tf.contrib.opt.clip_gradients_by_global_norm

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.

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

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.