# tf.contrib.training.resample_at_rate

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/contrib/training/python/training/resample.py#L68-L98) |

Given `inputs` tensors, stochastically resamples each at a given rate.

    tf.contrib.training.resample_at_rate(
        inputs, rates, scope=None, seed=None, back_prop=False
    )

For example, if the inputs are `[[a1, a2], [b1, b2]]` and the rates
tensor contains `[3, 1]`, then the return value may look like `[[a1,
a2, a1, a1], [b1, b2, b1, b1]]`. However, many other outputs are
possible, since this is stochastic -- averaged over many repeated
calls, each set of inputs should appear in the output `rate` times
the number of invocations.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `inputs` | A list of tensors, each of which has a shape of `[batch_size, ...]` |
| `rates` | A tensor of shape `[batch_size]` containing the resampling rates for each input. |
| `scope` | Scope for the op. |
| `seed` | Random seed to use. |
| `back_prop` | Whether to allow back-propagation through this op. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| Selections from the input tensors. ||

<br />