ML Community Day is November 9! Join us for updates from TensorFlow, JAX, and more Learn more


Gated Recurrent Unit - Cho et al. 2014.

Inherits From: GRU, RNN, Layer, Module

Used in the notebooks

Used in the guide Used in the tutorials

See the Keras RNN API guide for details about the usage of RNN API.

Based on available runtime hardware and constraints, this layer will choose different implementations (cuDNN-based or pure-TensorFlow) to maximize the performance. If a GPU is available and all the arguments to the layer meet the requirement of the CuDNN kernel (see below for details), the layer will use a fast cuDNN implementation.

The requirements to use the cuDNN implementation are:

  1. activation == tanh
  2. recurrent_activation == sigmoid
  3. recurrent_dropout == 0
  4. unroll is False
  5. use_bias is True
  6. reset_after is True
  7. Inputs, if use masking, are strictly right-padded.
  8. Eager execution is enabled in the outermost context.

There are two variants of the GRU implementation. The default one is based on v3 and has reset gate applied to hidden state before matrix multiplication. The other one is based on original and has the order reversed.

The second variant is compatible with CuDNNGRU (GPU-only) and allows inference on CPU. Thus it has separate biases for kernel and recurrent_kernel. To use this variant, set 'reset_after'=True and recurrent_activation='sigmoid'.

For example:

inputs = tf.random.normal([32, 10, 8])
gru = tf.keras.layers.GRU(4)
output = gru(inputs)
(32, 4)
gru = tf.keras.layers.GRU(4, return_sequences=True, return_state=True)
whole_sequence_output, final_state = gru(inputs)
(32, 10, 4)
(32, 4)

units Positive integer, dimensionality of the output space.
activation Activation function to use. Default: hyperbolic tangent (tanh). If you pass None, no activation is applied (ie. "linear" activation: a(x) = x).
recurrent_activation Activation function to use for the recurrent step. Default