Questions tagged [pytorch]
Pytorch is an open source library for Tensors and Dynamic neural networks in Python with strong GPU acceleration. For details, see https://pytorch.org.
722 questions
1vote
0answers
26views
What's wrong with my ML implementation? (from a technical report)
I came across a (short and curt) technical report that claims to be SOTA on keyword spotting, but it didn't share its code and had a very short explanation of its network. I implemented the model, but ...
2votes
0answers
28views
PyGOD memory error despite batch size argument
Anyone know why PyGOD's DOMINANT implementation produces a memory error even though the batch size argument is reasonable? To reproduce: ...
- 121
0votes
0answers
17views
Custom loss function not behaving as expected in PyTorch but does in TensorFlow
I tried modifying the reconstruction loss such that values that are pushed out of bounds do not contribute to the loss and it works as expected in tensorflow after training an autoencoder. However, ...
2votes
0answers
38views
How to train next token prediction text generation model using Pytorch Transformer classes?
For learning purposes, I have tried to train a text generation model at a tiny scale in this notebook using RNN/LSTM model. But I am not able to take it further to use transformer model. Can anyone ...
0votes
0answers
38views
Does `torch_mlir.compile` exist now in Pytorch?
I was trying to build and run a pytorch based project code. But I'm facing some errors. I'm attaching the code: ...
0votes
0answers
14views
How to properly implement and debug RPN anchors in ResNet-18 for multi-object detection?
I am working on my first object detection project and need to implement multi-object detection using ResNet-18 (I am restricted to using this architecture). My dataset follows the COCO format and ...
- 11
0votes
0answers
32views
How to feed a list of tensor images to nn in the right way?
I am building a neural networks based with a dataloader I defined. I defined a class that take samples randomly from a list of images. However when I train the network, after loading first batch to ...
- 149
0votes
0answers
20views
Is my Pytorch's LSTM underfiting
Friends here I want to ask about graph loss on my LSTM Pytorch modeling for stock price prediction, with like this is my modeling overfitting? for the results themselves are good, like this: MSE: ...
1vote
0answers
30views
LSTM predicts the same value
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 ...
0votes
0answers
13views
Adding context specific information to RNN/LSTM at current time?
I have a time series of values like below, where I'm looking at a history of sales: ...
- 157
0votes
1answer
24views
How dataloader shuffle dataset per epoch?
Since dataloader is defined before training begins, I was wondering what does 'shuffle= True' mean. It can be two cases: it only shuffle batch orders for the next epoch but each batch is constant. it ...
- 149
4votes
1answer
339views
Why my program does not work for higher dimension tensors?
I am trying to write a model in pytorch. I have 3 classes A,B,C. Each class is a list of tensors. I want to take samples from these classes. Each class has also a reserve class that when the class is ...
- 149
1vote
0answers
24views
Difficulity extracting predicted values and target values from TFT model (pytorch)
I'm building a TFT forecasting model using PyTorch for the first time and having trouble extracting the predicted values along with their corresponding actual values from the output. Ideally, I’d like ...
- 11
1vote
0answers
14views
How can I efficiently process and load a large Protobuf dataset for machine learning model training?
I am training a model on multiple cache miss examples from various trace simulations. For every trace I have thousands of miss examples stored and I have many traces. I'm storing the examples in ...
- 11
0votes
1answer
46views
why cuda is not available?
I was trying to install pytorch with cuda on my system. My gpu is a little old. Its NVIDIA GeForce GT 720m and my driver version is 391.35. When I installed cudatoolkit in anaconda, it installed CUDA ...
- 149
