All Questions
Tagged with autoencoder tensorflow2.0
30 questions
3
votes
0
answers
372
views
Workaround for removal of add_loss()
I'm working through a Keras/Tensorflow course that uses Keras 2 to build a variational autoencoder and I'm trying to get it working in Keras 3. I've managed to overcome a lot of issues but I'm stuck ...
- 174
0
votes
1
answer
474
views
ValueError: All layers added to a Sequential model should have unique names
I am trying to train a VAE model for music generation.
When I run the following program, it shows an error:
All layers added to a Sequential model should have unique names. Name "" is ...
- 3
0
votes
1
answer
509
views
VAE issue with tensorflow
I am trying to build a VAE using the MNIST dataset.
Error:
--------------------------------------------------------------------------- AttributeError Traceback (most recent ...
- 71
0
votes
1
answer
515
views
Trying to create u-net like structure for signal processing using Conv1D
I have tried to create a u-net-like neural network (autoencoder) structure for signal processing applications using Tensorflow2. However, I have run into some problems when training the model.
Here is ...
- 13
1
vote
1
answer
6k
views
AttributeError: 'Tensor' object has no attribute 'numpy' while extending keras sequential model
I am trying to compile a Keras Sequential model (in TF2) in the eager execution mode.
Following is my custom layer:
class CustomLayer(Layer):
def __init__(self, output_shape, **kwargs):
self....
- 1,006
1
vote
0
answers
98
views
How to reconstruct the decoder from an LSTM-AE?
I have a trained LSTM-AE, of which the architecture is as follows:
In brief, I have an LSTM-AE of depth 3, the number of cells on the LSTM layers on the encoder side are [120, 80, 50] (and symmetric ...
- 95
1
vote
1
answer
239
views
Trying to tying the weights of the encoder and decoder layer but getting this unknown error for the Reshaping layer
Trying to tying the weights of the encoder and decoder layer but getting this unknown error for the Reshaping layer. My tensorflow version is up to date, and I imported the layers from tensorflow....
- 11
0
votes
1
answer
203
views
Sentence VAE Loss Layer Implementation On Keras Giving Issues
So I've been implementing the sentence VAE on TF-Keras (latest versions). The custom function below calculates the VAE loss from sparse categorical outputs.
def vae_loss(encoder_inputs, ...
- 41
1
vote
0
answers
161
views
VAE, CNN or lstm autoencoders code samples needed for non sequential data augmentation python
This post may sound very simple but I have done a little search on this and couldn't find anything useful in Stackoverflow for data augmentation.
If someone could post a sample code for variational ...
- 3,528
0
votes
1
answer
462
views
Conv1dTranspose creates the wrong dimensions
I'm trying to build an undercomplete autoencoder for music dimensionality reduction. My Autoencoder class is modular, I can give in input a list of convlayers sizes and it creates me automatically the ...
- 411
0
votes
1
answer
650
views
Is there any way to improve the performance of the denoising autoencoder?
I am trying to train a denoising autoencoder to denoise with an image composed of two simple lines as input. However, even when using a simple image like this, it does not output a good output.What's ...
- 67
2
votes
1
answer
295
views
How to extract the hidden vector (the output of the ReLU after the third encoder layer) as the image representation
I am implementing an autoencoder using the Fashion Mnsit dataset. The code for the encoder-
class MNISTClassifier(Model):
def __init__(self):
super(MNISTClassifier, self).__init__()
...
0
votes
1
answer
675
views
Value error after fitting my custom model
I am creating an encoder on the fashion MNIST dataset. The encoder consists of three layers, Each input image is flattened into a dimensionality of 784. The three encoder layers are with output ...
- 405
0
votes
1
answer
178
views
Dimensional error in the keras fit function (Conditional variational autoencoder in keras)
I am trying to implement a conditional autoencoder, which is really very straightforward, and getting errors while making the fit function work. Here is the full code snippet
import numpy as np
import ...
- 519
2
votes
1
answer
949
views
Keras 'plot_model' shows wrong graph for nested models (Autoencoder)
When I create an autoencoder architecture with multiple inputs and outputs, the plot_model graph does not show up as expected (problems highlighted in red).
I assume the first issue occurs because I ...
- 103