器？每次我想使用它时，我是否必须适合估算器？（我希望不会）

我想知道是否有人可以帮助我了解如何保存估算器以便以后使用它。（据我所知，我无法使用tf.train.Saver创建一个保护程序，因为我没有运行会话。）

以下是我的train.py文件中的代码：

def main(unused_argv):

#Load training and eval data (part missing)


# Create the estimator
hand_detector = learn.Estimator(model_fn=cnn_model_fn, model_dir="\cnn_model_fn")

# Set up logging for predictions
# Log the values in the "Softmax" tensor with label "probabilities"
tensors_to_log = {"probabilities": "softmax_tensor"}
logging_hook = tf.train.LoggingTensorHook(
    tensors=tensors_to_log, every_n_iter=50)

# Train the model
hand_detector.fit(
    x=train_data,
    y=train_labels,
    batch_size=100,
    steps=20000,
    monitors=[logging_hook])

# Configure the accuracy metric for evaluation
metrics = {
    "accuracy":
        learn.MetricSpec(
            metric_fn=tf.metrics.accuracy, prediction_key="classes"),
}

# Evaluate the model and print results
eval_results = hand_detector.evaluate(
    x=eval_data, y=eval_labels, metrics=metrics)
print(eval_results)

# Save the model for later use (part missing!)

Answer 1

几乎所有机器学习的实际应用都试图训练一次模型，然后将其保存以备将来使用新数据。大多数分类器在训练阶段花费数小时，在测试阶段只需几秒钟，因此基本学习如何成功保存训练有素的模型。

我将解释如何出口＆＃34;高水平＆＃34; Tensorflow模型（使用 export_savedmodel ）。函数 export_savedmodel 需要参数serving_input_receiver_fn，即不带参数的函数，它定义模型和预测变量的输入。因此，您必须创建自己的 serving_input_receiver_fn ，其中模型输入类型与训练脚本中的模型输入匹配，并且预测变量输入类型与测试脚本中的预测变量输入匹配。另一方面，如果创建自定义模型，则必须定义由函数 tf.estimator.export.PredictOutput 定义的export_outputs，该输入是定义必须匹配的名称的字典使用测试脚本中预测器输出的名称。

例如：

培训课程

def serving_input_receiver_fn():
    serialized_tf_example = tf.placeholder(dtype=tf.string, shape=[None], name='input_tensors')
    receiver_tensors      = {"predictor_inputs": serialized_tf_example}
    feature_spec          = {"words": tf.FixedLenFeature([25],tf.int64)}
    features              = tf.parse_example(serialized_tf_example, feature_spec)
    return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)
def estimator_spec_for_softmax_classification(logits, labels, mode):
    predicted_classes = tf.argmax(logits, 1)
    if (mode == tf.estimator.ModeKeys.PREDICT):
        export_outputs = {'predict_output': tf.estimator.export.PredictOutput({"pred_output_classes": predicted_classes, 'probabilities': tf.nn.softmax(logits)})}
        return tf.estimator.EstimatorSpec(mode=mode, predictions={'class': predicted_classes, 'prob': tf.nn.softmax(logits)}, export_outputs=export_outputs) # IMPORTANT!!!
    onehot_labels = tf.one_hot(labels, 31, 1, 0)
    loss          = tf.losses.softmax_cross_entropy(onehot_labels=onehot_labels, logits=logits)
    if (mode == tf.estimator.ModeKeys.TRAIN):
        optimizer = tf.train.AdamOptimizer(learning_rate=0.01)
        train_op  = optimizer.minimize(loss, global_step=tf.train.get_global_step())
        return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op)
    eval_metric_ops = {'accuracy': tf.metrics.accuracy(labels=labels, predictions=predicted_classes)}
    return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
def model_custom(features, labels, mode):
    bow_column           = tf.feature_column.categorical_column_with_identity("words", num_buckets=1000)
    bow_embedding_column = tf.feature_column.embedding_column(bow_column, dimension=50)   
    bow                  = tf.feature_column.input_layer(features, feature_columns=[bow_embedding_column])
    logits               = tf.layers.dense(bow, 31, activation=None)
    return estimator_spec_for_softmax_classification(logits=logits, labels=labels, mode=mode)
def main():
    # ...
    # preprocess-> features_train_set and labels_train_set
    # ...
    classifier     = tf.estimator.Estimator(model_fn = model_custom)
    train_input_fn = tf.estimator.inputs.numpy_input_fn(x={"words": features_train_set}, y=labels_train_set, batch_size=batch_size_param, num_epochs=None, shuffle=True)
    classifier.train(input_fn=train_input_fn, steps=100)
    full_model_dir = classifier.export_savedmodel(export_dir_base="C:/models/directory_base", serving_input_receiver_fn=serving_input_receiver_fn)

