search

OSUPCVLab / MobileUNETR

Official Implementation of MobileUNETR: A Lightweight End-To-End Hybrid Vision Transformer For Efficient Medical Image Segmentation (ECCV2024) (Oral)
39 stars 4 forks source link

When backpropagating gradients, why do you encounter NaN values? #2

Open lhhvictory opened 2 months ago

lhhvictory commented 2 months ago

When backpropagating gradients, why do you encounter NaN values? RuntimeError: Function 'AddBackward0' returned nan values in its 0th output.

srperera commented 2 months ago

we did not encounter that issue during training. where do you run into this issue?