Topic: "model-compression"
chouaib-629/quantileRegression
Quantile regression for delivery time and some scenarios.
Language: Jupyter Notebook - Size: 589 KB - Last synced at: 22 days ago - Pushed at: 4 months ago - Stars: 2 - Forks: 0
msadeqsirjani/adaptive_edge_ai
Optimizing deep learning models for edge devices through intelligent compression and knowledge distillation. Achieve up to 90% model size reduction while maintaining performance, enabling efficient AI deployment on resource-constrained devices.
Language: Python - Size: 395 KB - Last synced at: about 1 month ago - Pushed at: 5 months ago - Stars: 2 - Forks: 0
Miocio-nora/Decay_Pruning_Method
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.
Size: 417 KB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 2 - Forks: 0
ksm26/Quantization-Fundamentals-with-Hugging-Face
Learn linear quantization techniques using the Quanto library and downcasting methods with the Transformers library to compress and optimize generative AI models effectively.
Language: Jupyter Notebook - Size: 205 KB - Last synced at: about 1 month ago - Pushed at: about 1 year ago - Stars: 2 - Forks: 9
oswaldoludwig/Pruning-pre-trained-models-using-evolutionary-computation
This repository contains scripts to prune Wav2vec2 using a neuroevolution-based method. More details about this method can be found in the paper Compressing Wav2vec2 for Embedded Applications.
Language: Shell - Size: 4.53 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 2 - Forks: 0
cuguilke/psykedelic
Pruning System in Keras for a Deeper Look Into Convolutions
Language: Python - Size: 3.21 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 2 - Forks: 0
memgonzales/mirror-segmentation
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
Language: Python - Size: 197 MB - Last synced at: about 2 months ago - Pushed at: almost 2 years ago - Stars: 2 - Forks: 0
llyx97/Marginal-Utility-Diminishes
[ACL 2021] "Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation", Yuanxin Liu, Fandong Meng, Zheng Lin, Weiping Wang, Jie Zhou
Language: Python - Size: 2.25 MB - Last synced at: about 2 years ago - Pushed at: over 2 years ago - Stars: 2 - Forks: 0
r-papso/torch-optimizer
PyTorch models optimization by neural network pruning
Language: Python - Size: 55.3 MB - Last synced at: 19 days ago - Pushed at: about 3 years ago - Stars: 2 - Forks: 1
anishacharya/Online-Embedding-Compression-AAAI-2019
Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or introduce significant latency. We propose a compression method that leverages low rank matrix factorization during training, to compress the word embedding layer which represents the size bottleneck for most NLP models. Our models are trained, compressed and then further re-trained on the downstream task to recover accuracy while maintaining the reduced size. Empirically, we show that the proposed method can achieve 90% compression with minimal impact in accuracy for sentence classification tasks, and outperforms alternative methods like fixed-point quantization or offline word embedding compression. We also analyze the inference time and storage space for our method through FLOP calculations, showing that we can compress DNN models by a configurable ratio and regain accuracy loss without introducing additional latency compared to fixed point quantization. Finally, we introduce a novel learning rate schedule, the Cyclically Annealed Learning Rate (CALR), which we empirically demonstrate to outperform other popular adaptive learning rate algorithms on a sentence classification benchmark.
Language: Python - Size: 36 MB - Last synced at: about 2 years ago - Pushed at: over 3 years ago - Stars: 2 - Forks: 2
chadHGY/awesome-deep-model-compression
Awesome Deep Model Compression
Size: 47.9 KB - Last synced at: 5 days ago - Pushed at: about 4 years ago - Stars: 2 - Forks: 0
seanjparker/knowledge-distillation
Knowledge Distillation using Teacher-Student and Teacher-Assistant-Student Models
Language: Jupyter Notebook - Size: 46.9 MB - Last synced at: over 1 year ago - Pushed at: over 4 years ago - Stars: 2 - Forks: 1
elliottloveridge/compressed-video-classification
Quantization, Element-Wise Pruning and Knowledge Distillation applied to 3D CNN's for Video Classification.
