This repository is created for on-device real time hand segmentation in video footage.
-
Updated
Jan 18, 2022 - Jupyter Notebook
This repository is created for on-device real time hand segmentation in video footage.
The original experiments code for AAAI 2020 paper, "AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates"
PyTorch models optimization by neural network pruning
Implementation of Adversarial Training for BERT and BERT-Like Models and Analysis of effects of model compression on Robustness of a model
Code Implementation of On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee
Cut models not trees 🌳
Compressed CNNs for airplane classification in satellite images (APoZ-based parameter pruning, INT8 weight quantization)
[ICLR 2022] Code for paper "Exploring Extreme Parameter Compression for Pre-trained Language Models"(https://arxiv.org/abs/2205.10036)
Brute Force Architecture Search
About Code for the paper "NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models" (EMNLP 2023 Findings)
Iterative Training: Finding Binary Weight Deep Neural Networks with Layer Binarization
analysing Model Pruning and Unit Pruning on a large dense MNIST network
Pruning System in Keras for a Deeper Look Into Convolutions
模型剪枝小demo
This repository includes a general informations and examples about how to make a machine learning model just a few lines of code in Python using PyCaret package.
Presented at the 2023 International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG 2023). Lightweight mirror segmentation CNN that uses an EfficientNet backbone, employs parallel convolutional layers to capture edge features, and applies filter pruning for model compression
Transformers Compression Practice
Vocabulary Trimming (VT) is a model compression technique, which reduces a multilingual LM vocabulary to a target language by deleting irrelevant tokens from its vocabulary. This repository contains a python-library vocabtrimmer, that remove irrelevant tokens from a multilingual LM vocabulary for the target language.
basis embedding: a product quantization based model compression method for language models.
Implementation of the SuRP algorithm by the authors of the AISTATS 2022 paper "An Information-Theoretic Justification for Model Pruning".
Add a description, image, and links to the model-compression topic page so that developers can more easily learn about it.
To associate your repository with the model-compression topic, visit your repo's landing page and select "manage topics."