My language model produces fluent responses.Even when it does not know the answer, it sounds confident.Users sometimes trust incorrect replies.There is no indication of uncertainty.
Home/deep learning
Decode Trail Latest Questions
My GAN generates images but they look washed out.Many samples look almost identical.Training loss looks stable.But the visual quality never improves.
I upgraded to a GPU with much more VRAM.I increased the batch size to use the available memory.Now the training is noticeably slower per epoch.There are no errors, but performance feels worse than before.
Asked: April 14, 2025In: Deep Learning
I am training a convolutional neural network on a custom image dataset using PyTorch.For the first few batches the loss looks normal, but suddenly it becomes NaN and never recovers.There are no crashes or stack traces, only the ...