https://github.com/ambroggi/pruning-project-for-deep-neural-networks
BERT-of-Theseus: Compressing BERT by Progressive Module Replacing
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/andrijazz/pruning
https://github.com/andris955/diplomaterv
Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
https://github.com/anshu123priya/Real-v-s-Fake-Emotion-Challenge
MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Face Images
https://github.com/anshu123priya/Real-vs-Fake-Emotion-Challenge
MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Face Images
https://github.com/apd10/RzLinear
Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing
https://github.com/arm-software/ml-restructurable-activation-networks
https://github.com/astorfi/attention-guided-sparsity
GASL: Guided Attention for Sparsity Learning in Deep Neural Networks
https://github.com/athulshibu/Rewarded-meta-pruning
Revisiting Random Channel Pruning for Neural Network Compression
https://github.com/avoroshilov/tf-squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/bentoml/openllm
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/bogireddytejareddy/3d-squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/bowenl0218/bpgan-signal-compression
https://github.com/brianjychan/landuse
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/caiyuanhao1998/bisci
Basic Binary Convolution Unit for Binarized Image Restoration Network
https://github.com/cambridge-mlg/variational-shannon-coding
Weightless: Lossy Weight Encoding For Deep Neural Network Compression
https://github.com/castorini/honkling
https://github.com/chriswegmann/drone_steering
https://github.com/cmasch/squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/code-implementation1/Code4/tree/main/lenet
GASL: Guided Attention for Sparsity Learning in Deep Neural Networks
https://github.com/code-implementation1/Code8/tree/main/squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/copenlu/ALPS_2021
TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLP
https://github.com/cornell-zhang/llm-datatypes
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/coronazap/bert_client
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/cospplay/bert-master
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/cuber2460/bert
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/cuguilke/microexpnet
MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Face Images
https://github.com/cunningham-lab/cb
The continuous categorical: a novel simplex-valued exponential family
https://github.com/da-steve101/binary_connect_cifar
https://github.com/deep-learning-algorithm/LightWeightCNN
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/dfki-nlp/llmcheckup
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/digantamisra98/digantamisra98.github.io
https://github.com/dividiti/ck-caffe
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/dorlivne/simple_net_pruning
To prune, or not to prune: exploring the efficacy of pruning for model compression
https://github.com/dr-aheydari/SoftAdapt
Going Beyond Classification Accuracy Metrics in Model Compression
https://github.com/dudwns511/dcd_cikm21
DE-RRD: A Knowledge Distillation Framework for Recommender System
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.