Compute pairwise distance in a batch without replicating tensor in Tensorflow?

by

You can use some linear algebra to turn it into matrix ops. Note that what you need matrix D where a[i] is the ith row of your original matrix and 

D[i,j] = (a[i]-a[j])(a[i]-a[j])'

You can rewrite that into 

D[i,j] = r[i] - 2 a[i]a[j]' + r[j]

Where r[i] is squared norm of ith row of the original matrix.

In a system that supports standard broadcasting rules you can treat r as a column vector and write D as

D = r - 2 A A' + r'

In TensorFlow you could write this as

A = tf.constant([[1, 1], [2, 2], [3, 3]])
r = tf.reduce_sum(A*A, 1)

# turn r into column vector
r = tf.reshape(r, [-1, 1])
D = r - 2*tf.matmul(A, tf.transpose(A)) + tf.transpose(r)
sess = tf.Session()
sess.run(D)

result

array([[0, 2, 8],
       [2, 0, 2],
       [8, 2, 0]], dtype=int32)

More Related Contents:

  1. How to save/restore a model after training?
  2. How to prevent tensorflow from allocating the totality of a GPU memory?
  3. Keras, How to get the output of each layer?
  4. Deep-Learning Nan loss reasons
  5. Failed to get convolution algorithm. This is probably because cuDNN failed to initialize,
  6. Why is TensorFlow 2 much slower than TensorFlow 1?
  7. Fix not load dynamic library for Tensorflow GPU
  8. Can Keras with Tensorflow backend be forced to use CPU or GPU at will?
  9. ImportError: No module named tensorflow
  10. Cannot import Tensorflow for GPU on Windows 10
  11. What is the difference between tf.keras and tf.python.keras?
  12. TensorFlow: Remember LSTM state for next batch (stateful LSTM)
  13. Tensorflow set CUDA_VISIBLE_DEVICES within jupyter
  14. How to *actually* read CSV data in TensorFlow?
  15. Negative dimension size caused by subtracting 3 from 1 for ‘conv2d_2/convolution’
  16. Dimension of shape in conv1D
  17. Is there a simpler way to handle batch inputs from tfrecords?
  18. Loading a trained Keras model and continue training
  19. Keras Custom loss function to pass arguments other than y_true and y_pred
  20. Split .tfrecords file into many .tfrecords files
  21. tf.nn.conv2d vs tf.layers.conv2d
  22. Multiple outputs in Keras
  23. Can’t install Tensorflow Mac
  24. How to implement Grad-CAM on a trained network
  25. Error while import tensorflow module
  26. Tensorflow Allocation Memory: Allocation of 38535168 exceeds 10% of system memory
  27. looking for source code of from gen_nn_ops in tensorflow
  28. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  29. Permission denied when installing Tensorflow
  30. How is the Keras Conv1D input specified? I seem to be lacking a dimension

Leave a Comment