问题描述
我正在尝试构建一个自定义Keras层,该层返回一个从上一个softmax层中选择的类的一个热矢量,即,如果 Sofmax 层返回[0.4 0.1 0.5],我想根据此 softmax 概率,对0至2类进行随机选择.
I am trying to build a custom Keras Layer that returns a one hot vector of a class chosen from a previous softmax layer, i.e, if Sofmax layer returns [0.4 0.1 0.5] I want to make a ramdom choice on classes 0 to 2 according to this softmax probability.
这是我到目前为止所做的:
Here is what I have done so far:
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras import utils
def sampling(x):
# HERE: I need to input 'x' into the 'tf.math.log' function, but after trying it created an error
samples = tf.random.categorical(tf.math.log([[0.4 0.1 0.5]]), 1) # samples should be like [[z]] with z a number between 0 and 2
return utils.to_categorical(samples[0][0], num_classes=3)
x = keras.Input(shape=(1,1,))
x, _, _ = layers.LSTM(100, return_sequences=True, return_state=True)(x)
x = layers.Dense(3, activation="softmax")(x)
x = layers.Lambda(sampling)(x)
此代码返回:
TypeError: array ()接受1个位置参数,但给出了2个
TypeError: array() takes 1 positional argument but 2 were given
此处是Google Colab链接
Here is the Google Colab link
推荐答案
您可以使用 tf.one_hot
来实现.
如果采样功能的输入是2D:
If the input of the sampling function is 2D:
X = np.random.uniform(0,1, (100,1,1))
y = tf.keras.utils.to_categorical(np.random.randint(0,3, (100,)))
def sampling(x):
zeros = x*0 ### useless but important to produce gradient
samples = tf.random.categorical(tf.math.log(x), 1)
samples = tf.squeeze(tf.one_hot(samples, depth=3), axis=1)
return zeros+samples
inp = Input(shape=(1,1,))
x, _, _ = LSTM(100, return_sequences=False, return_state=True)(inp)
x = Dense(3, activation="softmax")(x)
out = Lambda(sampling)(x)
model = Model(inp, out)
model.compile('adam', 'categorical_crossentropy')
model.fit(X,y, epochs=3)
如果采样功能的输入是3D:
If the input of the sampling function is 3D:
tf.random.categorical
仅接受2D Logit.您可以使用 tf.map_fn
tf.random.categorical
accepts only 2D logits. You can adapt the operation for 3D logits using tf.map_fn
X = np.random.uniform(0,1, (100,1,1))
y = tf.keras.utils.to_categorical(np.random.randint(0,3, (100,)))
y = y.reshape(-1,1,3)
def sampling(x):
zeros = x*0 ### useless but important to produce gradient
samples = tf.map_fn(lambda t: tf.random.categorical(tf.math.log(t), 1), x, fn_output_signature=tf.int64)
samples = tf.squeeze(tf.one_hot(samples, depth=3), axis=1)
return zeros+samples
inp = Input(shape=(1,1,))
x, _, _ = LSTM(100, return_sequences=True, return_state=True)(inp)
x = Dense(3, activation="softmax")(x)
out = Lambda(sampling)(x)
model = Model(inp, out)
model.compile('adam', 'categorical_crossentropy')
model.fit(X,y, epochs=3)
这篇关于在Keras中制作采样层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!