https://bitbucket.org/YanivShu/binary_weighted_networks_public
공식 코드Exact Backpropagation in Binary Weighted Networks with Group Weight Transformations
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://bitbucket.org/dmmlgeneva/softvqae
공식 코드Learned transform compression with optimized entropy encoding
https://bitbucket.org/edge-team-leat/microai_public
공식 코드Quantization and Deployment of Deep Neural Networks on Microcontrollers
https://bitbucket.org/fhirschberger/clustering
공식 코드Large Scale Clustering with Variational EM for Gaussian Mixture Models
https://bitbucket.org/maciekwielgosz/anomaly_detection
공식 코드https://code.stanford.edu/tambe-lab/blockdialect
공식 코드BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference
https://git.skewed.de/count0/graph-tool
공식 코드Network reconstruction via the minimum description length principle
https://github.com/0nutation/slmtokbench
공식 코드SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models
https://github.com/0nutation/uslm
공식 코드SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models
https://github.com/0xshooka/frame-symbol
공식 코드Evaluating Large Language Models on the Frame and Symbol Grounding Problems: A Zero-shot Benchmark
https://github.com/1adrianb/binary-networks-pytorch
공식 코드Improved training of binary networks for human pose estimation and image recognition
https://github.com/1hunters/LIMPQ
공식 코드Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance
https://github.com/1hunters/retraining-free-quantization
공식 코드Retraining-free Model Quantization via One-Shot Weight-Coupling Learning
https://github.com/30stomercury/autoregressive-co-training
공식 코드Autoregressive Co-Training for Learning Discrete Speech Representations
https://github.com/42Shawn/CMIM
공식 코드https://github.com/42shawn/causal-dfq
공식 코드https://github.com/42shawn/lcr_bnn
공식 코드https://github.com/42shawn/ptq4dm
공식 코드https://github.com/5k5000/cldetection2023
공식 코드https://github.com/A2R-Lab/Just-Round
공식 코드Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion
https://github.com/ACIL-Group/DDVFA
공식 코드https://github.com/AI-Application-and-Integration-Lab/Accept
공식 코드ACCEPT: Adaptive Codebook for Composite and Efficient Prompt Tuning
https://github.com/AaronZ345/StyleSinger
공식 코드StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis
https://github.com/AaronZ345/TCSinger
공식 코드TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control
https://github.com/Aaronhuang-778/SliM-LLM
공식 코드SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
https://github.com/Abhishek2271/TransferabilityAnalysis
공식 코드Properties that allow or prohibit transferability of adversarial attacks among quantized networks
https://github.com/AlbertOh90/Soft-VQ-VAE
공식 코드https://github.com/AlexBlck/compsketch
공식 코드https://github.com/AlignedQuant/AlignedKV
공식 코드AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned Quantization
https://github.com/AngusG/cleverhans-attacking-bnns
공식 코드https://github.com/ApexGen-X/MergeVQ
공식 코드https://github.com/Aria-K-Alethia/BigCodec
공식 코드BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec
https://github.com/Atmegal/DGCPN
공식 코드Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashing
https://github.com/AyoubBelhadji/disruptive_quantization
공식 코드Weighted quantization using MMD: From mean field to mean shift via gradient flows
https://github.com/BGUCompSci/WaveletCompressedConvolution
공식 코드https://github.com/BME-SmartLab/DeepMOS
공식 코드Improving Self-Supervised Learning-based MOS Prediction Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.