3rd place solution for NeurIPS 2019 MicroNet challenge
-
Updated
Nov 8, 2019 - Python
3rd place solution for NeurIPS 2019 MicroNet challenge
This repository is the official implementation of the paper Pruning via Iterative Ranking of Sensitivity Statistics and implements novel pruning / compression algorithms for deep learning / neural networks. Amongst others it implements structured pruning before training, its actual parameter shrinking and unstructured before/during training.
(Unstructured) Weight Pruning via Adaptive Sparsity Loss
Submission name: QualcommAI-EfficientNet. MicroNet Challenge (NeurIPS 2019) submission - Qualcomm AI Research
ESPN: Extreme Sparse Pruned Network
The repository contains an implementation to try experiments of Lottery Ticket Hypothesis
Add a description, image, and links to the unstructured-pruning topic page so that developers can more easily learn about it.
To associate your repository with the unstructured-pruning topic, visit your repo's landing page and select "manage topics."