A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch
-
Updated
Jan 22, 2024 - Python
A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch
Multi-task learning with adapted torchvision models (SSD, FasterRCNN, DeepLabv3) using Lightning-AI
Add a description, image, and links to the loss-balancing topic page so that developers can more easily learn about it.
To associate your repository with the loss-balancing topic, visit your repo's landing page and select "manage topics."