All Questions
66
questions
10
votes
1
answer
5k
views
CUDNN_STATUS_BAD_PARAM when trying to perform inference on a LSTM Seq2Seq with masked inputs
I'm using keras layers on tensorflow 2.0 to build a simple LSTM-based Seq2Seq model for text generation.
versions I'm using: Python 3.6.9, Tensorflow 2.0.0, CUDA 10.0, CUDNN 7.6.1, Nvidia driver ...
- 11.8k
7
votes
0
answers
1k
views
Entity Embedding of Categorical within Time Series Data and LSTM
I'm trying to solve a time series problem. In short, for each customer and material (SKU code), I have different orders placed in the past. I need to build a model that predict the number of days ...
4
votes
1
answer
3k
views
add LSTM/GRU to BERT embeddings in keras tensorflow
I am experimenting with BERT embeddings following this code https://github.com/strongio/keras-bert/blob/master/keras-bert.py
These are the important bits of the code (lines 265-267):
bert_output = ...
- 101
4
votes
2
answers
1k
views
What does Keras do with the initial values of cell & hidden states (RNN, LSTM) for inference?
Assuming training is finished: what values does Keras use for the 0th cell state and hidden states at inference (in LSTM and RNN layers)? I could think of at least three scenarios, and could not find ...
- 487
3
votes
2
answers
379
views
Does model.reset_states for LSTM affect any other non-LSTM layers in the model?
I am using the Stateful mode of LSTMs in tf.keras where I need to manually do reset_states when I have processed my sequence data, as described here. It seems that normally people do model....
- 4,414
3
votes
1
answer
241
views
InvalidArgumentError on Decoder Model during Inference, for LSTM-based Seq2Seq on Tensorflow 2.0
versions: Python 3.6.9, Tensorflow 2.0.0, CUDA 10.0, CUDNN 7.6.1, Nvidia driver version 410.78.
I'm trying to port a LSTM-based Seq2Seq tf.keras model to tensorflow 2.0
Right now I'm facing the ...
- 11.8k
3
votes
0
answers
894
views
LSTM for imbalanced time series classification
I wanted to fit simple LSTM model to perform binary classification on multivariate time series data. Since my data is severely imbalanced, I have integrated class_weight argument from sklearn in my ...
- 50
3
votes
2
answers
2k
views
LSTM - Use deltaTime as a feature? How to handle irregular timestamps?
I'm trying to create a LSTM for classification of data sequences.
The data structure of every training input that I would use is:
[[
[deltaX,deltaY,deltaTime],
[deltaX,deltaY,deltaTime],...
],class]
...
- 430
2
votes
2
answers
5k
views
error Node: 'binary_crossentropy/Cast' Cast string to float is not supported while train model
i want to train my data i already make my data to string with word2vec pretrain model from here https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.id.300.vec.gz and success to make a model, but ...
- 35
2
votes
1
answer
862
views
What is the connections between two stacked LSTM layers?
The question is like this one What's the input of each LSTM layer in a stacked LSTM network?, but more into implementing details.
For simplicity how about 4 units and 2 units structures like the ...
- 468
2
votes
1
answer
722
views
Pad vectors in tf.keras for LSTM
Keras has a preprocessing util to pad sequences, but it assumes that the sequences are integer numbers.
My sequences are vectors (my own embeddings, I do not want to use Keras embeddings), is there ...
- 1,478
2
votes
0
answers
319
views
How to freeze tensorflow variables inside tf.keras framework on eager execution mode?
I'm trying to fine tune the input weights in a recurrent cell without letting the backpropagation affect previous states (kind of truncated backpropagation with n = 1). I'm using tf.keras and eager ...
- 21
1
vote
2
answers
1k
views
Confused about how to combine CONV1D and LSTM
I am struggling to understand this code which combines both CONV1D and LSTM.
model = tf.keras.models.Sequential([
tf.keras.layers.Conv1D(filters=32, kernel_size=5,
strides=1, ...
- 425
1
vote
1
answer
636
views
Dense vs. TimeDistributed(Dense)
Is there any difference between this two methods of using Dense layer? Seems output shape is the same and number of parameters is the same.
Will be the output the same if we use fixed weights?
Will ...
- 20.8k
1
vote
1
answer
82
views
N timeseries feed to one layer with N lstm cells, how to concatenate lstm horizontally as a layer?
I am trying to impliment https://dl.acm.org/doi/pdf/10.1145/3269206.3271794 .
It has a network structure like
timeseries1 -> lstm1
timeseries2 -> lstm2
....
timeseriesN -> lstmN
[lstm1, ...
anon
1
vote
1
answer
241
views
Meaning of 2D input in Keras LSTM
In Keras, LSTM is in the shape of [batch, timesteps, feature]. What if I indicate the input as keras.Input(shape=(20, 1)) and feed a matrix of (100, 20, 1) as input? What's the number of batch that it'...
