We propose a lossless compression algorithm based on the NTK matrix for DNN. The compressed network yields asymptotically the same NTK as the original (dense and unquantized) network, with its weights and activations taking values only in {0, 1, -1} up to scaling.
☆26Nov 23, 2023Updated 2 years ago
Alternatives and similar repositories for Lossless_Compression
Users that are interested in Lossless_Compression are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2022] "Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, and No Retraining" by Lu Miao*, Xiaolong Luo*, T…☆34Jan 20, 2022Updated 4 years ago
- Official PyTorch implementation of "Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming" (ICML'23)☆13Apr 13, 2026Updated 2 months ago
- [CVPRW 2021] Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms☆29Nov 9, 2022Updated 3 years ago
- This is a YOLOv4 post-processing code used gpu based on pure libtorch API☆13May 15, 2022Updated 4 years ago
- Random Forest Models of Fast MTT Decision and Motion Estimation for Inter Coding of H.266/VVC☆12Mar 27, 2021Updated 5 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [Preprint] Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Prunin…☆41Sep 9, 2025Updated 9 months ago
- Zero-parameter, automatic Canny edge detection with C++ and OpenCV.☆18May 31, 2017Updated 9 years ago
- ICME2022 Special Session “Beyond Accuracy: Responsible, Responsive, and Robust Multimedia Retrieval ”☆12Jun 3, 2024Updated 2 years ago
- [CVPR 2022] DiSparse: Disentangled Sparsification for Multitask Model Compression☆14Sep 6, 2022Updated 3 years ago
- Two-phase Scheme for Trimming QTMT CU Partition using Multi-branch Convolutional Neural Networks☆16Jul 4, 2021Updated 4 years ago
- Code for our WACV 2021 paper "Exploiting the Redundancy in Convolutional Filters for Parameter Reduction"☆11Jan 6, 2021Updated 5 years ago
- codes for Neural Architecture Ranker and detailed cell information datasets based on NAS-Bench series☆12Jul 11, 2022Updated 3 years ago
- codes for ICML2021 paper iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients☆10May 27, 2021Updated 5 years ago
- Official code repository for the paper "Rethinking Model Prototyping through the MedMNIST+ Dataset Collection" @ Scientific Reports☆13Mar 5, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Code for Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot☆43Nov 8, 2020Updated 5 years ago
- ☆13Aug 9, 2022Updated 3 years ago
- Libraries for efficient and scalable group-structured dataset pipelines.☆25Jun 18, 2025Updated last year
- Advancing Medical Image Segmentation Through Multi-Task and Multi-Scale Contrastive Knowledge Distillation☆20Jun 13, 2024Updated 2 years ago
- ☆17Aug 7, 2023Updated 2 years ago
- Official implementation for paper "Relational Surrogate Loss Learning", ICLR 2022☆37Nov 25, 2022Updated 3 years ago
- Code for ICML 2022 paper "SPDY: Accurate Pruning with Speedup Guarantees"☆20May 3, 2023Updated 3 years ago
- my personal blog(https://lucifer.ren/blog/)☆10May 22, 2026Updated last month
- 使用STM32F103RCT6和合宙的Air724UG 4G模块做的一个户外光照传感器，并将秒级间隔的光照数据传输至OneNet云端☆16Oct 10, 2023Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- "Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics" by Wuyang Chen, Xinyu Gong, Yu…☆27Aug 20, 2023Updated 2 years ago
- ICML2019 Accepted Paper. Overcoming Multi-Model Forgetting☆14Jun 5, 2019Updated 7 years ago
- 国内外数据竞赛资讯整理☆18Nov 6, 2021Updated 4 years ago
- SuperCollider classes for communicating with Open Brain Computer Interface☆12Jan 16, 2024Updated 2 years ago
- Official implementation for "Knowledge Distillation with Refined Logits".☆23Aug 26, 2024Updated last year
- model compression and optimization for deployment for Pytorch, including knowledge distillation, quantization and pruning.(知识蒸馏，量化，剪枝)☆21Sep 10, 2024Updated last year
- Code for RepNAS☆14Dec 21, 2021Updated 4 years ago
- Platform Forus is an Open SaaS solution that facilitates the management and issuance of social benefits, offering a collaborative platfor…☆10Updated this week
- [ICML2025] KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference☆29Jan 27, 2026Updated 5 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- This repository contains the code of the paper Multi-class classification of brain tumor types from MR Images using EfficientNets☆14Aug 22, 2025Updated 10 months ago
- Benchmarking Attention Mechanism in Vision Transformers.☆20Oct 10, 2022Updated 3 years ago
- This repository contains the publishable code for CVPR 2021 paper TransNAS-Bench-101: Improving Transferrability and Generalizability of …☆25Apr 11, 2023Updated 3 years ago
- [ICLR'22] PyTorch code for our paper "Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning"☆29Feb 18, 2023Updated 3 years ago
- PyTorch implementation for OD-cheap-convolution.☆20Sep 29, 2019Updated 6 years ago
- The official project website of "NORM: Knowledge Distillation via N-to-One Representation Matching" (The paper of NORM is published in IC…☆20Sep 18, 2023Updated 2 years ago
- A generic code base for neural network pruning, especially for pruning at initialization.☆32Sep 3, 2022Updated 3 years ago