技术博客tensorflow与教程in.pptx

Variational Inference in TensorFlow;Outline;Variational Inference;Learning unknown variables;Learning unknown variables;Variational lower bound: Overview;Variational lower bound: Algorithm;Amortized inference: Overview;Amortized inference: Algorithm;Variational Auto-Encoder;Bayesian Neural Network;TensorFlow Distributions;TensorFlow Distributions: Overview;TensorFlow Distributions: Overview;TensorFlow Distributions: Overview;TensorFlow Distributions: Overview;TensorFlow Distributions: Regression example;TensorFlow Distributions: Regression example;TensorFlow Distributions: Classification example;TensorFlow Distributions: Classification example;VAE in TensorFlow;VAE in TensorFlow: Overview;VAE in TensorFlow: Overview;VAE in TensorFlow: Prior encoder;VAE in TensorFlow: Networks;VAE in TensorFlow: Results;Bonus: BNN in TensorFlow;def define_network(images, num_classes=10): mean = tf.get_variable(mean, [28 * 28, num_classes]) stddev = tf.get_variable(stddev, [28 * 28, num_classes]) prior = tfd.MultivariateNormalDiag( tf.zeros_like(mean), tf.ones_like(stddev)) posterior = tfd.MultivariateNormalDiag(mean, tf.nn.softplus(stddev)) bias = tf.get_variable(bias, [num_classes]) # Or Bayesian, too logit = tf.nn.relu(tf.matmul(posterior.sample(), images) + bias) return tfd.Categorical(logit), posterior, prior;def define_network(images, num_classes=10): mean = tf.get_variable(mean, [28 * 28, num_classes]) stddev = tf.get_variable(stddev, [28 * 28, num_classes]) prior = tfd.MultivariateNormalDiag( tf.zeros_like(mean), tf.ones_like(stddev)) posterior = tfd.MultivariateNormalDiag(mean, tf.nn.softplus(stddev)) bias = tf.get_variable(bias, [num_classes]) # Or Bayesian, too logit = tf.nn.relu(tf.matmul(posterior.sample(), images) + bias) return tfd.Categorical(logit), posterior, prior dist, posterior, prior = define_network(images) elbo = (tf.reduce_mean(dist.log_prob(label)) - tf.reduce_mean(tfd.kl_divergence(posterior, prior));Thats a