Language: Python - Size: 17.6 MB - Last synced at: about 2 years ago - Pushed at: over 4 years ago - Stars: 2 - Forks: 0
Inpyo-Hong/Model-Compression-Paper-List
Model Compression Paper List (Focusing on Quantization, Particularly Zero-Shot Quantization)
Size: 42 KB - Last synced at: 11 days ago - Pushed at: 11 days ago - Stars: 1 - Forks: 0
18520339/unstructured-local-search-pruning
Apply Simulated Annealing and Genetic Algorithm to solve the problem of Neural Network pruning without prior assumptions of weight importance
Language: Jupyter Notebook - Size: 2.28 MB - Last synced at: 8 days ago - Pushed at: 5 months ago - Stars: 1 - Forks: 0
amikom-gace-research-group/characterize-pruning
Characterization study repository for pruning, a popular way to compress a DL model. this repo also investigates optimal sparse tensor layouts for pruned nets
Language: Python - Size: 64.5 KB - Last synced at: 10 months ago - Pushed at: 10 months ago - Stars: 1 - Forks: 1
ChenyangLi-97/NN-BCD
Code Implementation of On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee
Language: Jupyter Notebook - Size: 9.9 MB - Last synced at: 8 months ago - Pushed at: over 1 year ago - Stars: 1 - Forks: 0
elphinkuo/distiller
The original experiments code for AAAI 2020 paper, "AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates"
Language: Jupyter Notebook - Size: 36.1 MB - Last synced at: about 2 months ago - Pushed at: over 1 year ago - Stars: 1 - Forks: 0
vi2enne/Neural-Network-Pruning
Language: Python - Size: 60.5 KB - Last synced at: 12 months ago - Pushed at: over 2 years ago - Stars: 1 - Forks: 1
souvikdey05/Human_Activity_Recognition
Classify an activity by sensor data from gyroscope and accelerometer.
Language: Python - Size: 2.2 MB - Last synced at: about 2 years ago - Pushed at: almost 4 years ago - Stars: 1 - Forks: 1
philsaurabh/Neuron-Pruning-Demonstration
Implementation of Neuron Pruning with weight pruning
Language: Jupyter Notebook - Size: 3.42 MB - Last synced at: about 2 years ago - Pushed at: over 4 years ago - Stars: 1 - Forks: 0
suuyawu/PED-Model-Compression
Implementation for the paper "Model-free Energy Distance for Pruning Deep Neural Networks"
Language: Python - Size: 1.77 MB - Last synced at: about 1 year ago - Pushed at: over 4 years ago - Stars: 1 - Forks: 1
daniel-rychlewski/cnn-planesnet
Compressed CNNs for airplane classification in satellite images (APoZ-based parameter pruning, INT8 weight quantization)
Language: Python - Size: 497 MB - Last synced at: over 1 year ago - Pushed at: almost 5 years ago - Stars: 1 - Forks: 0
ieee820/RFSong-7993 Fork of songwsx/RFSong-7993
设计的轻量级RFB进行行人检测，AP达到0.7993，参数量仅有3.1MB，200 FPS
Size: 11.7 MB - Last synced at: almost 2 years ago - Pushed at: over 5 years ago - Stars: 1 - Forks: 0
sujin-1013/task-aware-DMO
Task-Aware Dynamic Model Optimization for Multi-Task Learning (IEEE Access 2023)
Size: 1.47 MB - Last synced at: 8 days ago - Pushed at: 8 days ago - Stars: 0 - Forks: 0
Won-Seong/lightweight-resnet
Compressing ResNet50 with iterative pruning & distillation to maintain high accuracy on CIFAR-100.
Language: Python - Size: 115 KB - Last synced at: 23 days ago - Pushed at: 23 days ago - Stars: 0 - Forks: 0
lpalbou/model-quantizer
Effortlessly quantize, benchmark, and publish Hugging Face models with cross-platform support for CPU/GPU. Reduce model size by 75% while maintaining performance.
Language: Python - Size: 165 KB - Last synced at: 14 days ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0
jaicdev/QDPStudio
QDP Studio is a unified framework for deep learning model compression. It combines quantization, pruning, and decomposition to reduce model size, improve inference speed, and maintain accuracy. Its streamlined pipeline for training, compressing, and evaluating models optimizes deployments in resource-constrained environments.
