Merge pull request #20 from tnakae/feature_support-python35

this is UNOFFICIAL implementation.

# Requirements

- python 3

- python >= 3.5

- Tensorflow

- Numpy

- sklearn

※この実装は論文著者とは無関係です。

# 動作要件

- python 3

- python >= 3.5

- Tensorflow

- Numpy

- sklearn

            for size in self.hidden_layer_sizes[:-1]:

                n_layer += 1

                z = tf.layers.dense(z, size, activation=self.activation,

                    name=f"layer_{n_layer}")

                    name="layer_{}".format(n_layer))

            # activation function of last layer is linear

            n_layer += 1

            z = tf.layers.dense(z, self.hidden_layer_sizes[-1],

                name=f"layer_{n_layer}")

                name="layer_{}".format(n_layer))

        return z

            for size in self.hidden_layer_sizes[:-1][::-1]:

                n_layer += 1

                z = tf.layers.dense(z, size, activation=self.activation,

                    name=f"layer_{n_layer}")

                    name="layer_{}".format(n_layer))

            # activation function of last layes is linear

            n_layer += 1

            x_dash = tf.layers.dense(z, self.input_size,

                name=f"layer_{n_layer}")

                name="layer_{}".format(n_layer))

        return x_dash

                if (epoch + 1) % 100 == 0:

                    loss_val = self.sess.run(loss, feed_dict={input:x, drop:0})

                    print(f" epoch {epoch+1}/{self.epoch_size} : loss = {loss_val:.3f}")

                    print(" epoch {}/{} : loss = {:.3f}".format(epoch + 1, self.epoch_size, loss_val))

            # Fix GMM parameter

            fix = self.gmm.fix_op()

            for size in self.hidden_layer_sizes[:-1]:

                n_layer += 1

                z = tf.layers.dense(z, size, activation=self.activation,

                    name=f"layer_{n_layer}")

                    name="layer_{}".format(n_layer))

                if dropout_ratio is not None:

                    z = tf.layers.dropout(z, dropout_ratio,

                        name=f"drop_{n_layer}")

                        name="drop_{}".format(n_layer))

            # Last layer uses linear function (=logits)

            size = self.hidden_layer_sizes[-1]