Difference between Variable and get_variable in TensorFlow

by

I’d recommend to always use tf.get_variable(...) — it will make it way easier to refactor your code if you need to share variables at any time, e.g. in a multi-gpu setting (see the multi-gpu CIFAR example). There is no downside to it.

Pure tf.Variable is lower-level; at some point tf.get_variable() did not exist so some code still uses the low-level way.

More Related Contents:

  1. What are logits? What is the difference between softmax and softmax_cross_entropy_with_logits?
  2. TensorFlow Only running on 1/32 of the Training data provided [duplicate]
  3. How to get current available GPUs in tensorflow?
  4. How to export Keras .h5 to tensorflow .pb?
  5. Keras + Tensorflow and Multiprocessing in Python
  6. Is it still necessary to install CUDA before using the conda tensorflow-gpu package?
  7. Meaning of inter_op_parallelism_threads and intra_op_parallelism_threads
  8. How do I use TensorFlow GPU?
  9. Is Tensorflow compatible with a Windows workflow?
  10. Keras replacing input layer
  11. Tensorflow: How to write op with gradient in python?
  12. Reproducible results in Tensorflow with tf.set_random_seed
  13. Keras Sequential model with multiple inputs
  14. ValueError at /image/ Tensor Tensor(“activation_5/Softmax:0”, shape=(?, 4), dtype=float32) is not an element of this graph
  15. Streaming large training and test files into Tensorflow’s DNNClassifier
  16. Conditional assignment of tensor values in TensorFlow
  17. How to get other metrics in Tensorflow 2.0 (not only accuracy)?
  18. Clearing Tensorflow GPU memory after model execution
  19. Removing then Inserting a New Middle Layer in a Keras Model
  20. Why can’t I get reproducible results in Keras even though I set the random seeds?
  21. AttributeError: module ‘tensorflow.python.keras.utils.generic_utils’ has no attribute ‘populate_dict_with_module_objects’
  22. How to get stable results with TensorFlow, setting random seed
  23. “freeze” some variables/scopes in tensorflow: stop_gradient vs passing variables to minimize
  24. How can I visualize the weights(variables) in cnn in Tensorflow?
  25. overcome Graphdef cannot be larger than 2GB in tensorflow
  26. NotImplementedError: Cannot convert a symbolic Tensor (2nd_target:0) to a numpy array
  27. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  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