How to use the edward2.experimental.rank1_bnns.rank1_bnn_layers function in edward2

To help you get started, we’ve selected a few edward2 examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github Google-Health / records-research / model-uncertainty / bayesian_rnn_model.py View on Github external
alpha_initializer=rank1_utils.make_initializer(
              alpha_initializer, random_sign_init, dropout_rate),
          gamma_initializer=rank1_utils.make_initializer(
              gamma_initializer, random_sign_init, dropout_rate),
          kernel_initializer="he_normal",
          alpha_regularizer=rank1_utils.make_regularizer(
              alpha_regularizer, prior_mean, prior_stddev),
          gamma_regularizer=rank1_utils.make_regularizer(
              gamma_regularizer, prior_mean, prior_stddev),
          kernel_regularizer=tf.keras.regularizers.l2(l2),
          bias_regularizer=tf.keras.regularizers.l2(l2),
          use_additive_perturbation=use_additive_perturbation,
          ensemble_size=ensemble_size)

    # 3. Output affine layer.
    self.output_layer = rank1_bnn_layers.DenseRank1(
        output_layer_dim,
        alpha_initializer=rank1_utils.make_initializer(
            alpha_initializer, random_sign_init, dropout_rate),
        gamma_initializer=rank1_utils.make_initializer(
            gamma_initializer, random_sign_init, dropout_rate),
        kernel_initializer="he_normal",
        alpha_regularizer=rank1_utils.make_regularizer(
            alpha_regularizer, prior_mean, prior_stddev),
        gamma_regularizer=rank1_utils.make_regularizer(
            gamma_regularizer, prior_mean, prior_stddev),
        kernel_regularizer=tf.keras.regularizers.l2(l2),
        bias_regularizer=tf.keras.regularizers.l2(l2),
        use_additive_perturbation=use_additive_perturbation,
        ensemble_size=ensemble_size)