Question

我正在使用TensorFlow构建深度学习模型。 TensorFlow新手。

由于某些原因，我的模型的批量大小有限，那么这种有限的批量大小将使模型具有很大的差异。

所以，我想用一些技巧来增加批量。我的想法是存储每个小批量的渐变，例如64个小批量，然后将渐变相加，使用这64个迷你批次的训练数据的平均渐变来更新模型的参数。

这意味着对于前63个迷你批次，不要更新参数，在64迷你批次之后，只更新模型的参数一次。

但是由于TensorFlow是基于图形的，有人知道如何实现这个想要的功能吗？

非常感谢。

Answer 1

我在这里找到了一个解决方案：https://github.com/tensorflow/tensorflow/issues/3994#event-766328647

opt = tf.train.AdamOptimizer()
tvs = tf.trainable_variables()
accum_vars = [tf.Variable(tf.zeros_like(tv.initialized_value()), trainable=False) for tv in tvs]                                        
zero_ops = [tv.assign(tf.zeros_like(tv)) for tv in accum_vars]
gvs = opt.compute_gradients(rmse, tvs)
accum_ops = [accum_vars[i].assign_add(gv[0]) for i, gv in enumerate(gvs)]
train_step = opt.apply_gradients([(accum_vars[i], gv[1]) for i, gv in enumerate(gvs)])

在训练循环中：

while True:
    sess.run(zero_ops)
    for i in xrange(n_minibatches):
        sess.run(accum_ops, feed_dict=dict(X: Xs[i], y: ys[i]))
    sess.run(train_step)

但是这段代码看起来不是很干净漂亮，有没有人知道如何优化这些代码？

Answer 2

我遇到了同样的问题并且弄明白了。

首先获取符号渐变，然后将累积的渐变定义为tf.Variables。（似乎必须在定义tf.global_variables_initializer()之前运行grads_accum。否则我会收到错误，不确定原因。）

tvars = tf.trainable_variables()
optimizer = tf.train.GradientDescentOptimizer(lr)
grads = tf.gradients(cost, tvars)

# initialize
tf.local_variables_initializer().run()
tf.global_variables_initializer().run()

grads_accum = [tf.Variable(tf.zeros_like(v)) for v in grads] 
update_op = optimizer.apply_gradients(zip(grads_accum, tvars))

在训练中，您可以在每批中累积渐变（保存在gradients_accum），并在运行第64批后更新模型：

feed_dict = dict()
for i, _grads in enumerate(gradients_accum):
    feed_dict[grads_accum[i]] = _grads
sess.run(fetches=[update_op], feed_dict=feed_dict)

您可以参考tensorflow/tensorflow/python/training/optimizer_test.py作为示例用法，尤其是此功能：testGradientsAsVariables()。

希望它有所帮助。

Answer 3

以前的解决方案不计算累积梯度的平均值，这可能会导致训练不稳定。我已经修改了上面的代码，应该可以解决这个问题。

# Fetch a list of our network's trainable parameters.
trainable_vars = tf.trainable_variables()

# Create variables to store accumulated gradients
accumulators = [
    tf.Variable(
        tf.zeros_like(tv.initialized_value()),
        trainable=False
    ) for tv in trainable_vars
]

# Create a variable for counting the number of accumulations
accumulation_counter = tf.Variable(0.0, trainable=False)

# Compute gradients; grad_pairs contains (gradient, variable) pairs
grad_pairs = optimizer.compute_gradients(loss, trainable_vars)

# Create operations which add a variable's gradient to its accumulator.
accumulate_ops = [
    accumulator.assign_add(
        grad
    ) for (accumulator, (grad, var)) in zip(accumulators, grad_pairs)
]

# The final accumulation operation is to increment the counter
accumulate_ops.append(accumulation_counter.assign_add(1.0))

# Update trainable variables by applying the accumulated gradients
# divided by the counter. Note: apply_gradients takes in a list of 
# (grad, var) pairs
train_step = optimizer.apply_gradients(
    [(accumulator / accumulation_counter, var) \
        for (accumulator, (grad, var)) in zip(accumulators, grad_pairs)]
)

# Accumulators must be zeroed once the accumulated gradient is applied.
zero_ops = [
    accumulator.assign(
        tf.zeros_like(tv)
    ) for (accumulator, tv) in zip(accumulators, trainable_vars)
]

