python - 递归使用函数会导致 tensorflow 中模型大小的增加

Question

我使用一个函数来计算每个时期tf.Session()内的均方误差。但是，如果我在每一步都保存模型，则保存的文件的大小会随着步长的增加而增加。

当我使用函数get_mse()时，每个纪元后保存的check_points的大小都会增加。但是，当我使用一个简单的语句来计算 mse 即 MSE 时，它不会发生。我做错了什么？

import os
import numpy as np
import tensorflow as tf
from tensorflow.python.ops.losses.losses_impl import Reduction, compute_weighted_loss
from tensorflow.python.framework import ops
from tensorflow.python.ops import math_ops

def get_mse(
    labels, predictions, weights=1.0, name="mse", scope=None,
    loss_collection=ops.GraphKeys.LOSSES,
    reduction=Reduction.SUM_BY_NONZERO_WEIGHTS):
  with ops.name_scope(scope, name,
                      (predictions, labels, weights)) as scope:
    predictions = math_ops.to_float(predictions)
    labels = math_ops.to_float(labels)
    predictions.get_shape().assert_is_compatible_with(labels.get_shape())
    losses = math_ops.squared_difference(predictions, labels)
    return compute_weighted_loss(
losses, weights, scope, loss_collection, reduction=reduction)

true  = np.random.random((100,1))
pred = np.random.random((100,1))

variable_to_save = tf.Variable(true)
true_ph = tf.placeholder(tf.float32, shape = [None, 1], name='labels')
pred_ph = tf.placeholder(tf.float32, shape = [None, 1], name='predictions')

MSE = tf.reduce_mean(tf.square(pred_ph - true_ph), name='get_mse')

with tf.Session() as sess:
    init = tf.global_variables_initializer()
    sess.run(init)
    saver = tf.train.Saver(max_to_keep=100)
    for epoch in range(10):
        mse = sess.run(get_mse(true_ph, pred_ph), feed_dict={'labels:0': true, 'predictions:0':pred})   #this increases size of checkpoints after each epoch
        #mse = sess.run(MSE, feed_dict={'labels:0': true, 'predictions:0': pred})   #running this does not increases size of check_points
        saver.save(sess, os.getcwd(), global_step=epoch)

Answer 1

每次调用 get_mse() 时，您都会构建另一堆计算图节点。 IE。每次您创建 predictions 的另一个版本时, labels ，和losses .

调用 get_mse() 一次并将结果存储到变量中，例如 mse_computer 。然后使用 sess.run(mse_computer, feed_dict=....相反。

希望对你有帮助