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/UMich-BipedLab/sync_lidartag_apriltag
https://github.com/VenciFreeman/Compress
https://github.com/Verified-Intelligence/alpha-beta-CROWN_vnncomp2024
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
https://github.com/VincentChandelier/ELIC-QVRF
QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression
https://github.com/VincentChandelier/GACN-QVRF
QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression
https://github.com/VincentChandelier/QRAF
QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression
https://github.com/VincentChandelier/SADN-QVRF
QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression
https://github.com/VincentChandelier/STF-QVRF
QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression
https://github.com/WallaceLiu/product-quantization
Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search
https://github.com/Wi-sc/GenMesh
Neural Vector Fields: Implicit Representation by Explicit Learning
https://github.com/Xilinx/QNN-MO-PYNQ
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
https://github.com/Xilinx/brevitas/tree/f0978b2d6df559dff9097d4e3c8ffbbcfd934b96/src/brevitas_examples/super_resolution
A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance
https://github.com/ZTao-z/ProxylessNAS
HAQ: Hardware-Aware Automated Quantization with Mixed Precision
https://github.com/ZouJiu1/LSQplus
https://github.com/abdelfattah-lab/PQA
PQA: Exploring the Potential of Product Quantization in DNN Hardware Acceleration
https://github.com/agnusmaximus/Word2Bits
https://github.com/ai-forever/Kandinsky-2
MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation
https://github.com/ai-forever/movqgan
https://github.com/akashrajkn/waffles-and-posteriors
https://github.com/alextmallen/adaptive-retrieval
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
https://github.com/alfreddzh/paperso
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
https://github.com/almazan/deep-image-retrieval
End-to-end Learning of Deep Visual Representations for Image Retrieval
https://github.com/amazon-science/dq-bart
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization
https://github.com/amirgholami/pyhessian
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks
https://github.com/amirreisizadeh/QuanTimed-DSGD
https://github.com/ammesatyajit/VideoBERT
VideoBERT: A Joint Model for Video and Language Representation Learning
https://github.com/amymariaparker2401/new
https://github.com/anakin-skywalker-joseph/folder
Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models
https://github.com/analogdevicesinc/ai8x-training
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
https://github.com/andreacos/CnnJpegPrimaryQuantizationEstimation
Primary quantization matrix estimation of double compressed JPEG images via CNN
https://github.com/andrewlstewart/StereoNet_PyTorch
StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction
https://github.com/answerdotai/cold-compress
https://github.com/apple/ml-quant
https://github.com/arcee-ai/PruneMe
https://github.com/archinetai/bitcodes-pytorch
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.