# Add one last op for zeroing the counter
zero_ops.append(accumulation_counter.assign(0.0))

此代码的使用方式与@weixsong提供的方式相同。

Answer 4

如果我不再次在sess.run（train_step）中提供feed_dict，则您发布的方法似乎会失败。我不知道为什么需要feed_dict，但是有可能再次运行所有累加器，并重复上一个示例。这是我必须做的事情：

            self.session.run(zero_ops)
            for i in range(0, mini_batch):

                self.session.run(accum_ops, feed_dict={self.ph_X: imgs_feed[np.newaxis, i, :, :, :], self.ph_Y: flow_labels[np.newaxis, i, :, :, :], self.keep_prob: self.dropout})

            self.session.run(norm_acums, feed_dict={self.ph_X: imgs_feed[np.newaxis, i, :, :, :], self.ph_Y: flow_labels[np.newaxis, i, :, :, :], self.keep_prob: self.dropout})
            self.session.run(train_op, feed_dict={self.ph_X: imgs_feed[np.newaxis, i, :, :, :], self.ph_Y: flow_labels[np.newaxis, i, :, :, :], self.keep_prob: self.dropout})

为了归一化梯度，我知道这只是将累积的gradietn除以batchsize，所以我只添加了一个新运算符

norm_accums = [accum_op/float(batchsize) for accum_op in accum_ops]

有人也有同样的feed_dict问题吗？

*更新如我所料，这是错误的，它将再次使用批处理中的最后一个示例运行所有图形。这个小代码测试了

import numpy as np
import tensorflow as tf
ph = tf.placeholder(dtype=tf.float32, shape=[])
var_accum = tf.get_variable("acum", shape=[], 
initializer=tf.zeros_initializer())
acum = tf.assign_add(var_accum, ph)
divide = acum/5.0
init = tf.global_variables_initializer()
    with tf.Session() as sess:
    sess.run(init)
    for i in range(5):
         sess.run(acum, feed_dict={ph: 2.0})

c = sess.run([divide], feed_dict={ph: 2.0})
#10/5 = 2
print(c)
#but it gives 2.4, that is 12/5, so sums one more time

我想出了解决方法。因此，张量流具有条件操作。我放一个分支中的累积，以及归一化和更新的最后一个累积，在另一个分支中。我的代码一团糟，但是为了快速检查，我想说一些使用示例的代码。

import numpy as np
import tensorflow as tf

ph = tf.placeholder(dtype=tf.float32, shape=[])
#placeholder for conditional braching in the graph
condph = tf.placeholder(dtype=tf.bool, shape=[])

var_accum = tf.get_variable("acum", shape=[], initializer=tf.zeros_initializer())

accum_op = tf.assign_add(var_accum, ph)

#function when condition of condph is True
def truefn():
   return accum_op
#function when condtion of condph is False
def falsefn():
   div = accum_op/5.0
   return div

#return the conditional operation
cond = tf.cond(condph, truefn, falsefn)

init = tf.global_variables_initializer()

with tf.Session() as sess:
   sess.run(init)
   for i in range(4):
       #run only accumulation
       sess.run(cond, feed_dict={ph: 2.0, condph: True})
   #run acumulation and divition
   c = sess.run(cond, feed_dict={ph: 2.0, condph: False})

print(c)
#now gives 2

*重要说明：忘记所有无效的内容。优化器会失败。

Answer 5

您可以使用Pytorch代替Tensorflow，因为它允许用户在训练过程中累积梯度

Answer 6

Tensorflow 2.0兼容答案：与上面提到的weixsong的答案以及Tensorflow Website中提供的解释一致，下面提到的是Tensorflow 2.0版中的累积梯度代码：

def train(epochs):
  for epoch in range(epochs):
    for (batch, (images, labels)) in enumerate(dataset):
       with tf.GradientTape() as tape:
        logits = mnist_model(images, training=True)
        tvs = mnist_model.trainable_variables
        accum_vars = [tf.Variable(tf.zeros_like(tv.initialized_value()), trainable=False) for tv in tvs]
        zero_ops = [tv.assign(tf.zeros_like(tv)) for tv in accum_vars]
        loss_value = loss_object(labels, logits)

       loss_history.append(loss_value.numpy().mean())
       grads = tape.gradient(loss_value, tvs)
       #print(grads[0].shape)
       #print(accum_vars[0].shape)
       accum_ops = [accum_vars[i].assign_add(grad) for i, grad in enumerate(grads)]



    optimizer.apply_gradients(zip(grads, mnist_model.trainable_variables))
    print ('Epoch {} finished'.format(epoch))

# call the above function    
train(epochs = 3)

完整代码可在此Github Gist中找到。

如何使用累积渐变更新模型参数？

6 个答案: