(CVPR 2021, Oral) Dynamic Slimmable Network
-
Updated
Dec 31, 2021 - Python
(CVPR 2021, Oral) Dynamic Slimmable Network
Search Engine based on an inverted index developed by Francesca Pezzuti, Pietro Tempesti and Benedetta Tessa for the Multimedia Information Retrieval course
Make Structured Pruning Methods Smooth and Adaptive: Decay Pruning Method (DPM) is a novel smooth and dynamic pruning approach, that can be seemingly integrated with various existing structured pruning methods, providing significant improvement.
Textual Search Engine is a Java 17 application for indexing and searching text documents. It features two modules: INDEX: builds an inverted index. PROMPT: processes queries with scoring (TFIDF/BM25) and dynamic pruning.
Add a description, image, and links to the dynamic-pruning topic page so that developers can more easily learn about it.
To associate your repository with the dynamic-pruning topic, visit your repo's landing page and select "manage topics."