I’m working with pytorch and I’m really missing a layer from keras: tf.keras.layers.StringLookup
that helped with processing of ids. Is there any workaround to do something similar with pytorch?
And example of the functionality im looking for:
vocab = ["a", "b", "c", "d"]
data = tf.constant([["a", "c", "d"], ["d", "a", "b"]])
layer = tf.keras.layers.StringLookup(vocabulary=vocab)
layer(data)
Outputs:
<tf.Tensor: shape=(2, 3), dtype=int64, numpy=
array([[1, 3, 4],
[4, 1, 2]])>