Questions tagged [pytorch-lightning]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0 votes
0 answers
10 views

How to selectively train a deep model based on the unavailability of a subset of the feature set

I am creating a deep learning binary classification model. Each sample in the dataset contains two mutually exclusive feature sets X and Y. Feature set X is present in all samples; however, there are ...
flamingo_stark's user avatar
0 votes
0 answers
16 views

Bayes HyperParameter tuning using wandb

Here in below code, I'm trying to use wandb sweep to find optimal lr, weight-decay using the below code: ...
Sarvagya Porwal's user avatar
0 votes
0 answers
71 views

Multi GPU training using Pytorch fabric

I am launching the Pytorch fabric below : ...
Shrinidhi M's user avatar
0 votes
1 answer
408 views

Torchmetrics Binary Accuracy and Multiclass Accuracy don't match

in my program I have the problem that for a 2-class classification problem my multiclass accuracy and binary class accuracy don't match. I have generated a very small sample example where you can see ...
YumYum's user avatar
  • 3
1 vote
0 answers
107 views

Backward propagation slower as epochs increase in pytorch

I'm trying to replicate TasNet paper using Pytorch Lightning, but the training time increases as the epochs increase (the first epoch takes 20 seconds, the fifth 2:30 minutes). I've used PyTorch ...
programming-duck's user avatar
0 votes
0 answers
944 views

RuntimeError: It looks like your LightningModule has parameters that were not used in producing the loss returned by training_step

I'm trying to use donut, which is a transformer model with a huggingface implementation, and pre-train it on a language it hasn't been yet on my desktop. Unfortunately the version of the stack ...
lte__'s user avatar
  • 1,320