All Questions
85 questions
0
votes
0
answers
37
views
Very slow Evaluation of a Pytorch LSTM model
I'm experiencing some issues with an LSTM model designed to perform "Audio Event Recognition" from a dataset of crime-related audio samples.
The overall network seems to be working fine ...
0
votes
0
answers
116
views
LSTM model prediction does not change with different inputs
I am implementing in PyTorch an LSTM model to predict if the closing value of a stock will go up or down in the next 5 and 10 minutes.
Specifically, I am using 24 years of 5 minute data with 19 ...
- 31
2
votes
0
answers
29
views
LSTM stuck on image generation
I created an LSTM for generating next image in a sequence (I know CNN is for image generation but I need the entire image not just the filters to give to the next iteration of the sequence). So I have ...
0
votes
0
answers
30
views
NaN loss when training LSTM-Attention
During model training, the loss value suddenly became Nan. Even though I change the parameters a lot, it still failed.
I checked the error when training and it prints the error in the output, not the ...
0
votes
1
answer
66
views
CrossEntropyLoss on PyTorch LSTM model with one classification per timestep
I am trying to make an LSTM model that will detect anomalies in timeseries data. It takes 5 inputs and produces 1 boolean output (True/False if anomaly is detected). The anomaly pattern will usually ...
- 1
0
votes
0
answers
39
views
Predicting next elements with an LSTM, based on previous ones, or even based on no previouse ones
I have a time series problem, which consists of predicting prices with an LSTM. The dataset is imported from the Python library yfinance. I used the example code in a geeks for geeks tutorial built in ...
0
votes
0
answers
66
views
Preparing data for LTSM with multiple features and uncorrelated target ends up in predicting mean value
I am trying to predict micro-weather events, such as the expected temperature in the next hour, by using an LTSM for a regression. It's an exercise in LTSM.
The data:
I have a CSV with 10000 samples (...
- 227
1
vote
0
answers
233
views
LSTM : predict_step in PyTorch Lightning
I've developed code for an LSTM model, but I'm uncertain about how to utilize it for predictions in a production environment. Could you please assist? In the provided predict.py script, I aim to ...
- 25
0
votes
1
answer
541
views
UserWarning: RNN module weights are not part of single contiguous chunk of memory
Was working on a Siamese LSTM model for classification, undertook this project to understand the implementation and working of it. The model runs well on CPU but when I try to shift it to GPU, this ...
0
votes
1
answer
176
views
Seq2Seq LSTM not learning properly
I am trying to solve a seq-to-seq problem with a LSTM in Pytorch. Concretely, I am taking sequences of 5 elements, to predict the next 5 ones. My concern has to do with the data transformations. I ...
0
votes
1
answer
92
views
PyTorch LSTM not using hidden layer
I am using PyTorch's LSTM api, but have a bit of an issue. I'm using an LSTM for a dummy AI model. The task of the model is to return 1 if the previous number is less than the current one.
So for an ...
- 191
0
votes
1
answer
81
views
Video classification using CNN + LSTM combination loss isn't reducing, metrics aren't improving
I'm trying to build a binary classification network for videos.
Dataset class loads 16/32 frames per video along with its label.
The model is a combination of pretrained Resnet101 followed by LSTM and ...
0
votes
1
answer
55
views
LSTM keeps plotting the pure straight line with the result equals to 0
I have tried to predicted the household consumption power task with the LSTM model in Pytorch, I have tried to add the normalization through the MinMaxScaler(), and tries to to reshape it to the ...
0
votes
1
answer
118
views
Pytorch LSTM Multi Target Dimension Error
I've been trying for days to do an LSTM Multi Target without success, for a dataset with the first 8 columns being targets and the other columns features, generating dimension errors. The challenge ...
- 1
0
votes
0
answers
41
views
Why do I get a long list of zeros in classification of text?
I have 500 comments in Russian from YouTube. I tokenized them using the youtokentome library.
df['textOriginal'].to_csv('text.txt', index=False, header=False)
model_path = 'tokenizer.model'
yttm.BPE....
