tensorflow einsum vs. matmul vs. tensordot

by

Both tf.tensordot() and tf.einsum() are syntactic sugar that wrap one or more invocations of tf.matmul() (although in some special cases tf.einsum() can reduce to the simpler elementwise tf.multiply()).

In the limit, I’d expect all three functions to have equivalent performance for the same computation. However, for smaller matrices, it may be more efficient to use tf.matmul() directly, because it would yield a simpler TensorFlow graph with fewer operations, and hence the pre-operation invocation costs will be lower.

More Related Contents:

  1. How to print the value of a Tensor object in TensorFlow?
  2. What are logits? What is the difference between softmax and softmax_cross_entropy_with_logits?
  3. How to get current available GPUs in tensorflow?
  4. How to export Keras .h5 to tensorflow .pb?
  5. How to choose cross-entropy loss in TensorFlow?
  6. Keras + Tensorflow and Multiprocessing in Python
  7. Is it still necessary to install CUDA before using the conda tensorflow-gpu package?
  8. Meaning of inter_op_parallelism_threads and intra_op_parallelism_threads
  9. Error running basic tensorflow example
  10. How do I use TensorFlow GPU?
  11. Is Tensorflow compatible with a Windows workflow?
  12. Tensorflow, best way to save state in RNNs?
  13. Remove nodes from graph or reset entire default graph
  14. How does Keras 1d convolution layer work with word embeddings – text classification problem? (Filters, kernel size, and all hyperparameter)
  15. ValueError at /image/ Tensor Tensor(“activation_5/Softmax:0”, shape=(?, 4), dtype=float32) is not an element of this graph
  16. Streaming large training and test files into Tensorflow’s DNNClassifier
  17. What do I need K.clear_session() and del model for (Keras with Tensorflow-gpu)?
  18. Clearing Tensorflow GPU memory after model execution
  19. Tensorflow: Using Adam optimizer
  20. AttributeError: module ‘tensorflow.python.keras.utils.generic_utils’ has no attribute ‘populate_dict_with_module_objects’
  21. How to get stable results with TensorFlow, setting random seed
  22. “freeze” some variables/scopes in tensorflow: stop_gradient vs passing variables to minimize
  23. Load numpy array in google-cloud-ml job
  24. overcome Graphdef cannot be larger than 2GB in tensorflow
  25. How to create a keras layer with a custom gradient in TF2.0?
  26. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  27. Permission denied when installing Tensorflow
  28. How to use TensorFlow metrics in Keras
  29. How to visualize RNN/LSTM gradients in Keras/TensorFlow?
  30. How is the Keras Conv1D input specified? I seem to be lacking a dimension

Leave a Comment