LSTM | Long Short-Term Memory implementation from scratch | Interpreter library

I'm trying to use GridSearchCV to find the best hyperparameters for an LSTM model, including the best parameters for vocab size and the word embeddings dimension. First, I prepared my testing and training data.

I am approaching a problem that Keras must offer an excellent solution for, but I am having problems developing an approach (because I am such a neophyte concerning anything for deep learning). I have sales data. It contains 11106 distinct customers, each with its time series of purchases, of varying length (anyway from 1 to 15 periods).

I want to develop a single model to predict each customer's purchase amount for the next period. I like the idea of an LSTM, but clearly, I cannot make one for each customer; even if I tried, there would not be enough data for an LSTM in any case---the longest individual time series only has 15 periods.

I have used types of Markov chains, clustering, and regression in the past to model this kind of data. I am asking the question here, though, about what type of model in Keras is suited to this type of prediction. A complication is that all customers can be clustered by their overall patterns. Some belong together based on similarity; others do not; e.g., some customers spend with patterns like $100-$100-$100, others like $100-$100-$1000-$10000, and so on.

Can anyone point me to a type of sequential model supported by Keras that might handle this well? Thank you.

I am trying to achieve this in R. Haven't been able to build a model that gives me more than about .3 accuracy.

I have an input that is a time series of 5 dimensions:

a = [[8,3],[2] , [4,5],[1], [9,1],[2]...] #total 100 timestamps. For each element, dims 0,1 are numerical data and dim 2 is a numerical encoding of a category. This is per sample, 3200 samples

The category has 3 possible values (0,1,2)

I want to build a NN such that the last dimension (the category) will go through an embedding layer with output size 8, and then will be concatenated back to the first two dims (the numerical data).

So, this will be something like:

I'm trying to build the model illustrated in this picture:

I obtained a pre-trained BERT and respective tokenizer from HuggingFace's transformers in the following way:

I am trying to train a BiLSTM-CRF on detecting new NER entities with Pytorch. To do so, I am using a snippet of code derivated from the Pytorch Advanced tutorial. This snippet implements batch training.

I followed the READ-ME in order to present data as required. Everything works great on CPU, but when I'm trying to get it to GPU, the following error occur :

I want to do time series multi-class classification with time-series data. Here the data set I have got needs to be preprocessed heavily and that just to get an idea of how to implement the model I have used the IRIS data set(not suitable for LSTM) since it has the exact same structure of the time series data I have( 4 input features,1 output feature, 120 samples). I have the following code implemented but it causes me the invalid shape error when fitting the model with a batch size of 5 (changed the batch size many times but didn't seem to make any change)

tensorflow version 2.3.1 numpy version 1.20

below the code

I'm trying to train a model using LSTM layers. I'm using a GPU and all needed libraries are loaded.

When I'm building the model this way:

I am a beginner with LSTMs so sorry if this is a basic question. I've been trying to make a simple LSTM model that loads data from a csv text file for training