ef3c40a4542966e2dac08cc51710ddedc31fd2d9,deepchem/models/tensorgraph/progressive_multitask.py,ProgressiveMultitaskRegressor,add_adapter,#ProgressiveMultitaskRegressor#Any#Any#Any#,215

Before Change

    // prev_layers is a list with elements of size
    // (batch_size, layer_sizes[i-1])
    prev_layer = Concat(axis=1, in_layers=prev_layers)
    with self._get_tf("Graph").as_default():
      alpha = TensorWrapper(
          tf.Variable(
              tf.truncated_normal((1,), stddev=alpha_init_stddev),
              name="alpha_layer_%d_task%d" % (i, task)))
      trainable_layers.append(alpha)

    prev_layer = prev_layer * alpha
    dense1 = Dense(
        in_layers=[prev_layer],
        out_channels=layer_sizes[i - 1],

After Change

    alpha = layers.Variable(tf.truncated_normal((1,), stddev=alpha_init_stddev))
    trainable_layers.append(alpha)

    prev_layer = Multiply()([prev_layer, alpha([])])
    dense1 = Dense(
        layer_sizes[i - 1],
        kernel_initializer=tf.truncated_normal_initializer(
            stddev=weight_init_stddev),
        bias_initializer=tf.constant_initializer(value=bias_init_const))
    prev_layer = dense1(prev_layer)
    trainable_layers.append(dense1)

    dense2 = Dense(
        layer_sizes[i],
        kernel_initializer=tf.truncated_normal_initializer(
            stddev=weight_init_stddev),
        use_bias=False)
    prev_layer = dense2(prev_layer)
    trainable_layers.append(dense2)

    return prev_layer, trainable_layers

Instances