- 53
1
vote
1
answer
121
views
Logits and labels must be broadcastable: logits_size=[29040,3] labels_size=[290400,3]
I am using this code:
import tensorflow as tf
import numpy as np
from tensorflow.keras.layers import Dense, LSTM, Input, Conv2D, Lambda
from tensorflow.keras import Model
def reshape_n(x):
x = tf....
- 5,511
1
vote
1
answer
736
views
Validation accuracy zero and Loss is higher. Intent classification Using LSTM
I'm trying to Build and LSTM model for intent classification using Tensorflow, Keras. But whenever I'm training the model with 30 or 40 epochs, my 1st 20 validation accuracy is zero and loss is more ...
1
vote
1
answer
3k
views
How to apply Layer Normalisation in LSTMCell
I want to apply Layer Normalisation to recurrent neural network while using tf.compat.v1.nn.rnn_cell.LSTMCell.
There is a LayerNormalization class but how should I apply this in LSTMCell.
I am using ...
1
vote
1
answer
314
views
simple LSTM implementation in tensorflow: Consider casting elements to a supported type error
I'm trying to implement a simple LSTM cell on Tensorflow to compare its performance with another one I implemented previously.
x = tf.placeholder(tf.float32,[BATCH_SIZE,SEQ_LENGTH,FEATURE_SIZE])
y = ...
- 11
1
vote
1
answer
190
views
Keras ValueError: Dimensions must be equal LSTM
I'm creating a Bidirectional LSTM but I faced following error
ValueError: Dimensions must be equal, but are 5 and 250 for '{{node Equal}} = Equal[T=DT_INT64, incompatible_shape_error=true](ArgMax, ...
- 21
1
vote
0
answers
429
views
Error while replicating Keras-LSTM example for SHAP-based interpretability
I am trying to replicate Keras-LSTM DeepExplainer example. I am getting the following error when trying to compute the shap values:
This warning: keras is no longer supported, please use tf.keras ...
- 11
1
vote
0
answers
60
views
Tensorflow: Shapes (None, 1) and (None, 1, 10) are incompatible
I'm building an RNN and am having trouble passing in the data. The csv file I'm pulling data from has a sentence column, and a label column that's filled with a binary classification value (1 or 0). ...
- 425
1
vote
1
answer
187
views
ValueError when loading a text classification model in Tensorflow
I am getting an error when I try to load the model with tf.keras.models.load_model() and I am getting the following error
ValueError: The mask that was passed in was tf.RaggedTensor(values=Tensor(&...
- 306
1
vote
0
answers
436
views
Dimensional error in the non-linguistic dataset as input to LSTM based Encoder-decoder model using attention
I'm trying to implement attention -LSTM based encoder decoder model for multi-class classification. The dataset is non-linguistic in nature.
Characteristics of my dataset:
x_train.shape = (930,5)
...
1
vote
1
answer
608
views
Can I split my long sequences into 3 smaller ones and use a stateful LSTM for 3 samples?
I am doing a time-series sequence classification problem.
I have 80 time-series all length 1002. Each seq corresponds to 1 of 4 categories (copper, cadmium, lead, mercury). I want to use Keras LSTMs ...
- 1,087
1
vote
0
answers
167
views
Output layer of LSTM (many to many)
I want to use LSTM to predict Y (size = [batch_size, time_length=1, feature_dim=3]) from X (size = [batch_size, time_length=42, feature_dim=12]). The problem is using data (12 features) during past 42 ...
- 197
1
vote
0
answers
393
views
Tensorflow custom loss function - can't get samples of y_pred and y_true in loss function
I'm running an LSTM network that works fine (TF 2.0). My problem starts when trying to modify the loss function.
I planed to adjust some data manipulation over 'y_true' and 'y_pred' but since TF force ...
- 11
1
vote
0
answers
401
views
Custom training loops for LSTMs (Tensorflow 2)
I am currently implementing the neural image captioning model shown here:
https://www.tensorflow.org/tutorials/text/image_captioning
The training loop passes a batch of sentences word by word into ...
- 23
1
vote
0
answers
266
views
How can I create keras functional api of multiple inputs and outputs?
The network consist of encoder, lstm and decoder.
The encoder take an input image sequence (TimeDistribution) and extract 2 outputs with different shape.
one use for lstm and pass it to decoder and ...
- 121
1
vote
2
answers
849
views
Tensorflow 2 custom LSTM Cell initial states
I try to implement a custom LSTM cell. Firstly, I try to reproduce the original LSTM cell before I put customization. However, I run into a problem that the initial state is a single tensor instead of ...
- 11
0
votes
1
answer
1k
views
How to combine independent CNN and LSTM networks
I'm currently working with timeseries forecasts using tensorflow and keras. I built an CNN which performs quite good and a basic LSTM with shows also quite good results. Now I was thinking to combine ...
- 413
0
votes
1
answer
954
views
Cannot have names for input and output in keras model.fit
In short:
Why does this line work -
model.fit(x_train, y_train, epochs=30, batch_size=40, verbose=2)
And this line doesn't
model.fit({"word_input": x_train, "main_output": y_train}...
- 6,032
0
votes
1
answer
103
views
How to add mask for padded sentences in LSTM layer in a binary classification problem?
I am trying to design a LSTM-CNN model using glove embeddings and some dialogue act information as text features, I have used padding at two levels: within a sentence to make all sentences of equal ...
- 49
0
votes
1
answer
236
views
next character prediction with GRU gives different results each time
I am trying to predicts a evolution of sentiments in a dialouge. To that end, I have used BERT to get the sentiments. Then for each call, I have encoded sentiments as P for Positive, E for Negative ...
- 185
0
votes
1
answer
770
views
Multiclass classification LSTM keras
I'm stuck in writing keras code for multiclass classification problem. I will expose my problem.
I have a dataset in a single csv file which has rows in the following form
1.45 -10.09 1.02 1 ...
0
votes
1
answer
525
views
Keras continuous training with DB
I am new to Keras and still looking for ways for continuous training the model. Since my dataset is very large to store in memory, I am supposed to store in a DB (NoSql DB- MongoDb or HBase) and train ...
- 5,856
0
votes
1
answer
221
views
How to understand and debug the error inside keras.model.fit?
I am trying to implement a keras LSTM. I am getting an error inside keras.model.fit. I am not understanding what this error means. My code is given below -
print(x_train.shape)
print(y_train.shape)
...
- 6,032
0
votes
0
answers
33
views
Is it possible to assign to a tf.SymbolicTensor during graph execution?
I have a tf.function I'm trying to execute as the training step to a keras.layers.LSTM. During the execution of this function, I happen to need to assign an intermediate value (computed within the tf....
- 1
0
votes
0
answers
21
views
Error with CNN-LSTM on Keras: ValueError: Input 0 of layer sequential is incompatible with the layer: expected ndim=4, found ndim=3
I was trying to create a CNN-LSTM model and I received an error message:
` ValueError: Input 0 of layer sequential is incompatible with the layer: expected ndim=4, found ndim=3. Full shape received: (...
- 1
0
votes
0
answers
48
views
Tensorflow/Keras LSTM RNN model for consumption forecast not learning/underfitting
Hi everyone I need help!
I have build a LSTM RNN model with Tensorflow and Keras to predict the electricity consumption of a building. I have half hourly data since august 2021 (just above 4 million ...
- 1
0
votes
0
answers
13
views
RNN where features are sequences with different lengths
I have a sequential RNN using Keras. Some of my features are sequences with different lengths (eg time series where data is collected daily or monthly) and some other features are scalars. Would this ...
- 71
0
votes
0
answers
38
views
'TfidfVectorizer' object has no attribute 'vocabulary_'
print(tfidf.vocabulary_)
saya memiliki code berikut yang salah
import numpy as np
import pandas as pd
import tensorflow as tf
import string
from sklearn.model_selection import train_test_split
from ...
0
votes
0
answers
30
views
Create a custom LSTM Layer which feedbacks output as input in next time step
I proceeded with idea of using raw_rnn function for writing a custom LSTM Layer, such that output of previous time step is passed as input of next time step. I find it difficult to extend the model ...
- 1
0
votes
0
answers
107
views
Error while importing tensorflow: No module named tensorflow.tsl
I've working on RNN_LSTM and the codes were working well just a month ago, but now gives errors, I tried to fix but no result....
Found out the error is on TensorFlow
I installed successfully but can'...
0
votes
1
answer
99
views
Tensorflow ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type numpy.ndarray)
I am trying to train an LSTM model using sequences of numbers for a binary classification task.
I don't want to pad the sequences and for this reason I set batch_size = 1. My data looks like this
...
- 181
0
votes
0
answers
68
views
how to make a stacked keras LSTM
My Tensorflow non-stacked LSTM model code works well for this:
# reshape input to be [samples, time steps, features]
trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
testX = np....
- 3,360
0
votes
0
answers
27
views
How to train a LSTM with a sequence of numbers with different lenghts?
I am trying to train a LSTM with a dataset in which both the input and the output are a sequence of numbers of different lenght. Each number in the input represents a timestep. Example of input and ...
- 1
0
votes
0
answers
95
views
How can I get non-negative outputs in time series forecasting using LSTM
I am doing a prediction for time series data using lstm keras. The train does not contain any negative numbers.
The issue is, when the predicting test data, the outputted prediction sometimes is ...
0
votes
1
answer
137
views
LSTM training difficulties
I wanted to train LSTM model for tabular time series data. My data shape is
((7342689, 50, 5), (7342689,))
I was having a hard time to handle the training loss. Initially I tried with default ...
- 50