All Questions
577 questions
0
votes
1
answer
65
views
How to import dataset for image sequence classification?
I want to build a model (RNN) on an image sequence to predict a binary variable. I saw a lot of tutorials for multi-input classification, but I didn't find anywhere how to import my data ?
I have a ...
0
votes
1
answer
106
views
Why does my SimpleRNN model in Sequential API show '?' for output shape and zero trainable parameters when using Embedding layers?
I'm building a SimpleRNN model with an Embedding layer in Keras and encountering an issue when using the Sequential API. The model summary shows the output shape as ? and the number of trainable ...
0
votes
1
answer
76
views
Tensorflow saving model works but loading it doesn't
I trained an LSTM model in tensorflow, and it works fine, but when I save the model and then try to load it from disk, it throws me a ValueError when loading. FYI saving and loading works for other ...
0
votes
0
answers
15
views
can we use Keras Sequential model with dense layers for non-temporal data
can we use Keras Sequential model with dense layers for non-temporal data
i want to use deep learning methods with a tabular dataset of depression i found that we can use keras sequential model with ...
0
votes
0
answers
47
views
I'm having issues w/ my RNN; keeps predicting too high numbers
So I'm creating a frame AI network to predict substantial outbreaks throughout the world. The first step of my process is predicting factor data over the next couple of years. So far, I've been ...
0
votes
0
answers
36
views
Nevertheless input different 'data.csv' |Why RNN result's always linear?
It's my forecast code
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.models import Sequential
from ...
0
votes
0
answers
157
views
RNN - LSTM model for multivariate time series
I'm using LSTM for time series forecasting. This is my dataset:
enter image description here
X1,...,5 is the multivariate time serie, y the value to predict and mean, std, var, median, volume are the ...
1
vote
1
answer
92
views
Fitting an RNN model using a tensorflow dataset
I'm still new to using TensorFlow datasets and would like some help with the following. Assume I have a matrix where each row is an observation and I would like to use the window function in order to ...
- 937
0
votes
1
answer
30
views
Tensorflow error InvalidArgumentError: indices[42,244] = -1 is not in [0, 7000)
I am new to neural networks and I am trying to train an LSTM network with the following code:
# Split the data into training and testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, ...
1
vote
1
answer
184
views
Tensorflow simple cumulative sum of product RNN cell
I am trying to build a Tensorflow model that calculates a cumulative sum of products of two of the input features, i.e. predicting on only (1,2) should return 2, and then predicting on (2,2) should ...
0
votes
0
answers
115
views
RNN Keras Error || No OpKernel was registered to support Op 'CudnnRNN' used by {{node CudnnRNN}} with these attrs
I am currently working on a RNN using Keras, but I am stuck with this error:
---------------------------------------------------------------------------
ValueError ...
0
votes
1
answer
89
views
Why is my RNN model outputting the error: 'Input 0 of layer is incompatible with the layer'?
I have issue in my RNN model. The error is:
Input 0 of layer "sequential_3" is incompatible with the layer: expected shape=(None, 90, 3), found shape=(None, 3).
I still don't know how to ...
-1
votes
1
answer
34
views
ValueError: Input 0 is incompatible with layer lstm_35: expected ndim=3, found ndim=2
I am trying a regression problem with signals with a lstm. The shape of X_train is (3867,5000,1) and X_test(1998,5000,1). I have this error "ValueError: Input 0 is incompatible with layer lstm_35:...
1
vote
0
answers
85
views
ValueError: No gradients provided for any variable: (['embedding_1/embeddings:0', 'image_layer_1/kernel:0', 'image_layer_1/bias:0',
This is a program that generates captions for images and then updates the weights of the model based on the cross entropy loss. While updating the weights of the model, I come across this error and ...
- 44
0
votes
0
answers
52
views
why TensorFlow LSTM RNN fails to predict a target even if data contains it?
I have a time series DS containing ~800k time steps.
I am trying to train a simple LSTM RNN using TensorFlow/Keras.
After several unsuccessful tries to predict any useful (meaningful) target I decided ...
0
votes
1
answer
83
views
Keras SimpleRNNCell appears to fail to distribute learning among all its weights
This question is about SimpleRNNCell, a class in Tensorflow to perform basic Recurrent Neural Network. Unless there's something fundamentally wrong in my code, it appears that training is not spread ...
- 3
1
vote
0
answers
55
views
Multi Station time series forecast of flood through LSTM
I need to make flood forecast for 11 different stations. Each station require different forecast i.e. flood level (water inflow in cusecs) is different for different stations. Can A single LSTM model ...
