keras 自定义层中的持久变量 [英] Persistent Variable in keras Custom Layer

查看:23
本文介绍了keras 自定义层中的持久变量的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述

我想写一个自定义层,我可以在运行之间在内存中保留一个变量.例如,

I want write a custom layer, where I can keep a variable in memory between runs. For example,

class MyLayer(Layer):
def __init__(self, out_dim = 51, **kwargs):
    self.out_dim = out_dim
    super(MyLayer, self).__init__(**kwargs)

def build(self, input_shape):
    a = 0.0
    self.persistent_variable = K.variable(a)
    self.built = True

def get_output_shape_for(self, input_shape):
    return (input_shape[0], 1)

def call(self, x, mask=None):
    a = K.eval(self.persistent_variable) + 1
    K.set_value(self.persistent_variable, a)
    return self.persistent_variable

m = Sequential()
m.add(MyLayer(input_shape=(1,)))

当我运行 m.predict 时,我希望 persistent_variable 得到更新,并打印增加的值.但它看起来总是打印 0

When I run m.predict, I expect the persistent_variable to get updated, and print the incremented value. But it looks like it always prints 0

# Dummy input
x = np.zeros(1)

m.predict(x, batch_size=1)

我的问题是,如何在每次运行 m.predict

My question is, how do I make the persistent_variable increment and save after every run of m.predict

谢谢,内文

推荐答案

诀窍是你必须在你的调用函数中调用 self.add_update(...) 来注册一个函数每次评估模型时都会调用它(我通过深入研究有状态 rnns 的源代码发现了这一点).如果您执行 self.stateful = True,它将为每个训练和预测调用调用您的自定义更新函数,否则它只会在训练期间调用它.例如:

The trick is that you have to call self.add_update(...) in your call function to register a function that will be called every time your model is evaluated (I found this by digging into the source code of the stateful rnns). If you do self.stateful = True it will call your custom update function for every training and prediction call, otherwise it will only call it during training. For example:

import keras.backend as K
import numpy as np
from keras.engine.topology import Layer

class CounterLayer(Layer):
  def __init__(self, stateful=False,**kwargs):
    self.stateful = stateful # True means it will increment counter on predict and train, false means it will only increment counter on train 
    super(CounterLayer, self).__init__(**kwargs)


  def build(self, input_shape):
    # Define variables in build
    self.count = K.variable(0, name="count")
    super(CounterLayer, self).build(input_shape)

  def call(self, x, mask=None):
    updates = []
    # The format is (variable, value setting to)
    # So this says 
    # self.pos = self.pos + 1
    updates.append((self.count, self.count+1))

    # You can append more updates to this list or call add_update more
    # times if you want

    # Add our custom update

    # We stick x here so it calls our update function every time our layer 
    # is given a new x
    self.add_update(updates, x)

    # This will be an identity layer but keras gets mad for some reason
    # if you just output x so we'll multiply it by 1 so it thinks it is a
    # "new variable"
    return self.count
  # in newer keras versions you might need to name this compute_output_shape instead
  def get_output_shape_for(self, input_shape):
    # We will just return our count as an array ([[count]])
    return (1,1)

  def reset_states(self):
    self.count.set_value(0)

示例用法:

from keras.layers import Input
from keras.models import Model
from keras.optimizers import RMSprop
inputLayer = Input(shape=(10,))
counter = CounterLayer() # Don't update on predict
# counter = CounterLayer(stateful=True) # This will update each time you call predict
counterLayer = counter(inputLayer)
model = Model(input=inputLayer, output=counterLayer)
optimizer = RMSprop(lr=0.001)
model.compile(loss="mse", optimizer=optimizer)


# See the value of our counter
print counter.count.get_value()

# This won't actually train anything but each epoch will update our counter

# Note that if you say have a batch size of 5, update will be called 5 times per epoch
model.fit(np.zeros([1, 10]), np.array([0]), batch_size=1, nb_epoch=5)

# The value of our counter has now changed
print counter.count.get_value()

model.predict(np.zeros([1, 10]))

# If we did stateful=False, this didn't change, otherwise it did
print counter.count.get_value()

这篇关于keras 自定义层中的持久变量的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!

查看全文
登录 关闭
扫码关注1秒登录
发送“验证码”获取 | 15天全站免登陆