https://github.com/anubis09/resource_constrained_semantic_segmentation_for_waste_sorting
공식 코드Resource Constrained Semantic Segmentation for Waste Sorting
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/aozhongzhang/comq
공식 코드COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization
https://github.com/aozhongzhang/magr
공식 코드MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
https://github.com/aparna-aketi/Low_Precision_DL
공식 코드Low Precision Decentralized Distributed Training over IID and non-IID Data
https://github.com/apple/learning-compressible-subspaces
공식 코드LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time
https://github.com/applied-machine-learning-lab/embedding-in-recommender-systems
공식 코드https://github.com/arghadippurdue/GraNNite
공식 코드https://github.com/arielamar123/adc-learning-hyperopt
공식 코드https://github.com/artidoro/qlora
공식 코드https://github.com/arunmallya/piggyback
공식 코드Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights
https://github.com/asdvfghg/bearingpga-net
공식 코드https://github.com/austin-thetrueshinobi/is-win-research
공식 코드Hardware Acceleration for Real-Time Wildfire Detection Onboard Drone Networks
https://github.com/avc2-uestc/craft-sr
공식 코드Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution
https://github.com/avc2-uestc/frequency-inspired-optimization-for-efficientsr
공식 코드Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution
https://github.com/avc2-uestc/qmedsam
공식 코드Efficient Quantization-Aware Training on Segment Anything Model in Medical Images and Its Deployment
https://github.com/awai54st/Enabling-Binary-Neural-Network-Training-on-the-Edge
공식 코드https://github.com/awei669/VQ-Font
공식 코드https://github.com/awslabs/sockeye
공식 코드The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020
https://github.com/baaivision/nova
공식 코드https://github.com/balditommaso/PyLandscape
공식 코드Loss Landscape Analysis for Reliable Quantized ML Models for Scientific Sensing
https://github.com/baohaoliao/apiq
공식 코드https://github.com/baoshengyu/H3R
공식 코드https://github.com/barasamit/QuantAttack
공식 코드QuantAttack: Exploiting Dynamic Quantization to Attack Vision Transformers
https://github.com/bartwojcik/adaptive_computation_modules
공식 코드Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference
https://github.com/bashlab/quads
공식 코드QUADS: QUAntized Distillation Framework for Efficient Speech Language Understanding
https://github.com/basiralab/falcon
공식 코드FALCON: Feature-Label Constrained Graph Net Collapse for Memory Efficient GNNs
https://github.com/batuceng/max_quantile
공식 코드https://github.com/bcjuan/itmmqnet
공식 코드A Mixed Quantization Network for Computationally Efficient Mobile Inverse Tone Mapping
https://github.com/ben-hawks/pytorch-jet-classify
공식 코드Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference
https://github.com/benediktfesl/quantized_channel_estimation
공식 코드Channel Estimation for Quantized Systems based on Conditionally Gaussian Latent Models
https://github.com/beyondhtx/qprompt
공식 코드Quantized Prompt for Efficient Generalization of Vision-Language Models
https://github.com/bghojogh/Quantized-Fisher-Discriminant-Analysis
공식 코드https://github.com/bhigy/discrete-repr
공식 코드Discrete representations in neural models of spoken language
https://github.com/biclab/spikeyolo
공식 코드https://github.com/bifeat/bifeat
공식 코드BiFeat: Supercharge GNN Training via Graph Feature Quantization
https://github.com/billamihom/rapq
공식 코드RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.