tf.compat.v1.nn.relu6

Computes Rectified Linear 6: min(max(features, 0), 6).

In comparison with tf.nn.relu, relu6 activation functions have shown to empirically perform better under low-precision conditions (e.g. fixed point inference) by encouraging the model to learn sparse features earlier. Source: Convolutional Deep Belief Networks on CIFAR-10: Krizhevsky et al., 2010.

For example:

x = tf.constant([-3.0, -1.0, 0.0, 6.0, 10.0], dtype=tf.float32)
y = tf.nn.relu6(x)
y.numpy()
array([0., 0., 0., 6., 6.], dtype=float32)

features A Tensor with type float, double, int32, int64, uint8, int16, or int8.
name A name for the operation (optional).

A Tensor with the same type as features.

Convolutional Deep Belief Networks on CIFAR-10: Krizhevsky et al., 2010 (pdf)