one_hot¶
dragon.vm.tensorflow.
one_hot
(
indices,
depth,
on_value=1,
off_value=0,
name=None
)[source]¶Return the one-hot representation of input.
\[\text{out}_{ij} = \begin{cases} \text{off\_value}, & \text{ if } \text{input}_{i} \neq j \\ \text{on\_value}, & \text{ otherwise } \end{cases} \]The max value of input, i.e., the
depth
should be specified:x = tf.constant([0, 1, 2, 3], tf.int64) print(tf.one_hot(x, depth=5)) # depth >= 4 will be ok
Use
on_value
oroff_value
custom filling:print(tf.one_hot(x, depth=4, on_value=2, off_value=3))
- Parameters:
- indices (dragon.Tensor) – The input tensor.
- depth (int) – The depth of representation.
- on_value (int, optional, default=1) – The value for equal branch.
- off_value (int, optional, default=0) – The value for not-equal branch.
- name (str, optional) – The operation name.
- Returns:
dragon.Tensor – The output tensor.