[英]Exporting Tensorflow probability's Hidden Markov Model
I want to export HMM model because training it every time takes time.我想导出 HMM model 因为每次训练它都需要时间。 My method is to save all matrices in file.
我的方法是将所有矩阵保存在文件中。 I want to know is there any tensorflow way I can do it?
我想知道有什么 tensorflow 方法可以做到吗? Also is it possible to export it with api to other languages like C++.
也可以将它与 api 一起导出到其他语言,如 C++。
you can iterate over and save the weights from the model variables by calling variables
attribute of tfp.distributions.HiddenMarkovModel()
您可以通过调用
tfp.distributions.HiddenMarkovModel()
的variables
属性来迭代并保存 model 变量的权重
tf.saved_model
would be the recommended way to do this. tf.saved_model
将是执行此操作的推荐方法。 Something like:就像是:
import tensorflow as tf
import tensorflow_probability as tfp
hmm = tfp.distributions.HiddenMarkovModel(
initial_distribution=tfp.distributions.Categorical(logits=tf.Variable([0., 0])),
transition_distribution=tfp.distributions.Categorical(logits=tf.Variable([[0., 0]] * 2)),
observation_distribution=tfp.distributions.Normal(tf.Variable([0., 0]),
tfp.util.TransformedVariable([1., 1], tfp.bijectors.Softplus(low=1e-3))),
num_steps=10)
x = hmm.sample(100)
opt = tf.optimizers.Adam(0.01)
@tf.function
def one_step():
with tf.GradientTape() as t:
nll = -hmm.log_prob(x)
grads = t.gradient(nll, hmm.trainable_variables)
opt.apply_gradients(zip(grads, hmm.trainable_variables))
for _ in range(10):
one_step()
class Foo(tf.Module):
def __init__(self, hmm):
self._hmm = hmm
@tf.function(input_signature=[tf.TensorSpec.from_tensor(x)])
def log_prob(self, x):
return self._hmm.log_prob(x)
tf.saved_model.save(Foo(hmm), '/tmp/tf.model')
q = tf.saved_model.load('/tmp/tf.model')
q.log_prob(x)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.