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/2023-MindSpore-1/ms-code-211/tree/main/DynamicQuant
https://github.com/2023-MindSpore-1/ms-code-211/tree/main/east
EAST: Encoding-Aware Sparse Training for Deep Memory Compression of ConvNets
https://github.com/2023-MindSpore-1/ms-code-222/tree/main/bert
https://github.com/2023-MindSpore-1/ms-code-222/tree/main/snn
SNN-SC: A Spiking Semantic Communication Framework for Collaborative Intelligence
https://github.com/2023-MindSpore-1/ms-code-5/tree/main/fasttext
https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm
https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm3
https://github.com/2023-MindSpore-4/Code14/tree/main/RepVGG
https://github.com/2023-MindSpore-4/Code3/tree/main/DynamicQuant
https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/bert
https://github.com/2024-MindSpore-1/Code3/tree/main/DeepLSTM
Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation
https://github.com/A-Mulvihill/TCD-Computer-Vision-Project-2023
https://github.com/AIM-SKKU/TVQ
https://github.com/AIdeaLab/wav2vec2_docker
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/ANSHUMAN87/Bias-Correction
Data-Free Quantization Through Weight Equalization and Bias Correction
https://github.com/ActiveVisionLab/NUQ
https://github.com/Adamdad/Samesame
Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization
https://github.com/Adlik/model_optimizer
https://github.com/AhmadQasim/proxylessnas-dense
HAQ: Hardware-Aware Automated Quantization with Mixed Precision
https://github.com/AkashB23/4-bit-quantization-with-tensorflow-1.15.2
Post-training 4-bit quantization of convolution networks for rapid-deployment
https://github.com/Akaza994/Binary-Quantization
BinaryRelax: A Relaxation Approach For Training Deep Neural Networks With Quantized Weights
https://github.com/Arizona-Voice/Arizona-spotting
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/ArtyZe/yolo_quantization
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
https://github.com/AxelvL/AHPQ.jl
Accelerating Large-Scale Inference with Anisotropic Vector Quantization
https://github.com/BatsResearch/LexC-Gen
https://github.com/Beomi/BitNet-Transformers
BitNet: Scaling 1-bit Transformers for Large Language Models
https://github.com/BirgerMoell/tmh
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/BlinkDL/RWKV-LM
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
https://github.com/CanyonWind/Single-Path-One-Shot-NAS-MXNet
Single Path One-Shot Neural Architecture Search with Uniform Sampling
https://github.com/ChernovAndrey/chronos-forecasting-wasserstein
https://github.com/CoderINusE/NIPS-implementation
https://github.com/CoderINusE/unbounded-cache-lm
https://github.com/CycloneBoy/PPDetectionPytorch
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
https://github.com/DBraun/DAC-JAX
https://github.com/DW-yejing/fasttext4j-jdk6
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.