测试脚本

def main():
    # ...
    # preprocess-> features_test_set
    # ...
    with tf.Session() as sess:
        tf.saved_model.loader.load(sess, [tf.saved_model.tag_constants.SERVING], full_model_dir)
        predictor   = tf.contrib.predictor.from_saved_model(full_model_dir)
        model_input = tf.train.Example(features=tf.train.Features( feature={"words": tf.train.Feature(int64_list=tf.train.Int64List(value=features_test_set)) })) 
        model_input = model_input.SerializeToString()
        output_dict = predictor({"predictor_inputs":[model_input]})
        y_predicted = output_dict["pred_output_classes"][0]

（在Python 3.6.3中测试的代码，Tensorflow 1.4.0）

Answer 2

Estimator具有export_savedmodel成员函数用于此目的。您会找到文档here。

Answer 3

更新为David Valenzuela Urrutia's个答案（代码）

David Valenzuela Urrutia的答案是针对Python 3.6.3，Tensorflow 1.4.0的，所以我考虑将答案（代码示例）更新为Tensorflow 2.x，因为诸如 tf.Session 之类的一些功能不是Tensorflow版本2支持该功能，因此您需要将其替换为 tf.compat.v1.Session 才能正常工作。访问此link以了解有关添加到tensorflow版本2的更改的更多信息

培训脚本更新的代码

def serving_input_receiver_fn():
   serialized_tf_example = tf.compat.v1.placeholder(dtype=tf.string, shape=[None], 
       name='input_tensors')
   receiver_tensors      = {"predictor_inputs": serialized_tf_example}
   feature_spec          = {"words": tf.io.FixedLenFeature([25],tf.int64)}
   features              = tf.io.parse_example(serialized=serialized_tf_example, 
       features=feature_spec)
   return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)

def estimator_spec_for_softmax_classification(logits, labels, mode):
   predicted_classes = tf.argmax(input=logits, axis=1)
   if (mode == tf.estimator.ModeKeys.PREDICT):
      export_outputs = {'predict_output': 
   tf.estimator.export.PredictOutput({"pred_output_classes": predicted_classes, 'probabilities': tf.nn.softmax(logits)})}
   return tf.estimator.EstimatorSpec(mode=mode, predictions={'class': predicted_classes, 'prob': tf.nn.softmax(logits)}, export_outputs=export_outputs) # IMPORTANT!!!
   onehot_labels = tf.one_hot(labels, 31, 1, 0)
   loss        =tf.compat.v1.losses.softmax_cross_entropy(onehot_labels=onehot_labels, logits=logits)
   if (mode == tf.estimator.ModeKeys.TRAIN):
       optimizer = tf.compat.v1.train.AdamOptimizer(learning_rate=0.01)
       train_op  = optimizer.minimize(loss, global_step=tf.compat.v1.train.get_global_step())
       return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op)
   eval_metric_ops = {'accuracy': tf.compat.v1.metrics.accuracy(labels=labels, predictions=predicted_classes)}
   return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)

def model_custom(features, labels, mode):
   bow_column           = tf.feature_column.categorical_column_with_identity("words", num_buckets=1000)
   bow_embedding_column = tf.feature_column.embedding_column(bow_column, dimension=50)   
   bow                  = tf.compat.v1.feature_column.input_layer(features, feature_columns=[bow_embedding_column])
   logits               = tf.compat.v1.layers.dense(bow, 31, activation=None)
   return estimator_spec_for_softmax_classification(logits=logits, labels=labels, mode=mode)

def main():
   # ...
   # preprocess-> features_train_set and labels_train_set
   # ...
   classifier     = tf.estimator.Estimator(model_fn = model_custom)
   train_input_fn = tf.compat.v1.estimator.inputs.numpy_input_fn(x={"words": features_train_set}, y=labels_train_set, batch_size=batch_size_param, num_epochs=None, shuffle=True)
   classifier.train(input_fn=train_input_fn, steps=100)
   full_model_dir = classifier.export_savedmodel(export_dir_base="C:/models/directory_base", serving_input_receiver_fn=serving_input_receiver_fn)

测试脚本更新的代码

def main():
   # ...
   # preprocess-> features_test_set
   # ...
   with tf.compat.v1.Session() as sess:
       tf.compat.v1.saved_model.loader.load(sess, [tf.saved_model.SERVING], full_model_dir)
       predictor   = tf.contrib.predictor.from_saved_model(full_model_dir)
       model_input = tf.train.Example(features=tf.train.Features( feature={"words": tf.train.Feature(int64_list=tf.train.Int64List(value=features_test_set)) })) 
       model_input = model_input.SerializeToString()
       output_dict = predictor({"predictor_inputs":[model_input]})
       y_predicted = output_dict["pred_output_classes"][0]

如何在Tensorflow中保存估算工具以供日后使用？

3 个答案:

培训课程

测试脚本