- 9
1
vote
0
answers
52
views
InvalidArgumentError: slice index 1 of dimension 2 out of bounds when training GRU RNN
I'm a newbie in the world of recurrent neural networks and I am trying to follow a TensorFlow tutorial. This tutorial makes forecasting on weather time series data, and trains a LSTM model for it also....
- 311
0
votes
0
answers
50
views
My multilabel classification RNN is not learning
I have made a model that tries to predict the chances of every piano key playing in a time step given all time steps before it. I tried making a GRU network with 88 outputs(one for every piano key)
...
- 11
1
vote
0
answers
59
views
Why do I get different results when I use predict with all history and in real time using keras?
I wanna use predictions in real time, but I want to test that the results are the same as in the case of giving all the data as input only once. This is the code:
import numpy as np
from keras.layers ...
1
vote
0
answers
99
views
How point wise multiplication and addition takes place in LSTM?
timesteps=4, features=2 and LSTM(units=3)
Input to lstm will be (batch_size, timesteps, features) dimensions of the hidden State and cell state will be (None, unit in LSTM). When lstm take the input ...
- 49
0
votes
0
answers
55
views
Class weights not working with return_sequences Keras
''''
#x_train format = [samples, timesteps, features]
#y_train format = [samples, timesteps]
num_timesteps = len(x_train[0])
num_features = len(x_train[0, 0])
num_classes = 3
model = Sequential()
...
0
votes
0
answers
523
views
How can I reduce the batch size after a certain epoch or implement a adaptive batch size in deep learning?
I've implemented a BiLSTM model for classifying positive or negative sentiments from texts. Here, my batch size is constant in this code, which is 256 and epoch 60, but I want to reduce the batch size ...
- 138
0
votes
0
answers
80
views
Feeding UCF101 dataset through TensorFlow RNN
I am currently trying to build an RNN for the UCF101 dataset using TensorFlow.
The dataset can easily be loaded using tensorflow_datasets like so:
(train, test) = tfds.load('ucf101', split = ['train', ...
- 39
0
votes
0
answers
49
views
Sequential Keras model is able to predict different size of input?
I am new to recurrent networks and nlp. I try to create a text generation model. First I padded my sequences in order to prevent shape mismatch during training:
[1505, 422, 63, 324],
[ 7, 63, ...
- 1
0
votes
0
answers
2k
views
Exception encountered when calling layer "model_5" (type Functional)
This is the following code :
Hyper parameters
batch_size = 64
nb_epoch = 50
Parameters for dataset
img_rows, img_cols = 160, 160
nb_classes = 10
Parameters for network
nb_lstm_outputs = 30
...
-2
votes
1
answer
4k
views
Exception encountered when calling layer "model" (type Functional)
ValueError: Exception encountered when calling layer "model_5" (type Functional).
Input 0 of layer "gru_21" is incompatible with the layer: expected ndim=3, found ndim=4. ...
0
votes
1
answer
104
views
What does "ValueError: cannot reshape array of size 279936 into shape (529,529)" mean?
I was trying to run some RNN code.
# Original Dimensions
#ratio = 4
#image_width = int(image_width / ratio)
#image_height = int(image_height / ratio)
channels = 1
nb_classes ...
- 66
1
vote
0
answers
523
views
In TensorFlow/Keras, how do you use the `add_loss` method inside a custom RNN cell?
My Goal: Use the add_loss method inside a custom RNN cell (in graph execution mode) to add an input-dependent loss.
General Setup:
Using Python 3.9
Using TensorFlow 2.8 or 2.10
Assuming import ...
1
vote
1
answer
55
views
Predict text binary classification with RNN and didn't get expected output
I'm doing Amazon review sentiment analysis with RNN and LSTM.
df2['Texts'] are Amazon customer reviews, and df2['label'] are binary integer 0 or 1.
tokenizer = Tokenizer(num_words=5000, split=' ')
...
- 13
0
votes
0
answers
568
views
AttributeError: 'CuDNNLSTM' object has no attribute 'unroll'
I am trying to use Sherpa framework for population based training with this model
x1 = Input((window_size, 3), name='x1')
x2 = Input((window_size, 3), name='x2')
convA1 = Conv1D(hidden_num,...
- 331
0
votes
1
answer
99
views
LSTM custom Loss function caued error. ValueError: too many values to unpack (expected 4)
I tried to implement LSTM with custom function by
tf.random.set_seed(7)
model = Sequential()
model.add(LSTM(100, input_shape=(18,1 ), return_sequences=True))
model.add(Dropout(0.2))
#model.add(LSTM(...
- 331
1
vote
1
answer
447
views
How to buid keras model with multi dimensional input multi dimensional output
I want to use sensor reading to estimate some quantities. My sensor readings in each time step have 9 elements and the out quantities have 4 elements
input_size = (304414,9)
target_size = (304414,4)
...
