# tf.contrib.opt.clip_gradients_by_global_norm

<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/opt/python/training/multitask_optimizer_wrapper.py#L115-L143) |

Clips gradients of a multitask loss by their global norm.

    tf.contrib.opt.clip_gradients_by_global_norm(
        gradients_variables, clip_norm=20.0
    )

Ignores all-zero tensors when computing the global norm.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `gradients_variables` | a list of pairs (gradient, variable). |
| `clip_norm` | a float Tensor, the global norm to clip on. Default is 20.0. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| `list` | A list of pairs of the same type as gradients_variables,. |
| `fixed_global_norm` | A 0-D (scalar) Tensor representing the global norm. |

<br />