|---| | [ View source on GitHub](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/math/numeric.py#L64-L96) | Clips values to a specified min and max while leaving gradient unaltered. tfp.math.clip_by_value_preserve_gradient( t, clip_value_min, clip_value_max, name=None ) Like [`tf.clip_by_value`](https://www.tensorflow.org/api_docs/python/tf/clip_by_value), this function returns a tensor of the same type and shape as input `t` but with values clamped to be no smaller than to `clip_value_min` and no larger than `clip_value_max`. Unlike [`tf.clip_by_value`](https://www.tensorflow.org/api_docs/python/tf/clip_by_value), the gradient is unaffected by this op, i.e., tf.gradients(tfp.math.clip_by_value_preserve_gradient(x), x)[0] # ==> ones_like(x) > [!NOTE] > **Note:** `clip_value_min` needs to be smaller or equal to `clip_value_max` for correct results.


| ## Args || |---|---| | `t` | A `Tensor`. | | `clip_value_min` | A scalar `Tensor`, or a `Tensor` with the same shape as `t`. The minimum value to clip by. | | `clip_value_max` | A scalar `Tensor`, or a `Tensor` with the same shape as `t`. The maximum value to clip by. | | `name` | A name for the operation (optional). Default value: `'clip_by_value_preserve_gradient'`. |



| ## Returns || |---|---| | `clipped_t` | A clipped `Tensor`. |