how can I change
tf.contrib.layers.xavier_initializer()
to tf version >= 2.0.0 ??
all codes:
W1 = tf.get_variable("W1", shape=[self.input_size, h_size],
initializer=tf.contrib.layers.xavier_initializer())
change tf.contrib.layers.xavier_initializer() to 2.0.0
Viewed 7538
2 Answers
the TF2 replacement for tf.contrib.layers.xavier_initializer() is tf.keras.initializers.glorot_normal(Xavier and Glorot are 2 names for the same initializer algorithm) documentation link.
if dtype is important for some compatibility reasons - use tf.compat.v1.keras.initializers.glorot_normal
Just to slightly clarify @poe-dator answer's:
Using TF slim's tf.contrib.layers.xavier_initializer() without any parameters, returns uniformly distributed weights (uniform=True set by default).
So basically, the mapping between TF Slim and Keras works as follows:
tf.contrib.layers.xavier_initializer()should be replaced bytf.keras.initializers.GlorotUniform()tf.contrib.layers.xavier_initializer(uniform=False)should be replaced bytf.keras.initializers.GlorotNormal()
This difference is also noted in another Stack Overflow post, so kudos to the posters there.
Related