7. current community

    your communities

    more stack exchange communities

    company blog

Tagged Questions

0
votes
0answers
9 views

How to include tf.py_func code in Keras?

I am currently getting an error: TypeError: object of type 'NoneType' has no len() when compiling my code, and I am not sure where the error is coming from. Basically what I am trying to do is ...
0
votes
0answers
13 views

Auto encoder predict value negative for anomaly detection

I am using auto-encoder(unsupervised) for detecting anomaly in my input data. The procedure I am following is that Create Model from input data and save it to directory. I also save the ...
0
votes
2answers
47 views

Difference between 2 LSTM Autoencoders

I would like to know the difference between these 2 Models. the one above has 4 Layers looking into the model summary and you can also define the unit numbers for dimensionality reduction. But what is ...
0
votes
0answers
16 views

Implement an autoencoder flexible and stable with over 10 million iterations?

import numpy as np import pandas as pd import tensorflow as tf n_inputs = 80 n_hidden = 32 n_outputs = n_inputs learning_rate = 0.01 tf.reset_default_graph() X = tf.placeholder(tf.float32, shape=...
1
vote
1answer
32 views

Keras custom Loss function returning none

I am trying to code up an implementation of the variational autoencoder, however I am facing some difficulties regarding the loss function: def vae_loss(sigma, mu): def loss(y_true, y_pred): ...
-2
votes
0answers
47 views

tuple index out of range (Python + Chainer)

I am new and a very beginner of coding. Currently, I am planing to program an autoencoder for the features reduction by myself. Although I spent most of my time solving the error I got by taking a ...
-1
votes
1answer
26 views

ShuffleSplit of Sklearn issue

I have a data set named df_noyau_yes and I want to apply a ShuffleSplit to split it into train and test sets to train an autoencoder. The problem is that this functions returns indices of the ...
-1
votes
0answers
31 views

Autoencoder that does NOT use MNIST

I'm working on a project for my undergrad Intro to AI class and have tasked with finding an autoencoder (I don't need to write my own, just modify somebody else's) that will take in our input. So far ...
0
votes
0answers
25 views

What proportions of data to feed an auto-encoder for abnormality detection on time series vibration data

As a noob on auto-encoders and deep learning, i struggle with the following. I am trying to use an auto-encoder to perform anormality detection, on a vibration dataset, starting out with a reference ...
1
vote
1answer
26 views

Reusing a group of Keras layers

I know that you can reuse Keras layers. For eg I declare two layers for a decoder network: decoder_layer_1 = Dense(intermediate_dim,activation='relu',name='decoder_layer_1') decoder_layer_2 = Dense(...
3
votes
1answer
83 views

Dimensions of locally connected layers in Keras

I'm attempting to build an autoencoder using LocallyConnected1D layers (instead of Dense) but am having a lot of trouble understanding how the two layer types differ—especially when it comes to output ...
0
votes
0answers
20 views

Fit a trained autoencoder with another training data set in keras

I have trained a denoising auotencoder with a training set df_noised_noy_norm_y in keras. I have another data set df_active and I made this autoencoder predict it's encoded representation. Now, I want ...
1
vote
1answer
20 views

locallyconnected1D autoencoder in keras

I'm trying to create a LocallyConnected1D autoencoder in Keras by repurposing a 'simplest possible' Dense autoencoder from this tutorial. I keep getting the error bellow, which I believe is being ...
0
votes
0answers
48 views

Multiple time series prediction with LSTM Autoencoder in Keras

I'm trying to build an LSTM autoencoder as shown here. My code: from keras.layers import Input, LSTM, RepeatVector from keras.models import Model inputs = Input(shape=(window_length, input_dim)) ...
0
votes
0answers
21 views

Stacked denoising autoencoder predicted representation size

I'm dealing with a stacked denoising autoencoder with keras. I want to know when I use it after being trained in new data set using predict, it will generate the encoded representation of the data ...
0
votes
0answers
23 views

Prediction Error with stacked denoising autoencoder in keras

I trained a stacked denoising autoencoder with keras. Every thing was fine until it comes to predict new samples. The samples for prediction are named 'active' part, I did the necessary pre-processing ...
1
vote
1answer
33 views

Lock a variable value after a random use

I'm dealing with a stacked denoising autoencoder in keras. So for after generating the noised input using random tool, I noticed that even if I use a checkpointer to save the weights of the model, I ...
-1
votes
0answers
46 views

