AutoEncoder | Stacked Denoising and Variational Autoencoder | Machine Learning library

Sometimes we need to preprocess the data by feeding them through preprocessing layers. This becomes problematic when your model is an autoencoder, in which case the input is both the x and the y.

Correct me if I'm wrong, and perhaps there's other ways around this, but it seems obvious to me that if the true input is, say, [1,2,3], and I scale this to 0 and 1: [0,0.5,1], then the model should be evaluating the autoencoder based on x=[0,0.5,1] and y=[0,0.5,1] rather than x=[1,2,3]. So if my model is, for example:

I am attempting to do an anomaly detection NN with the MNIST fashion dataset as my input.

Currently, my model is as such

I am developing an LSTM autoencoder model for anomaly detection. I have my keras model setup as below:

I have seen multiple uses of both tf.keras.layers.Flatten() (ex. here) and tf.keras.layers.Input() (ex. here). After reading the documentation, it is not clear to me

1. whether either of them uses the other
2. whether both can be used interchangeably when introducing to a model an input layer (let's say with dimensions (64, 64))

I got this error when I try to fit the model. I tried to use a single GPU version but it remains. If I upgrade to TensorFlow 2 it will be solved but I need to keep it that in this version of TensorFlow.

This is the code for the model that I have used. This model consists of different layers.

My use case is the following: I am creating a dimensionality reducing AutoEncoder with Tensorflow. I have implemented three custom layers and with that a model

I am trying to do Anomaly detection with LSTM. I am able to plot all features with local and global anomaly but I am not able to print all anomaly values, datetime, loss, threshold and date together (like a table).

After calculating test and train MAE in the following way:

There is a similar question here which asks how to use image_dataset_from_directory() with autoencoder. Question is actually unanswered, because answer suggests using something else.

My question is, is it even possible to use image_dataset_from_directory() as input for convolutional autoencoder in Keras?

The variational autoencoder loss function is this: Loss = Loss_reconstruction + Beta * Loss_kld. I am trying to efficiently implement Kullback-Liebler Divergence Cyclic Annealing--that is changing the weight of beta dynamically during training. I subclass the tf.keras.callbacks.Callback class as a start, but I don't know how I can update a tf.keras.Model variable from a custom keras callback. Furthermore, I would like to track how the betas change at the end of each training step (on_train_batch_end), and right now I have a list in the callback class, but I know python lists don't play well with TensorFlow. When I fit the model, I get a warning that my on_train_batch_end function is slower than the processing of the batch itself. I think I should use a tf.TensorArray instead of python lists, but then the tf.TensorArray method write cannot use a tf.Variable for the index (i.e., as the number of steps changes, the index in the tf.TensorArray to which a new beta for that step should be written changes)... is there a better way to store value changes? It looks like this github shows a solution that doesn't involve a custom tf.keras.Model and that uses a different kind of KL annealing. Below is a callback function and dummy VAE.