Question

我希望在我的GPU上运行我的tensorflow代码的训练阶段，然后我完成并存储结果以加载我创建的模型并在CPU上运行其测试阶段。

我已经创建了这个代码（我已经把它的一部分，只是为了参考，因为它非常大，我知道规则是包含一个功能齐全的代码，我为此道歉）。

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
from tensorflow.contrib.rnn.python.ops import rnn_cell, rnn

# Import MNIST data http://yann.lecun.com/exdb/mnist/
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
x_train = mnist.train.images 
# Check that the dataset contains 55,000 rows and 784 columns
N,D = x_train.shape

tf.reset_default_graph()
sess = tf.InteractiveSession()

x = tf.placeholder("float", [None, n_steps,n_input]) 
y_true = tf.placeholder("float", [None, n_classes]) 
keep_prob = tf.placeholder(tf.float32,shape=[])
learning_rate = tf.placeholder(tf.float32,shape=[]) 

#[............Build the RNN graph model.............]

sess.run(tf.global_variables_initializer())
# Because I am using my GPU for the training, I avoid allocating the whole 
# mnist.validation set because of memory error, so I gragment it to 
# small batches (100)
x_validation_bin, y_validation_bin = mnist.validation.next_batch(batch_size)
x_validation_bin = binarize(x_validation_bin, threshold=0.1)
x_validation_bin = x_validation_bin.reshape((-1,n_steps,n_input))

for k in range(epochs):

    steps = 0

    for i in range(training_iters):
        #Stochastic descent
        batch_x, batch_y = mnist.train.next_batch(batch_size)
        batch_x = binarize(batch_x, threshold=0.1)
        batch_x = batch_x.reshape((-1,n_steps,n_input))
        sess.run(train_step, feed_dict={x: batch_x, y_true: batch_y,keep_prob: keep_prob,eta:learning_rate})

        if do_report_err == 1:
            if steps % display_step == 0:
                # Calculate batch accuracy
                acc = sess.run(accuracy, feed_dict={x: batch_x, y_true: batch_y,keep_prob: 1.0})
                # Calculate batch loss
                loss = sess.run(total_loss, feed_dict={x: batch_x, y_true: batch_y,keep_prob: 1.0})
                print("Iter " + str(i) + ", Minibatch Loss= " + "{:.6f}".format(loss) + ", Training Accuracy = " + "{:.5f}".format(acc))
        steps += 1




    # Validation Accuracy and Cost
    validation_accuracy = sess.run(accuracy,feed_dict={x:x_validation_bin, y_true:y_validation_bin, keep_prob:1.0})
    validation_cost = sess.run(total_loss,feed_dict={x:x_validation_bin, y_true:y_validation_bin, keep_prob:1.0})

    validation_loss_array.append(final_validation_cost)
    validation_accuracy_array.append(final_validation_accuracy)
    saver.save(sess, savefilename)
    total_epochs = total_epochs + 1

    np.savez(datasavefilename,epochs_saved = total_epochs,learning_rate_saved = learning_rate,keep_prob_saved = best_keep_prob, validation_loss_array_saved = validation_loss_array,validation_accuracy_array_saved = validation_accuracy_array,modelsavefilename = savefilename)

之后，我的模型已成功训练并保存了相关数据，因此我希望加载文件并在模型中进行最终训练和测试部分，但这次使用我的CPU。原因是GPU无法处理mnist.train.images和mnist.train.labels的整个数据集。

所以，手动我选择这个部分然后运行它：

with tf.device('/cpu:0'):
# Initialise variables
    sess.run(tf.global_variables_initializer())

    # Accuracy and Cost
    saver.restore(sess, savefilename)
    x_train_bin = binarize(mnist.train.images, threshold=0.1)
    x_train_bin = x_train_bin.reshape((-1,n_steps,n_input))
    final_train_accuracy = sess.run(accuracy,feed_dict={x:x_train_bin, y_true:mnist.train.labels, keep_prob:1.0})
    final_train_cost = sess.run(total_loss,feed_dict={x:x_train_bin, y_true:mnist.train.labels, keep_prob:1.0})

    x_test_bin = binarize(mnist.test.images, threshold=0.1)
    x_test_bin = x_test_bin.reshape((-1,n_steps,n_input))
    final_test_accuracy = sess.run(accuracy,feed_dict={x:x_test_bin, y_true:mnist.test.labels, keep_prob:1.0})
    final_test_cost = sess.run(total_loss,feed_dict={x:x_test_bin, y_true:mnist.test.labels, keep_prob:1.0})

但是我得到了OMM GPU内存错误，这对我来说没有意义，因为我认为我已经迫使程序依赖CPU。我没有在第一个（批量训练）代码中输入命令sess.close（），但我不确定这是否真的是它背后的原因。我实际上关注了这篇文章for the CPU 有关如何仅在CPU上运行最后一部分的任何建议吗？

Answer 1

with tf.device()语句仅适用于图形构建，而不适用于执行，因此在设备块内部执行sess.run相当于根本没有设备。

要做你想做的事，你需要建立单独的训练和测试图，它们共享变量。

Tensorflow：在GPU上运行训练阶段并在CPU

1 个答案: