Official code for "Run Time Adaptive Network Slimming for Mobile Environments", ISCAS 2019.
-
Updated
Oct 19, 2022 - Python
Official code for "Run Time Adaptive Network Slimming for Mobile Environments", ISCAS 2019.
An integrated PyTorch pipeline for pretraining GPT-2 on linear regression tasks with curriculum learning and fine-tuning on extended downstream tasks. Includes adaptive pruning (AdaPrune) to compare pruning-based adaptation against standard gradient-based fine-tuning.
Add a description, image, and links to the adaptive-pruning topic page so that developers can more easily learn about it.
To associate your repository with the adaptive-pruning topic, visit your repo's landing page and select "manage topics."