https://github.com/ist-daslab/gptq
공식 코드GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Papers with Code 아카이브
Model Compression
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 2
- 보존된 평가 기록
- 14
Model Compression is an actively pursued area of research over the last few years with the goal of deploying state-of-the-art deep networks in low-power and resource limited devices without significant drop in accuracy. Parameter pruning, low-rank factorization and weight quantization are some of the proposed methods to compress the size of deep networks.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ist-daslab/obc
공식 코드Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning
https://github.com/ist-daslab/spdy
공식 코드https://github.com/itayhubara/CalibTIP
공식 코드Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
https://github.com/ivclab/CPG
공식 코드Compacting, Picking and Growing for Unforgetting Continual Learning
https://github.com/ivganev/QR-decomposition-radial-NNs
공식 코드Universal approximation and model compression for radial neural networks
https://github.com/jack-willturner/characterising-neural-compression
공식 코드Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks
https://github.com/james-flemings/dp_compress
공식 코드Differentially Private Knowledge Distillation via Synthetic Text Generation
https://github.com/jbwang1997/crosskd
공식 코드CrossKD: Cross-Head Knowledge Distillation for Object Detection
https://github.com/jcw-anonymous/jcw
공식 코드Joint Channel and Weight Pruning for Model Acceleration on Moblie Devices
https://github.com/jhornauer/embedded_domain_adaptation
공식 코드Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware
https://github.com/jiaconghu/model-lego
공식 코드Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks
https://github.com/jiepku/mia-safecompress
공식 코드https://github.com/jiepku/safecompress
공식 코드https://github.com/jinqixiao/ComCAT
공식 코드COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models
https://github.com/jmdvinodjmd/HyperITE
공식 코드https://github.com/joeshenouda/vv-spaces-nn-width
공식 코드https://github.com/joserapa98/tensorization-nns
공식 코드Tensorization of neural networks for improved privacy and interpretability
https://github.com/juanerx/q-dit
공식 코드Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
https://github.com/juliagusak/musco
공식 코드https://github.com/juntongkuki/hyper-compression
공식 코드https://github.com/kaiqi123/cktf
공식 코드A Contrastive Knowledge Transfer Framework for Model Compression and Transfer Learning
https://github.com/kaiyangzhou/on-device-dg
공식 코드https://github.com/kenny-co/sgd-uap-torch
공식 코드Robustness and Transferability of Universal Attacks on Compressed Models
https://github.com/kgl-prml/shakeout-for-caffe
공식 코드Shakeout: A New Approach to Regularized Deep Neural Network Training
https://github.com/kimiandj/slicing_mi_generalization
공식 코드Slicing Mutual Information Generalization Bounds for Neural Networks
https://github.com/kuluhan/gtn
공식 코드Generalizing Teacher Networks for Effective Knowledge Distillation Across Student Architectures
https://github.com/lait-cvlab/singular-value-scaling
공식 코드Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement
https://github.com/landskape-ai/reprogram_lt
공식 코드https://github.com/lehduong/kesi
공식 코드https://github.com/lgrativol/flocora_eusipco24
공식 코드FLoCoRA: Federated learning compression with low-rank adaptation
https://github.com/lixinustc/awesome-diffusion-model-for-image-processing
공식 코드Diffusion Models for Image Restoration and Enhancement -- A Comprehensive Survey
https://github.com/luke-mcdermott-mi/distilled-pruning
공식 코드https://github.com/lxk00/BERT-EMD
공식 코드BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover's Distance
https://github.com/mac-automl/itpruner
공식 코드An Information Theory-inspired Strategy for Automatic Network Pruning
https://github.com/maincold2/Compact-3DGS
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.