A Gated Recurrent Unit (GRU) is a type of unit in a recurrent neural network.
Questions tagged [gated-recurrent-unit]
80 questions
2
votes
3 answers
Keras GRU model predicts only [-0., -0., -0., -0., -0.]
I'm trying to predict 5 periodic prices of cryptocurrency based on previous 50 inputs.
>>> X_train.shape, X_test.shape, Y_train.shape, Y_test.shape
((291314, 50, 8), (72829, 50, 8), (291314, 5), (72829, 5))
Here I have 50 previous samples x 8…
Vassily
- 5,263
- 4
- 33
- 63
2
votes
0 answers
Tensorflow Stacked GRU Cell
I am trying to implement a stacked RNN with MultiRNNCell and GRUCell in tensorflow.
From the default implementation of GRUCell, it can be seen that the "output" and the "state" of the GRUCell are the same:
class GRUCell(RNNCell)
...
def…
Jamie Cho
- 65
- 1
- 5
2
votes
1 answer
Tensorflow RNN input size
I am trying to use tensorflow to create a recurrent neural network. My code is something like this:
import tensorflow as tf
rnn_cell = tf.nn.rnn_cell.GRUCell(3)
inputs = [tf.constant([[0, 1]], dtype=tf.float32), tf.constant([[2, 3]],…
Vlad Firoiu
- 987
- 1
- 8
- 17
2
votes
0 answers
how to train data with large differences between values
I'm currently working on recurrent neural networks for text-to-speech but I'm stuck at one point.
I've some input files and they have characteristic features of text(phonemes etc.) with dimension 490. The output files are mgc(60-d), bap(25-d) and…
MGoksu
- 510
- 6
- 13
1
vote
1 answer
how to add unrelated training data with an embedding layer?
I am beginner in RNNs and would like to build a model gated recurrent unit GRU for predicting a user's action on an E-commerce website called google merchandize store that sells Google branded merchandise.
We have 5 different actions:
Add to…
Youssef Ashour
- 11
- 1
1
vote
0 answers
Pytorch GRU Trained on one class to Predict Unlabelled Data
I am creating a GRU to predict if data derived from traffic packets from a device is considered safe or anomalous. I plan to do this by training a model only on safe/ normal operating data and then having it check what it considers new unseen…
S_G
- 17
- 7
1
vote
0 answers
GRU Failed to call ThenRnnForward with model config
I am working with a multi classification problem using GRU architecture. It seems to have a configuration error. Please help me to debug the model. Thanks in advance.
Here I have provided the model:
# build the network
model =…
AMA
- 15
- 3
1
vote
0 answers
What is proper way to mimic keras timedistributed layer in pytorch?
I'm trying to mimic TimeDistributed in PyTorch just like keras TimeDistributed. please see below model
class GRULinear(nn.Module):
def __init__(self,input_size, hidden_size, num_layers, batch_first=False):
super().__init__()
…
Sky savani
- 37
- 3
1
vote
0 answers
PyTorch: GRU, one-to-many / many-to-one
I would like to implement a GRU able to encode a sequence of vectors to one vector (many-to-one), and then another GRU able to decode a vector to a sequence of vector (one-to-many). The size of the vectors wouldn't be changed. I would like to have…
papyrus
- 33
- 5
1
vote
0 answers
Adapting an LSTM Encoder Decoder sequence prediction loop for GRUs
How do I resolve this error?
ValueError: Layer model_101 expects 2 input(s), but it received 1 input tensors. Inputs received: []
I am following the guide from Jason Brownlee on how…
Simon
- 101
- 1
- 6
1
vote
2 answers
RNN - RuntimeError: input must have 3 dimensions, got 2
I’m getting the following error:
RuntimeError: input must have 3 dimensions, got 2
I have a single feature column that I am trying to feed into a GRU neural net.
Below are my data loader and neural net. I have also included the output of my data…
Mattpats
- 414
- 2
- 9
- 21
1
vote
0 answers
Trigger Word Detection training giving wrong predictions
After completing the assignment on trigger word detection in Andrew ng s course. I made some training examples and tried the same model but eventhough the accuracy is .88(which is not great considering the skewness of the data) the model is doing…
AVA
- 173
- 1
- 1
- 6
1
vote
1 answer
What do W and U notate in a GRU?
I'm trying to figure out how to backpropagate a GRU Recurrent network, but I'm having trouble understanding the GRU architecture precisely.
The image below shows a GRU cell with 3 neural networks, receiving the concatenated previous hidden state and…
Sebastian
- 23
- 6
1
vote
0 answers
Converting Keras Gru model to tf-lite
I am trying to convert my custom Keras model, with two bidirectional GRU layers, to tf-lite for use on mobile devices. I converted my model to the protobuff format and tried to convert it with the given code by TensorFlow:
converter =…
Jelle de Fries
- 885
- 1
- 11
- 20
1
vote
1 answer
RuntimeError: Expected hidden size (2, 24, 50), got (2, 30, 50)
I am trying to build a model for learning assigned scores (real numbers) to some sentences in a data set. I use RNNs (in PyTorch) for this purpose.
I have defined a model:
class RNNModel1(nn.Module):
def forward(self, input ,hidden_0):
…
Mahsa
- 581
- 1
- 9
- 28