How to assign a value to a TensorFlow variable?

by

In TF1, the statement x.assign(1) does not actually assign the value 1 to x, but rather creates a tf.Operation that you have to explicitly run to update the variable.* A call to Operation.run() or Session.run() can be used to run the operation:

assign_op = x.assign(1)
sess.run(assign_op)  # or `assign_op.op.run()`
print(x.eval())
# ==> 1

(* In fact, it returns a tf.Tensor, corresponding to the updated value of the variable, to make it easier to chain assignments.)

However, in TF2 x.assign(1) will now assign the value eagerly:

x.assign(1)
print(x.numpy())
# ==> 1

More Related Contents:

  1. How to make a custom activation function with only Python in Tensorflow?
  2. Multiple outputs in Keras
  3. What is right batch normalization function in Tensorflow?
  4. Keras, How to get the output of each layer?
  5. Using a pre-trained word embedding (word2vec or Glove) in TensorFlow
  6. What is the difference between ‘SAME’ and ‘VALID’ padding in tf.nn.max_pool of tensorflow?
  7. What is a `”Python”` layer in caffe?
  8. How to apply gradient clipping in TensorFlow?
  9. How to initialize weights in PyTorch?
  10. Tensorflow: How to replace or modify gradient?
  11. How do I initialize weights in PyTorch?
  12. Why do we need to call zero_grad() in PyTorch?
  13. Keras custom loss function: Accessing current input pattern
  14. Negative dimension size caused by subtracting 3 from 1 for ‘conv2d_2/convolution’
  15. How do I load a caffe model and convert to a numpy array?
  16. How can I use a pre-trained neural network with grayscale images?
  17. How to understand the term `tensor` in TensorFlow?
  18. Dimension of shape in conv1D
  19. TensorFlow ValueError: Cannot feed value of shape (64, 64, 3) for Tensor u’Placeholder:0′, which has shape ‘(?, 64, 64, 3)’
  20. Loading a trained Keras model and continue training
  21. How do I check if keras is using gpu version of tensorflow?
  22. Custom loss function in Keras
  23. How do I get the weights of a layer in Keras?
  24. How to handle non-determinism when training on a GPU?
  25. ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [8, 28, 28]
  26. How to implement Grad-CAM on a trained network
  27. keras: how to save the training history attribute of the history object
  28. Tensorflow One Hot Encoder?
  29. ValueError: Tensor must be from the same graph as Tensor with Bidirectinal RNN in Tensorflow
  30. how to implement custom metric in keras?

Leave a Comment