如何将多个参数从 Tensorflow 概率传递到 DistributionLambda 层?
How can I pass multiple parameters to a DistributionLambda layer from Tensorflow probability?
我正在使用 Keras 和 Tensorflow 概率构建一个模型,它应该输出 Gamma 函数的参数(alpha 和 beta)而不是单个参数,如下例所示(t
被传递给Normal
分布函数)。
import tensorflow as tf
import tensorflow_probability as tfp
tfd = tfp.distributions
# Build model.
model = tf.keras.Sequential([
tf.keras.layers.Dense(1),
tfp.layers.DistributionLambda(lambda t: tfd.Normal(loc=t, scale=1)),
])
# Do inference.
model.compile(optimizer=tf.optimizers.Adam(learning_rate=0.05), loss=negloglik)
model.fit(x, y, epochs=500, verbose=False)
# Make predictions.
yhat = model(x_tst)
我想从两个 Dense
层输出 alpha
和 beta
,然后将此参数传递给 Gamma
分布函数。
是这样的吗?
import tensorflow as tf
tf.enable_eager_execution()
print(tf.__version__) # 1.14.1-dev20190503
import tensorflow_probability as tfp
tfd = tfp.distributions
X = np.random.rand(4, 1).astype(np.float32)
d0 = tf.keras.layers.Dense(2)(X)
s0, s1 = tf.split(d0, 2)
dist = tfp.layers.DistributionLambda(lambda t: tfd.Gamma(t[0], t[1]))(s0, s1)
dist.sample()
# <tf.Tensor: id=10580, shape=(2,), dtype=float32, numpy=array([1.1754944e-38, 1.3052921e-01], dtype=float32)>
我正在使用 Keras 和 Tensorflow 概率构建一个模型,它应该输出 Gamma 函数的参数(alpha 和 beta)而不是单个参数,如下例所示(t
被传递给Normal
分布函数)。
import tensorflow as tf
import tensorflow_probability as tfp
tfd = tfp.distributions
# Build model.
model = tf.keras.Sequential([
tf.keras.layers.Dense(1),
tfp.layers.DistributionLambda(lambda t: tfd.Normal(loc=t, scale=1)),
])
# Do inference.
model.compile(optimizer=tf.optimizers.Adam(learning_rate=0.05), loss=negloglik)
model.fit(x, y, epochs=500, verbose=False)
# Make predictions.
yhat = model(x_tst)
我想从两个 Dense
层输出 alpha
和 beta
,然后将此参数传递给 Gamma
分布函数。
是这样的吗?
import tensorflow as tf
tf.enable_eager_execution()
print(tf.__version__) # 1.14.1-dev20190503
import tensorflow_probability as tfp
tfd = tfp.distributions
X = np.random.rand(4, 1).astype(np.float32)
d0 = tf.keras.layers.Dense(2)(X)
s0, s1 = tf.split(d0, 2)
dist = tfp.layers.DistributionLambda(lambda t: tfd.Gamma(t[0], t[1]))(s0, s1)
dist.sample()
# <tf.Tensor: id=10580, shape=(2,), dtype=float32, numpy=array([1.1754944e-38, 1.3052921e-01], dtype=float32)>