Trained pytorch auto-encoder model outputs junk on training subset inference

I'm trying to build a simple Auto-encoder with pytorch with the encoder being a standard convnet that outputs a latent code. The decoder is a reverse of the encoder that takes in the latent code and ...
1
vote
0answers
30 views

How to fault detection with the depth sparse denoising auto encoder with dataset csv

Currently I am trying to build a depth sparse denoising autoencoder for fault detection in dataset csv I use https://blog.keras.io/building-autoencoders-in-keras.html to apply it in numerical dataset....
0
votes
0answers
21 views

input shape and layer dimensions convolutional autoencoder

I want to train a convolutional Autoencoder with time series data to learn features and make later a prediction. I have the whole data in one dataframe and have 100 mio rows of data (1 column). From ...
0
votes
1answer
67 views

How to resolve runtime error due to size mismatch in PyTorch?

I am trying to implement a simple autoencoder using PyTorch. My dataset consists of 256 x 256 x 3 images. I have built a torch.utils.data.dataloader.DataLoader object which has the image stored as ...
1
vote
2answers
76 views

How to initialise weights of a MLP using an autoencoder #2nd part - Deep autoencoder #3rd part - Stacked autoencoder

I have built an autoencoder (1 encoder 8:5, 1 decoder 5:8) which takes the Pima-Indian-Diabetes dataset (https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv) and ...
0
votes
0answers
23 views

Loading weights through checkpoint keras provides different results

I'm new with keras. In fact, I conceive an autoencoder and train it on a part of Diabetes Dataset. Then, I use keras checkpointer to save the weights so that I can load it later in order to acheive ...
1
vote
0answers
24 views

Tied weights in tensorflow recurrent cell

In the context of an fully-connected autoencoder this paper states that one type of regularization is to use tied weights for weight matrixes (section 2in the paper). In the paper the weight matrix ...
0
votes
1answer
56 views

Deep autoencoder keeping constant accuracy in keras

I'm new in keras and deep learning field. In fact, I built a deep autoencoder using keras library based on ionosphere data set, which contains a mixed data frame (float, strings"objects", integers..) ...
0
votes
0answers
39 views

Developing Adversarial Autoencoder in tensorflow using Estimator API

I'm trying to code an adversarial autoencoder in tensorflow using the Estimator API and I'm having trouble with incorporating the discriminator (i.e. into my already function autoencoder). The issue ...
0
votes
1answer
90 views

Keras fit_generator using input and output image generators 'ndim' error

I decided to try my hand at training an auto-encoder for re-coloring grey scale images. This approach might be a tad naive, but I want to play with it and see how good (or bad) it works and examine ...
0
votes
1answer
252 views

Calculate signal to noise ratio of wav audio file in python

I'm working on speech enhancement using denoising autoencoders. My model is giving enhanced speech results in wav format for noisy input wav audio files. I want to check if the generated wav file is ...
0
votes
1answer
17 views

Tensorflow Saver.save can't write to docker shared volume

I am having a docker container with an Autoencoder that can be started via a Flask-Server. All the scripts are copied into the /root of the Docker and it also gains access to the shared volume /data ...
7
votes
1answer
209 views

Intermediate layer makes tensorflow optimizer to stop working

This graph trains a simple signal identity encoder, and in fact shows that the weights are being evolved by the optimizer: import tensorflow as tf import numpy as np initia = tf....
1
vote
0answers
422 views

LSTM Autoencoder on timeseries

I'm currently trying to implement an LSTM autoencoder to be used in order allow compression of transactions timeseries (Berka dataset) into a smaller encoded vector. The data I'm working with looks ...
0
votes
0answers
118 views

LSTMStateTuple object has no attribute get_shape when adding bidirectional encoder

Problem Summary I am having an issue adding a bi-directional encoder to my NMT model. This adds a second LSTM cell that runs backwards through the source data to improve translation quality. My ...
0
votes
1answer
141 views

Adapting the Keras variational autoencoder for denoising images

I'm trying to adapt the Keras example for VAE https://blog.keras.io/building-autoencoders-in-keras.html I have modified the code to use noisy mnist images as the input of the autoencoder and the ...
3
votes
1answer
240 views

AttributeError: 'Tensor' object has no attribute 'reshape'