Language: Python - Size: 35.2 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0
GabrielGlzSa/ModelCompressionRL
Library for compression of Deep Neural Networks.
Language: Jupyter Notebook - Size: 5.29 MB - Last synced at: about 2 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0
minseok0809/transformers-compression-practice
Transformers Compression Practice
Language: Jupyter Notebook - Size: 19.9 MB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 0 - Forks: 0
sathishkumar67/Knowledge-Distillation-Implementation
Model Compression using Knowledge Distillation
Language: Python - Size: 9.57 MB - Last synced at: 10 months ago - Pushed at: 10 months ago - Stars: 0 - Forks: 0
vtsouval/FedCode
Communication-Efficient Federated Learning via Transferring Codebooks
Size: 22.5 KB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 0 - Forks: 0
SCUS3/Wage-Regression-Analysis
This project provides a comprehensive guide to implementing PCA from scratch and validating it using scikit-learn's implementation. The visualizations help in understanding the data's variance and the effectiveness of dimensionality reduction.
Language: Python - Size: 18.6 KB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 0 - Forks: 0
jaketae/nn-svd
Neural network compression with SVD
Language: Python - Size: 33.2 KB - Last synced at: about 1 month ago - Pushed at: about 1 year ago - Stars: 0 - Forks: 0
jchenghu/sharebert
Implementation of the work "ShareBERT: Embeddings Are Capable of Learning Hidden Layers".
Language: Python - Size: 206 KB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 0 - Forks: 0
Neural-Dreamers/Forest-Sound-Analysis-on-Edge
A Comparative Analysis of Sound Data Pre-processing and Deep Learning Model Compression Techniques: A Study on Forest Sound Classification
Language: Jupyter Notebook - Size: 49.8 KB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 0 - Forks: 0
christopheitenberger/VSOL
Versioning System for Online Learning systems (VSOL)
Language: Python - Size: 3.09 MB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 0 - Forks: 0
basiralab/CQSIGN
Affordable GNN using Topological Contraction
Language: C - Size: 36.3 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0
angelolamonaca/PyTorch-Precision-Converter
A flexible utility for converting tensor precision in PyTorch models and safetensors files, enabling efficient deployment across various platforms.
Language: Python - Size: 3.91 KB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0
yester31/Pruning_EX
deep learning model compression with pruning
Language: Python - Size: 40 KB - Last synced at: almost 2 years ago - Pushed at: almost 2 years ago - Stars: 0 - Forks: 0
ataozarslan/PyCaret_Tutorial
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.
Language: Jupyter Notebook - Size: 130 KB - Last synced at: almost 2 years ago - Pushed at: almost 2 years ago - Stars: 0 - Forks: 0
diaoenmao/Restricted-Recurrent-Neural-Networks
[IEEE BigData 2019] Restricted Recurrent Neural Networks
Language: Python - Size: 10.8 MB - Last synced at: almost 2 years ago - Pushed at: about 2 years ago - Stars: 0 - Forks: 1
gowtham1997/Analysis_Of_Pruning_Techniques
analysing Model Pruning and Unit Pruning on a large dense MNIST network
Language: Jupyter Notebook - Size: 1.4 MB - Last synced at: about 2 years ago - Pushed at: over 2 years ago - Stars: 0 - Forks: 0
eyllcyldrm/MantarSiniflandirma
SVC and KNN methods were used to predict whether mushrooms are poisonous or edible according to their properties. Random forest and chi-square variable selection methods were applied and the 10-fold cross validation method was used and f1 scores were calculated by re-estimating. Finally, the models were compared.
