Question

我使用Tensorflow创建了一个简单的3层MNIST模型，并尝试将模型保存为.pb文件，以便我可以提取最终图层的权重和隐藏权重。但我无法获得最终的隐藏层和权重。请指导我如何保存重量。

我在代码中添加了以下行：

with tf.Graph().as_default():
    saver = tf.train.Saver()
    sess = tf.Session()
    saver.restore(sess,'/tmp/model.ckpt"')

但获得ValueError: No variables to save。我到底需要添加以上内容？

from __future__ import print_function

# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=False)

import tensorflow as tf
path_to_model_pb="/u"
# Parameters
learning_rate = 0.1
num_steps = 20
batch_size = 128
display_step = 100
#saver = tf.train.Saver()
# Network Parameters
n_hidden_1 = 15 # 1st layer number of neurons
#n_hidden_2 = 256 # 2nd layer number of neurons
num_input = 784 # MNIST data input (img shape: 28*28)
num_classes = 10 # MNIST total classes (0-9 digits)


# Define the neural network
def neural_net(x_dict):
    # TF Estimator input is a dict, in case of multiple inputs
    x = x_dict['images']
    # Hidden fully connected layer with 256 neurons
    layer_1 = tf.layers.dense(x, n_hidden_1)
    # Hidden fully connected layer with 256 neurons
    #layer_2 = tf.layers.dense(layer_1, n_hidden_2)
    # Output fully connected layer with a neuron for each class
    out_layer = tf.layers.dense(layer_1, num_classes)
    return out_layer


# Define the model function (following TF Estimator Template)
def model_fn(features, labels, mode):
    # Build the neural network
    logits = neural_net(features)

    # Predictions
    pred_classes = tf.argmax(logits, axis=1)
    pred_probas = tf.nn.softmax(logits)

    # If prediction mode, early return
    if mode == tf.estimator.ModeKeys.PREDICT:
        return tf.estimator.EstimatorSpec(mode, predictions=pred_classes)

        # Define loss and optimizer
    loss_op = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(
        logits=logits, labels=tf.cast(labels, dtype=tf.int32)))
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
    train_op = optimizer.minimize(loss_op,
                                  global_step=tf.train.get_global_step())

    # Evaluate the accuracy of the model
    acc_op = tf.metrics.accuracy(labels=labels, predictions=pred_classes)

    # TF Estimators requires to return a EstimatorSpec, that specify
    # the different ops for training, evaluating, ...
    estim_specs = tf.estimator.EstimatorSpec(
        mode=mode,
        predictions=pred_classes,
        loss=loss_op,
        train_op=train_op,
        eval_metric_ops={'accuracy': acc_op})
    saver = tf.train.Saver()
    return estim_specs




# Build the Estimator
model = tf.estimator.Estimator(model_fn)

# Define the input function for training
input_fn = tf.estimator.inputs.numpy_input_fn(
x={'images': mnist.train.images}, y=mnist.train.labels,
         batch_size=batch_size, num_epochs=None, shuffle=True)
# Train the Model

model.train(input_fn, steps=num_steps)

# Evaluate the Model
# Define the input function for evaluating
with tf.Graph().as_default():
    saver = tf.train.Saver()
    sess = tf.Session()
    input_fn = tf.estimator.inputs.numpy_input_fn(
    x={'images': mnist.test.images}, y=mnist.test.labels,
    batch_size=batch_size, shuffle=False)
# Use the Estimator 'evaluate' method
    e = model.evaluate(input_fn)

    print("Testing Accuracy:", e['accuracy'])

    saver.restore(sess,'/tmp/model.ckpt"')
   # save_path = saver.save(sess, "/tmp/model.ckpt")
    tf.train.write_graph(tf.get_default_graph(), path_to_model_pb,
                     'saved_model.pb', as_text=False)

Answer 1

您尚未在您所使用的图表中构建您的网络。Estimator使用自己的图表，并应为您处理会话管理。如果您希望模型保存权重，请将model_dir传递给构造函数。

model = tf.estimator.Estimator(model_fn, '/tmp/my_model_dir')
model.train(train_input_fn, steps=num_steps)
e = model.evaluate(eval_input_fn)

如果您想在估算器框架之外对网络进行处理，只需调用model_fn并从传递给估算器的model_dir加载变量。例如，要根据一些numpy feature_data生成推断：

graph = tf.Graph()
with graph.as_default():
    features = tf.placeholder(shape=feature_shape, dtype=tf.float32)
    labels = None
    mode = 'predict'

    spec = model_fn(features, labels, mode)
    saver = tf.train.Saver()

with tf.Session(graph=graph) as sess:
    saver.restore(sess, tf.train.latest_checkpoint('/tmp/my_model_dir'))
    sess.run(spec.inference, feed_dict={features: feature_data})

保存tensorflow模型的权重和偏差

1 个答案: