All Questions
1,956 questions
0
votes
1
answer
84
views
Using a symbolic `tf.Tensor` as a Python `bool` is not allowed
when I add a masking layer in my model, it gives this error. works fine without the masking tho. If anyone can solve this, id be grateful ! been scratching my head for 3 days now.
TensorFlow 2.17
def ...
- 50
1
vote
1
answer
82
views
autoencoder.fit() raises 'KeyError: 'Exception encountered when calling Functional.call()'
I'm trying to build a stacked LSTM sequence auto-encoder that takes a signal of 430 timesteps with each timestep having 1 value. You can see the code for the model below:
feat_dim = 1
timesteps = 430
...
- 97
0
votes
0
answers
20
views
LSTM training fades to Nan when batch_number>=2
I am running a very simple multilayer LSTM network. I have set different transformations for the data, namely StandardScaler(), RobustScaler() and MinMaxScaler(). The code runs smooth and I get no ...
- 21
0
votes
0
answers
40
views
How make dimension compatible between an TCN ins Space and a LSTM in Time?
I would like to create a model with a TCN followed by an LSTM. I have some difficulties to understand how to use the dimension of each layer I have.
my data can be viewed in 3D with (Time, space, ...
- 4,967
0
votes
0
answers
64
views
How can I train an LSTM Autoencoder for each iteration of training with each dataset?
I’ve been trying to build and train an LSTM Autoencoder. While the reference that I was using trained the model only once, I added a function to run the training multiple times if each iteration of ...
- 135
0
votes
1
answer
58
views
hyperband tuning on keras LSTM: issue with objective
I have a keras LSTM model (regressor):
def model_builder(hp):
model = Sequential()
hp_units = hp.Int('units', min_value=32, max_value=512, step=32)
model.add(LSTM(units=hp_units, input_shape=(...
- 179
0
votes
0
answers
31
views
Keras Masking Layer for Both Input and Output Layer
I have a tensor with this shape:
(num of samples, num of timesteps, num of features) -> 1000, 60, 4
The first 59 nodes are input for the model, while the last nodes are output for the model at '...
- 1,152
0
votes
0
answers
69
views
Keras LSTM model and predicting beyond validation set
I am currently encountering issues with formulating a prediction beyond my validation set. When utilizing a validation set, my model works fine and I am able to achieve a credible prediction.
However, ...
0
votes
0
answers
81
views
How ConvLSTM1D in keras constructed from separated Conv1D and LSTM layer?
I read this doc: https://keras.io/api/layers/recurrent_layers/conv_lstm1d/
But, can we construct the equivalent layer of ConvLSTM1D with using Conv1D and LSTM layer? Or, they are entirely separated ...
- 1,152
0
votes
0
answers
45
views
Why do my LSTM multi-step forecasts explode, despite low MAPE on validation set (single-step) on very simple linear trend?
Example below is self-complete.
I have recently switched from using darts (where forecast horizons etc) are all handled for me to keras because I wanted to integrate with other libraries such as shap ...
- 29
1
vote
1
answer
2k
views
ValueError: Unrecognized keyword arguments passed to LSTM: {'batch_input_shape'} in Keras
I'm trying to build and train a stateful LSTM model using Keras in TensorFlow, but I keep encountering a ValueError when specifying the batch_input_shape parameter.
The error message:
ValueError: ...
- 331
0
votes
1
answer
80
views
LSTM Model doesn't train
I am trying to find the chemical state of a particle with deep learning. As inputs I have the position of the particle according to time in X_train with shape (num_train,sequence_length). (My sequence ...
- 1
0
votes
0
answers
42
views
LSTM Prediction Issue: Not Predicting Last Record and Backward Prediction Behavior
I'm conducting some tests with LSTM for learning purposes, but I've encountered a peculiar situation while testing its predictions.
I've observed in the graph images that it doesn't predict the last ...
- 615
1
vote
0
answers
74
views
Can't import KerassRegressor
I have been trying to import KerasRegressor hyper-parameterization of the LSTM time series model to improve its performance in both HPC Linux** and **Windows. For this, I installed tensorflow using ...
1
vote
0
answers
55
views
SMOTE Oversampling in Text Classification Fails with Multiple Input Features
I have a text classification problem where the input has 2 features: a text and a language:
the text is a string variable. the language is a string variable that has the following values: "EN&...
- 143