Sparse Tensor (matrix) from a dense Tensor Tensorflow

by

You can use tf.where and tf.gather_nd to do that:

import numpy as np
import tensorflow as tf

# Make a tensor from a constant
a = np.reshape(np.arange(24), (3, 4, 2))
a_t = tf.constant(a)
# Find indices where the tensor is not zero
idx = tf.where(tf.not_equal(a_t, 0))
# Make the sparse tensor
# Use tf.shape(a_t, out_type=tf.int64) instead of a_t.get_shape()
# if tensor shape is dynamic
sparse = tf.SparseTensor(idx, tf.gather_nd(a_t, idx), a_t.get_shape())
# Make a dense tensor back from the sparse one, only to check result is correct
dense = tf.sparse_tensor_to_dense(sparse)
# Check result
with tf.Session() as sess:
    b = sess.run(dense)
np.all(a == b)
>>> True

More Related Contents:

  1. How do you change the size of figures drawn with Matplotlib?
  2. How to save/restore a model after training?
  3. How to prevent tensorflow from allocating the totality of a GPU memory?
  4. Keras, How to get the output of each layer?
  5. How to find the exact intersection of a curve (as np.array) with y==0?
  6. Set Colorbar Range in matplotlib
  7. Deep-Learning Nan loss reasons
  8. Failed to get convolution algorithm. This is probably because cuDNN failed to initialize,
  9. Why is TensorFlow 2 much slower than TensorFlow 1?
  10. Fix not load dynamic library for Tensorflow GPU
  11. How to trace the path in a Breadth-First Search?
  12. Can Keras with Tensorflow backend be forced to use CPU or GPU at will?
  13. ImportError: No module named tensorflow
  14. Cannot import Tensorflow for GPU on Windows 10
  15. What is the difference between tf.keras and tf.python.keras?
  16. Negative dimension size caused by subtracting 3 from 1 for ‘conv2d_2/convolution’
  17. Dimension of shape in conv1D
  18. Compute pairwise distance in a batch without replicating tensor in Tensorflow?
  19. Replacing placeholder for tensorflow v2
  20. How to know if underfitting or overfitting is occuring?
  21. How to install Tensorflow on Python 2.7 on Windows?
  22. How to handle non-determinism when training on a GPU?
  23. ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [8, 28, 28]
  24. How can I scrape tooltips value from a Tableau graph embedded in a webpage
  25. Why is numpy native on M1 Max greatly slower than on old Intel i5?
  26. Is it thread-safe when using tf.Session in inference service?
  27. How do I plot a Keras/Tensorflow subclassing API model?
  28. Attach a queue to a numpy array in tensorflow for data fetch instead of files?
  29. TensorFlow 2.0 Keras: How to write image summaries for TensorBoard
  30. How is the Keras Conv1D input specified? I seem to be lacking a dimension

Leave a Comment