|TensorFlow 1 version||View source on GitHub|
Computes the mean of elements across dimensions of a tensor.
tf.math.reduce_mean( input_tensor, axis=None, keepdims=False, name=None )
Used in the guide:
- Better performance with tf.function and AutoGraph
- Eager execution
- Ragged tensors
- Train and evaluate with Keras
- Training checkpoints
- Writing custom layers and models with Keras
Used in the tutorials:
- Convolutional Variational Autoencoder
- Custom training with tf.distribute.Strategy
- Custom training: basics
- Image captioning with visual attention
- Neural machine translation with attention
- Neural style transfer
- Text generation with an RNN
- Transformer model for language understanding
input_tensor along the dimensions given in
keepdims is true, the rank of the tensor is reduced by 1 for each
keepdims is true, the reduced dimensions
are retained with length 1.
axis is None, all dimensions are reduced, and a
tensor with a single element is returned.
x = tf.constant([[1., 1.], [2., 2.]]) tf.reduce_mean(x) # 1.5 tf.reduce_mean(x, 0) # [1.5, 1.5] tf.reduce_mean(x, 1) # [1., 2.]
input_tensor: The tensor to reduce. Should have numeric type.
axis: The dimensions to reduce. If
None(the default), reduces all dimensions. Must be in the range
keepdims: If true, retains reduced dimensions with length 1.
name: A name for the operation (optional).
The reduced tensor.
Equivalent to np.mean
Please note that
np.mean has a
dtype parameter that could be used to
specify the output type. By default this is
dtype=float64. On the other
tf.reduce_mean has an aggressive type inference from
x = tf.constant([1, 0, 1, 0]) tf.reduce_mean(x) # 0 y = tf.constant([1., 0., 1., 0.]) tf.reduce_mean(y) # 0.5