Papers with Code 아카이브
Quantization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 10
- 보존된 평가 기록
- 32
Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16).
Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ozzzp/ternary_decompose
공식 코드Ternary Singular Value Decomposition as a Better Parameterized Form in Linear Mapping
https://github.com/paperProof24/Appendix_BLAQ
공식 코드One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training
https://github.com/parikshit14/qnn-for-weed
공식 코드https://github.com/pashtari/lrf
공식 코드Quantization-aware Matrix Factorization for Low Bit Rate Image Compression
https://github.com/passalis/cbof
공식 코드Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks
https://github.com/pbonazzi/eva
공식 코드RGB-Event Fusion with Self-Attention for Collision Prediction
https://github.com/pclucas14/adaptive-quantization-modules
공식 코드Online Learned Continual Compression with Adaptive Quantization Modules
https://github.com/pei65536/graph_signal_compression
공식 코드https://github.com/pengshuang/PTQ4Protein
공식 코드Exploring Post-Training Quantization of Protein Language Models
https://github.com/perturb-spectrum/analysis_and_methods
공식 코드https://github.com/photooon/cqil
공식 코드CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent Layers
https://github.com/phuocphn/uniq
공식 코드Training Multi-bit Quantized and Binarized Networks with A Learnable Symmetric Quantizer
https://github.com/pic4ser/edgesrgan
공식 코드Generative Adversarial Super-Resolution at the Edge with Knowledge Distillation
https://github.com/pietro-talli/tmlcn_code
공식 코드https://github.com/pilancilab/caldera
공식 코드Compressing Large Language Models using Low Rank and Low Precision Decomposition
https://github.com/pilancilab/matrix-compressor
공식 코드Matrix Compression via Randomized Low Rank and Low Precision Factorization
https://github.com/pingchengdong/gqa-lut
공식 코드Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers
https://github.com/pingxue-hfut/ir2net
공식 코드IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks
https://github.com/pingxue-hfut/sd-bnn
공식 코드https://github.com/pku-sec-lab/fpqvar
공식 코드FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design
https://github.com/pladifes/climate_finance_bench
공식 코드https://github.com/possoj/fpga-spacepose
공식 코드https://github.com/pphuc25/distil-cd
공식 코드https://github.com/pprp/acbench
공식 코드Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
https://github.com/prateeky2806/compeft
공식 코드https://github.com/pravin1390/FastHDFilter
공식 코드Fast High-Dimensional Bilateral and Nonlocal Means Filtering
https://github.com/preminstrel/ECG-Classification
공식 코드https://github.com/princeton-nlp/DensePhrases
공식 코드https://github.com/prip-lab/MSU-LatentAFIS
공식 코드https://github.com/probberechts/pqdtw
공식 코드https://github.com/publiccoderepo/SMP_GNN_Quant
공식 코드Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message Propagation
https://github.com/publioelon/leaf-diseases-classification
공식 코드An Edge Computing-Based Solution for Real-Time Leaf Disease Classification using Thermal Imaging
https://github.com/pulp-platform/pulp-nn
공식 코드PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V Processors
https://github.com/purdue-nrl/TREND
공식 코드https://github.com/putshua/SNN_conversion_QCFS
공식 코드Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.