/TensorFlow Python



Defined in tensorflow/contrib/losses/python/losses/loss_ops.py.

See the guide: Losses (contrib) > Loss operations for use in neural networks.

Adds a pairwise-errors-squared loss to the training procedure. (deprecated)

THIS FUNCTION IS DEPRECATED. It will be removed after 2016-12-30. Instructions for updating: Use tf.losses.mean_pairwise_squared_error instead. Note that the order of the predictions and labels arguments has been changed.

Unlike mean_squared_error, which is a measure of the differences between corresponding elements of predictions and labels, mean_pairwise_squared_error is a measure of the differences between pairs of corresponding elements of predictions and labels.

For example, if labels=[a, b, c] and predictions=[x, y, z], there are three pairs of differences are summed to compute the loss: loss = [ ((a-b) - (x-y)).^2 + ((a-c) - (x-z)).^2 + ((b-c) - (y-z)).^2 ] / 3

Note that since the inputs are of size [batch_size, d0, ... dN], the corresponding pairs are computed within each batch sample but not across samples within a batch. For example, if predictions represents a batch of 16 grayscale images of dimension [batch_size, 100, 200], then the set of pairs is drawn from each image, but not across images.

weights acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If weights is a tensor of size [batch_size], then the total loss for each sample of the batch is rescaled by the corresponding element in the weights vector.


  • predictions: The predicted outputs, a tensor of size [batch_size, d0, .. dN] where N+1 is the total number of dimensions in predictions.
  • labels: The ground truth output tensor, whose shape must match the shape of the predictions tensor.
  • weights: Coefficients for the loss a scalar, a tensor of shape [batch_size] or a tensor whose shape matches predictions.
  • scope: The scope for the operations performed in computing the loss.


A scalar Tensor representing the loss value.


  • ValueError: If the shape of predictions doesn't match that of labels or if the shape of weights is invalid.

© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.