Defined in generated file: python/ops/gen_array_ops.py Stops gradient computation.

# Aliases:

• tf.compat.v1.stop_gradient
• tf.compat.v2.stop_gradient

 tf.stop_gradient(
    input,
    name=None
)

When executed in a graph, this op outputs its input tensor as-is. When building ops to compute gradients, this op prevents the contribution of its inputs to be taken into account. Normally, the gradient generator adds ops to a graph to compute the derivatives of a specified 'loss' by recursively finding out inputs that contributed to its computation. If you insert this op in the graph it inputs are masked from the gradient generator. They are not taken into account for computing gradients. This is useful any time you want to compute a value with TensorFlow but need to pretend that the value was a constant. Some examples include:

• The EMalgorithmwheretheM-step shouldnotinvolvebackpropagationthroughtheoutput oftheE-step.``
• Contrastive divergencetraining ofBoltzmannmachines where,when differentiating the energyfunction,thetraining mustnotbackpropagatethroughthegraphthat generated the samples fromthemodel.
• Adversarial training, where nobackprop shouldhappen through the adversarial example generationprocess.

# Args:

• input: A Tensor.
• name: A name for the operation (optional).

# Returns:

A Tensor. Has the same type as input.