Stack Overflow
Stack Overflow

Questions tagged [gated-recurrent-unit]

A Gated Recurrent Unit (GRU) is a type of unit in a recurrent neural network.

80 questions
20
votes
1 answer

ValueError: The two structures don't have the same number of elements

with tf.variable_scope('forward'): cell_img_fwd = tf.nn.rnn_cell.GRUCell(hidden_state_size, hidden_state_size) img_init_state_fwd = rnn_img_mapped[:, 0, :] img_init_state_fwd = tf.multiply( img_init_state_fwd, …
user3640928
  • 231
  • 1
  • 2
  • 7
13
votes
1 answer

Tensorflow Serving - Stateful LSTM

Is there a canonical way to maintain a stateful LSTM, etc. with Tensorflow Serving? Using the Tensorflow API directly this is straightforward - but I'm not certain how best to accomplish persisting LSTM state between calls after exporting the model…
Asher Newcomer
  • 201
  • 1
  • 7
10
votes
2 answers

In tensorflow, how to iterate over a sequence of inputs stored in a tensor?

I am trying RNN on a variable length multivariate sequence classification problem. I have defined following function to get the output of the sequence (i.e. the output of RNN cell after the final input from sequence is fed) def…
exAres
  • 4,806
  • 16
  • 53
  • 95
9
votes
3 answers

Mixing feed forward layers and recurrent layers in Tensorflow?

Has anyone been able to mix feedforward layers and recurrent layers in Tensorflow? For example: input->conv->GRU->linear->output I can imagine one can define his own cell with feedforward layers and no state which can then be stacked using the…
Fiorentino
  • 101
  • 6
8
votes
2 answers

calculating the number of parameters of a GRU layer (Keras)

Why the number of parameters of the GRU layer is 9600? Shouldn't it be ((16+32)*32 + 32) * 3 * 2 = 9,408 ? or, rearranging, 32*(16 + 32 + 1)*3*2 = 9408 model = tf.keras.Sequential([ tf.keras.layers.Embedding(input_dim=4500, output_dim=16,…
Abid Orucov
  • 93
  • 1
  • 4
8
votes
1 answer

Order of layers in hidden states in PyTorch GRU return

This is the API I am looking at, https://pytorch.org/docs/stable/nn.html#gru It outputs: output of shape (seq_len, batch, num_directions * hidden_size) h_n of shape (num_layers * num_directions, batch, hidden_size) For GRU with more than one…
zyxue
  • 7,904
  • 5
  • 48
  • 74
7
votes
3 answers

Reset parameters of a neural network in pytorch

I have a neural network with the following structure: class myNetwork(nn.Module): def __init__(self): super(myNetwork, self).__init__() self.bigru = nn.GRU(input_size=2, hidden_size=100, batch_first=True, bidirectional=True) …
learner
  • 3,168
  • 3
  • 18
  • 35
6
votes
1 answer

How do I set the initial state of a keras.layers.RNN instance?

I have created a stacked keras decoder model using the following loop: # Create the encoder # Define an input sequence. encoder_inputs = keras.layers.Input(shape=(None, num_input_features)) # Create a list of RNN Cells, these are then concatenated…
Aesir
  • 2,033
  • 1
  • 28
  • 39
5
votes
1 answer

Implementing Seq2Seq with GRU in Keras

I implanted the ten-minutes LSTM example from the Keras site and adjusted the network to handle word embeddings instead of character ones (from https://blog.keras.io/a-ten-minute-introduction-to-sequence-to-sequence-learning-in-keras.html). It…
Ridvan Aydin Sibic
  • 77
  • 5
5
votes
1 answer

How can I improve the classification accuracy of LSTM,GRU recurrent neural networks

Binary Classification Problem in Tensorflow: I have gone through the online tutorials and trying to apply it on a real-time problem using gated-recurrent unit (GRU). I have tried all the possibilities which I know to improve the classification. 1)…
OJJ
  • 53
  • 1
  • 4
5
votes
1 answer

Explanation of GRU cell in Tensorflow?

Following code of Tensorflow's GRUCell unit shows typical operations to get a updated hidden state, when previous hidden state is provided along with current input in the sequence. def __call__(self, inputs, state, scope=None): """Gated…
exAres
  • 4,806
  • 16
  • 53
  • 95
4
votes
1 answer

Finding TensorFlow equivalent of Pytorch GRU feature

I am confused about how to reconstruct the following Pytorch code in TensorFlow. It uses both the input size x and the hidden size h to create a GRU layer import torch torch.nn.GRU(64, 64*2, batch_first=True, return_state=True) Instinctively, I…
tensornerd
  • 41
  • 2
4
votes
1 answer

How to get final hidden state of bidirectional 2-layers GRU in pytorch

I am struggling with understanding how to get hidden layers and concatenate them. I am using the following code as an example: class classifier(nn.Module): #define all the layers used in model def __init__(self, vocab_size, embedding_dim,…
Abdul Wahab
  • 137
  • 2
  • 11
4
votes
2 answers

Keras - GRU layer with recurrent dropout - loss: 'nan', accuracy: 0

Problem description I am going through "Deep Learning in Python" by François Chollet (publisher webpage, notebooks on github). Replicating examples from Chapter 6 I encountered problems with (I believe) GRU layer with recurrent dropout. The code in…
user351437
  • 61
  • 6
4
votes
1 answer

Understanding GRU Architecture - Keras

I am using the Mycroft AI wake word detection and I am trying to understand the dimensions of the network. The following lines show the model in Keras: model = Sequential() model.add(GRU( params.recurrent_units, activation='linear', …
kleka
  • 364
  • 3
  • 14
1
2 3 4 5 6