https://github.com/firasl/BoCF
Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks
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/flagai-open/aquila2
https://github.com/flyingTan/DSQ
Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks
https://github.com/flytocc/PaddleClas
https://github.com/fongyk/graph-attention
End-to-end Learning of Deep Visual Representations for Image Retrieval
https://github.com/fongyk/graph-simple
End-to-end Learning of Deep Visual Representations for Image Retrieval
https://github.com/fostiropoulos/dvq
https://github.com/gatech-eic/s3-router
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/gatech-eic/shiftaddllm
https://github.com/gauenk/faiss_fork
https://github.com/geffencooper/ai8x-synthesis_ECE196
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
https://github.com/golsun/dialogrpt
ConveRT: Efficient and Accurate Conversational Representations from Transformers
https://github.com/greenbitai/low_bit_llama
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/guoqiang-zhang-x/BDIA
On Exact Bit-level Reversible Transformers Without Changing Architectures
https://github.com/hahnyuan/llmviewer
https://github.com/haiciyang/ladiffcodec
Generative De-Quantization for Neural Speech Codec via Latent Diffusion
https://github.com/hanfeng108/Language-Detection
https://github.com/haoosz/BiGR
https://github.com/hartb/faiss-gpu-feedstock
https://github.com/harvard-edge/source-seeking
https://github.com/heguixiang/caffe_deep_compression
https://github.com/hey-yahei/Quantization.MXNet
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
https://github.com/hey-yahei/RT_Quantization.MXNet
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
https://github.com/hltchkust/cantonese-asr
Unsupervised Cross-lingual Representation Learning for Speech Recognition
https://github.com/hmkx/hinerv
HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation
https://github.com/hpi-xnor/BMXNet
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
https://github.com/hqjenny/CoDeNet
https://github.com/huanzhang12/CROWN-IBP
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
https://github.com/huanzhang12/alpha-beta-CROWN
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
https://github.com/hufscapstone/Fast_text
https://github.com/huggingface/block_movement_pruning
And the Bit Goes Down: Revisiting the Quantization of Neural Networks
https://github.com/huggingface/nn_pruning
https://github.com/huggingface/text-generation-inference
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/huggingface/transformers-bloom-inference
ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers
https://github.com/huseinzol05/malaya-speech
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/hustzxd/LSQuantization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.