0fbb027c8b368473e7e7fd6b05db5911cd34ce76,autokeras/blocks/basic.py,Embedding,build,#Embedding#Any#Any#,855

Before Change


        input_node = nest.flatten(inputs)[0]
        // TODO: support more pretrained embedding layers.
        // glove, fasttext, and word2vec
        pretraining = self.pretraining or hp.Choice(
            "pretraining",
            ["random", "glove", "fasttext", "word2vec", "none"],
            default="none",
        )
        embedding_dim = self.embedding_dim or hp.Choice(
            "embedding_dim", [32, 64, 128, 256, 512], default=128
        )
        if pretraining != "none":
            // TODO: load from pretrained weights
            layer = layers.Embedding(
                input_dim=self.max_features,
                output_dim=embedding_dim,
                input_length=input_node.shape[1],
            )
            // trainable=False,
            // weights=[embedding_matrix])
        else:
            layer = layers.Embedding(
                input_dim=self.max_features, output_dim=embedding_dim
            )
            // input_length=input_node.shape[1],
            // trainable=True)
        output_node = layer(input_node)
        if self.dropout is not None:
            dropout = self.dropout
        else:
            dropout = hp.Choice("dropout", [0.0, 0.25, 0.5], default=0.25)
        if dropout > 0:
            output_node = layers.Dropout(dropout)(output_node)
        return output_node

After Change


        input_node = nest.flatten(inputs)[0]
        // TODO: support more pretrained embedding layers.
        // glove, fasttext, and word2vec
        pretraining = utils.add_to_hp(self.pretraining, hp)
        embedding_dim = utils.add_to_hp(self.embedding_dim, hp)
        if pretraining != "none":
            // TODO: load from pretrained weights
            layer = layers.Embedding(
                input_dim=self.max_features,
                output_dim=embedding_dim,
                input_length=input_node.shape[1],
            )
            // trainable=False,
            // weights=[embedding_matrix])
        else:
            layer = layers.Embedding(
                input_dim=self.max_features, output_dim=embedding_dim
            )
            // input_length=input_node.shape[1],
            // trainable=True)
        output_node = layer(input_node)
        dropout = utils.add_to_hp(self.dropout, hp)
        if dropout > 0:
            output_node = layers.Dropout(dropout)(output_node)
        return output_node
Italian Trulli
In pattern: SUPERPATTERN

Frequency: 4

Non-data size: 21

Instances


Project Name: jhfjhfj1/autokeras
Commit Name: 0fbb027c8b368473e7e7fd6b05db5911cd34ce76
Time: 2021-03-18
Author: samriddhidjokestersinha@gmail.com
File Name: autokeras/blocks/basic.py
Class Name: Embedding
Method Name: build


Project Name: keras-team/autokeras
Commit Name: 48d4604e38da537503f1d5fe3afa94e4d7f708d7
Time: 2021-02-07
Author: mandalbiswadip448@gmail.com
File Name: autokeras/blocks/basic.py
Class Name: RNNBlock
Method Name: build


Project Name: jhfjhfj1/autokeras
Commit Name: 0fbb027c8b368473e7e7fd6b05db5911cd34ce76
Time: 2021-03-18
Author: samriddhidjokestersinha@gmail.com
File Name: autokeras/blocks/basic.py
Class Name: Embedding
Method Name: build