I want to write a denoising autoencoder and for the sake visualization purposes I would like to print out the corrupted images as well. This is the testing part where I want to show the corrupted ...
4
votes
2answers
295 views

ValueError: Error when checking target: expected model_2 to have shape (None, 252, 252, 1) but got array with shape (300, 128, 128, 3)

hi I am building a image classifier for one-class classification in which i've used autoencoder while running this model I am getting this error by this line (autoencoder_model.fit) (ValueError: Error ...
0
votes
0answers
106 views

blind source separation using autoencoder in keras - how to filter predictions?

so i'm trying to use autoencoders in Keras to perform blind source separation similar to how its done in PCA or ICA. I'm hoping that due to their non-linear nature, autoencoders will be able to ...
0
votes
1answer
56 views

Training Keras autoencoder without bottleneck does not return original data

I'm trying to make an autoencoder using Keras with a tensorflow backend. In particular, I have data of a vector of n_components (i.e. 200) sampled n_times (i.e. 20000). It is key that when I train ...
0
votes
1answer
177 views

Saving the best val_loss with Keras callbacks

I put up an denoising autoencoder for the mnist dataset, based on what is discussed in here: https://blog.keras.io/building-autoencoders-in-keras.html I'm trying to see how the reconstruction of the ...
0
votes
1answer
162 views

Tensorflow gradients causing contractive autoencoder cost doesn't converge

To construct a contractive autoencoder, one uses an ordinary autoencoder with the cost function To implement this with the MNIST dataset, I defined the cost function using using tensorflow as def ...
2
votes
1answer
156 views

How to (efficiently) apply a channel-wise fully connected layer in TensorFlow

I'm coming to you again scratching my head at something that's being really slow and I hope to optimize. So I'm trying to implement a convolutional auto-encoder in TensorFlow with a big latent space ...
0
votes
0answers
20 views

how to add noise to tensor in NN for recognition faces

I'm just starting to learn NN and autoencoders. In my example I want to create function, where I can add noise from normal distribution with standard deviation sigma to my X. X - image tensor of shape ...
-1
votes
1answer
42 views

Why my autoencoder doesn't give the reduced representation?

I'm trying to create a reduced representation of my data, that I will use in another model, and I proceed in the following way : input = Input(shape=(70,)) encoded = Dense(output_dim=10, ...
0
votes
1answer
98 views

From 2D to 3D using convolutional autoencoder

I’d like to reconstruct 3D object from 2D images. For that, I try to use convolutional auto encoder. However, in which layer should I lift the dimensionality? I wrote a code below, however, it shows ...
0
votes
1answer
116 views

How to extract lower dimensional feature vectors from a denoising stacked autoencoder using python and tensorflow

The code below imports the MNIST data set and trains a stacked denoising autoencoder to corrupt, encode, then decode the data. Basically I want to use this as a non-linear dimensional reduction ...
0
votes
1answer
107 views

Autoencoder using Backpropagation

I'm trying to implement autoencoder using this resource which implements backpropagation algorithm. I'm using the same feed forward algorithm implemented there but however it gives me a large error. ...
0
votes
1answer
218 views

tensorflow cost is nan when training a autoencoder

I am training a autoencoder with tensorflow ,but the cost is nan ,i modify the learning rate and the optimizer, but it not works.i search some result shows that decreasing the lr may help it ,but I ...
1
vote
1answer
100 views

Add a custom loss to the autoencoder reconstruction loss

This is my first post here, so I hope it complies to the guidelines and is interesting also for other people except myself. I am building a CNN autoencoder that takes as input matrixes of fixed ...
1
vote
1answer
81 views

Issues Training CNN with Prime number input dimensions

I am currently developing a CNN model with Keras (an autoencoder). This type my inputs are of shape (47,47,3), that is a 47x47 image with 3 (RGB) layers. I have worked with some CNN's in the past, ...
1
vote
0answers
81 views

Issue with simple CAE

It looks like simple CAE not working for Carvana dataset I’m trying simple CAE for Carvana dataset. You can download it here My code is following: import numpy as np import pandas as pd import ...
2
votes
1answer
77 views

Saving and loading an autoencoder

I am trying to make a predictor using Auto Encoder (AE) and Alternating Least Squares (ALS) methods. ALS is created using pyspark.mllib.recommendation package. I am able to save the ALS model and ...

1 2 3