Since version 0.8 there is a Xavier initializer, see here for the docs.
You can use something like this:
W = tf.get_variable("W", shape=[784, 256],
initializer=tf.contrib.layers.xavier_initializer())
More Related Contents:
- TensorFlow not found using pip
- Convert a tensor to numpy array in Tensorflow?
- Keras not training on entire dataset
- How to apply gradient clipping in TensorFlow?
- FailedPreconditionError: Attempting to use uninitialized in Tensorflow
- NotImplementedError: Layers with arguments in `__init__` must override `get_config`
- Tensorflow error : DLL load failed: The specified procedure could not be found
- can’t import tensorflow in python, windows 10 64 bit
- How to set adaptive learning rate for GradientDescentOptimizer?
- Tensorflow Different ways to Export and Run graph in C++
- Tensorflow: How to replace a node in a calculation graph?
- This model has not yet been built error on model.summary()
- How to understand the term `tensor` in TensorFlow?
- Tensorflow r1.0 : could not a find a version that satisfies the requirement tensorflow
- TensorFlow ValueError: Cannot feed value of shape (64, 64, 3) for Tensor u’Placeholder:0′, which has shape ‘(?, 64, 64, 3)’
- TypeError: ‘Tensor’ object does not support item assignment in TensorFlow
- TensorFlow – numpy-like tensor indexing
- How do I set TensorFlow RNN state when state_is_tuple=True?
- In Tensorflow, get the names of all the Tensors in a graph
- Save and load model optimizer state
- Keras misinterprets training data shape
- In TensorFlow, what is the difference between Session.run() and Tensor.eval()?
- Why can I not import Tensorflow.contrib I get an error of No module named ‘tensorflow.python.saved
- How do I get the weights of a layer in Keras?
- Why is numpy native on M1 Max greatly slower than on old Intel i5?
- Is it thread-safe when using tf.Session in inference service?
- How do I plot a Keras/Tensorflow subclassing API model?
- Attach a queue to a numpy array in tensorflow for data fetch instead of files?
- TensorFlow 2.0 Keras: How to write image summaries for TensorBoard
- Multi-input Multi-output Model with Keras Functional API