Language: Jupyter Notebook - Size: 108 KB - Last synced at: about 2 years ago - Pushed at: almost 3 years ago - Stars: 0 - Forks: 0
NeelayS/KD_Lib Fork of SforAiDl/KD_Lib
A PyTorch model compression library consisting of knowledge distillation, pruning and quantization algorithms
Language: Python - Size: 22.2 MB - Last synced at: about 2 years ago - Pushed at: almost 3 years ago - Stars: 0 - Forks: 0
rwang97/SensAI-ViT Fork of ElliotBao/SensAI-Transformer
Class parallelism for Vision Transformer
Size: 37.7 MB - Last synced at: over 1 year ago - Pushed at: almost 3 years ago - Stars: 0 - Forks: 0
VijayKalmath/AdversarialTraining_in_Distilation_Of_BERT
Implementation of Adversarial Training for BERT and BERT-Like Models and Analysis of effects of model compression on Robustness of a model
Language: Jupyter Notebook - Size: 19.9 MB - Last synced at: about 2 years ago - Pushed at: almost 3 years ago - Stars: 0 - Forks: 0
CaoHaiNam/Sparsify-In-Deep-Neural-Network
Language: Python - Size: 155 KB - Last synced at: over 1 year ago - Pushed at: about 3 years ago - Stars: 0 - Forks: 0
rakutentech/iterative_training
Iterative Training: Finding Binary Weight Deep Neural Networks with Layer Binarization
Language: Python - Size: 179 KB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 0 - Forks: 1
IIGROUP/CNN-FCF
[CVPR 2019] Compressing Convolutional Neural Networks via Factorized Convolutional Filters.
Language: Python - Size: 165 KB - Last synced at: about 2 years ago - Pushed at: about 4 years ago - Stars: 0 - Forks: 0
underflow101/ai-zipper
ai-zipper offers numerous AI model compression methods, also it is easy to embed into your own source code
Language: Python - Size: 5.86 KB - Last synced at: about 2 years ago - Pushed at: about 4 years ago - Stars: 0 - Forks: 0
iid2019/iddl
An Integrated Distributed Deep Learning (IDDL) framework.
Language: Jupyter Notebook - Size: 24.9 MB - Last synced at: about 2 years ago - Pushed at: over 4 years ago - Stars: 0 - Forks: 0
chenllliang/Model-Compression-For-Speaker-Recognition
Distillation examples. Trying to make Speaker Recognition Faster through different Model Compression techniques
Language: Python - Size: 12.7 KB - Last synced at: about 1 year ago - Pushed at: almost 5 years ago - Stars: 0 - Forks: 1
jason950374/feature-compression
Language: Python - Size: 471 KB - Last synced at: about 2 years ago - Pushed at: about 5 years ago - Stars: 0 - Forks: 0
niyazed/cutting-models
Cut models not trees 🌳
Language: Jupyter Notebook - Size: 105 KB - Last synced at: about 2 years ago - Pushed at: over 5 years ago - Stars: 0 - Forks: 0
johnnyasd12/papers
awesome machine learning / deep learning papers
Size: 377 MB - Last synced at: over 1 year ago - Pushed at: over 5 years ago - Stars: 0 - Forks: 0
ieee820/distiller Fork of IntelLabs/distiller
Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://nervanasystems.github.io/distiller
Language: Jupyter Notebook - Size: 31.8 MB - Last synced at: almost 2 years ago - Pushed at: over 6 years ago - Stars: 0 - Forks: 0
ieee820/keras_compressor Fork of DwangoMediaVillage/keras_compressor
Model Compression CLI Tool for Keras.
Language: Python - Size: 19.5 KB - Last synced at: almost 2 years ago - Pushed at: over 6 years ago - Stars: 0 - Forks: 0
ieee820/Discrimination-aware-Channel-Pruning-for-Deep-Neural-Networks Fork of SCUT-AILab/DCP
Code for “Discrimination-aware-Channel-Pruning-for-Deep-Neural-Networks”
Language: Python - Size: 1.99 MB - Last synced at: almost 2 years ago - Pushed at: over 6 years ago - Stars: 0 - Forks: 0
aicaffeinelife/Experience_Loss
Code for paper - Experience Loss in PyTorch.
Language: Python - Size: 1.56 MB - Last synced at: almost 2 years ago - Pushed at: over 6 years ago - Stars: 0 - Forks: 0
okz12/NN_compression
Neural Network Compression
Language: Jupyter Notebook - Size: 3.16 GB - Last synced at: about 2 years ago - Pushed at: over 6 years ago - Stars: 0 - Forks: 1
Huizerd/monodepth Fork of mrharicot/monodepth
Model compression methods applied to the monocular depth estimation network by Godard et al.
Language: Python - Size: 9.95 MB - Last synced at: over 1 year ago - Pushed at: almost 7 years ago - Stars: 0 - Forks: 1