- 331
1
vote
1
answer
133
views
Multi dimensional input multi dimensional output rnn keras data preprocessing
I want to create a RNN model in Keras. In each time-step the input has 9 element and the output has 4 element.
input_size = (304414,9)
target_size = (304414,4)
How can I create a dataset of sliding ...
- 331
1
vote
1
answer
371
views
LSTM model has poor prediction in simple example
I am trying to generate a LSTM model using Keras. I create a simple sine wave example which contain more thang 1000 point to predict the next point. But the result is not good as i expected. When i ...
- 13
0
votes
2
answers
348
views
Keras RNN, incorrect shape of input even though shape is shown as correct
I am attempting to train an RNN to classify texts. On my computer, i have a large text file with all of the phrases to train the network on for each category (2 total), e.g
Phrase 1
Phrase 2
Phrase ...
- 310
0
votes
0
answers
98
views
inject the output of the network into the input layer of the next time step
I am trying to build an LSTM network using quarterly time series, making a forecast named yt (0 or 1) for each quarter. Here is the network I am currently using:
model = tf.keras.models.Sequential()
...
0
votes
1
answer
321
views
ValueError issue when using LSTM layer in tensorflow
I am trying to build up a very simple LSTM structure using padding and masking to learn how to train time series data. Suppose I have two people's blood value information per month. For the first ...
- 658
0
votes
0
answers
156
views
How to reshape dataset as input for RNN in Tensorflow
i try to feed my model with dataset values but i get a shape error. Can somebody help with it and explain how it works with datasets? Many thanks
import pandas as pd
import tensorflow as tf
import ...
- 33
0
votes
2
answers
741
views
Need to increase the accuracy of my LSTM model
This is my model
# normalize the dataset
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(df)
train_size = int(len(dataset) * 0.8)
test_size = len(dataset) - train_size
...
user17091916
3
votes
1
answer
3k
views
Weights and Bias dimensions in TensorFlow for LSTM
I am confused about the dimensions of the hidden weight array for an LSTM. I understand the input weight and bias dimension just fine. Now I just recently started learning about RNNs and LSTMs so ...
0
votes
1
answer
188
views
ValueError of Input and Output values during LSTM training
I was trying to implement a basic LSTM network using some random data, and I got the following error during execution of the code
'''
Traceback (most recent call last):
File "C:/Users/dell/...
- 43
1
vote
1
answer
928
views
Accessing the elements of an Input Layer in a keras model
I am trying to compile and train an RNN model for regression using Keras Tensorflow. I am using the "Functional API" way for the definition of my model.
I need to have 2 different inputs. ...
- 195
0
votes
1
answer
74
views
How to define size of input in Recurrent Neural Network for unsupervised learning model?
I'm trying to fit a neural network model(unsupervised).
I have only an input x, which is a vector with 10000 components, and I have an output, which is also a vector of the same size as x.
I've ...
- 121
1
vote
1
answer
311
views
tf.get_shape() returning None incorrectly
I'm currently trying to create a WGAN implementation with gradient penalty in keras following the setup here: https://keras.io/examples/generative/wgan_gp/. However, I have modified this to generate ...
- 45
0
votes
0
answers
103
views
Is there a way to get the real sequence_length in the model description of a RNN/LSTM in Keras?
I would like to get to know the real sequence_length in Keras for a LSTM/RNN. Unfortunately, when I print the model I only get None all the time as a value. Here is a part of the code:
...
- 870
0
votes
1
answer
258
views
How do I properly make a tf Dataset for recurrent-neural-network?
I have just preprocessed my categories data to one-hot encoding and used tf.argmax(). This way, I got it into a range of numbers of 1 to 34; thus, there are sequences of, say: [7, 4, 28, 14, 5, 15, 22,...
1
vote
1
answer
979
views
AttributeError: 'NoneType' object has no attribute '_inbound_nodes' when implement an operation between a constant tensor and a keras tensor
I'm implementing a ConvRNN in keras, and the implementation follows this which is originally implemented in Pytorch.
When the class ConvRNN is going to return a keras Model(inputs, outputs), then an ...
- 21
1
vote
1
answer
3k
views
How keras oov_token=True works
By default how does keras impute out-of-vocabulary token when oov_token=True.
According to keras official documentation it tells that if given, it will be added to word_index and used to replace out-...
- 1,401
0
votes
1
answer
597
views
Cannot load tensorflow saved model back
I am following this tutorial: https://www.tensorflow.org/text/tutorials/text_generation#export_the_generator
And i use the following code to save the model and load it back, the saving part works but ...
- 147