GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
reparameterizationHere are 18 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库
pytorch pruning quantization tensorrt model-compression qat onnx reparameterization tensorrt-conversion quantization-aware-training acnet
Stochastic Automatic Differentiation library for PyTorch.
pytorch reparameterization gradient-estimators stochastic-deep-learning stochastic-computation-graphs
[MICCAI'23] Official implementation of "RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection".
deep-neural-networks computer-vision deep-learning yolo convolutional-neural-networks object-detection medical-image-computing medical-image-processing medical-image-analysis shufflenet panet vovnet brain-tumor-detection reparameterization medical-image-dataset repvgg-model medical-image-detection br35h-brain-tumor-detection-2020 repconv-model
[TMC 2025/NOSSDAV 2023] Official code for RepCaM++ and RepCaM: Re-parameterization Content-aware Modulation for Neural Video Delivery
DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-Resolution (TMM 2023)
Spectral Tensor Train Parameterization of Deep Learning Layers
compression reproducible-research pytorch tensor reproducibility svd sttp householder aistats tensortrain reparameterization orthogonality stability-training svdp
Official code for Differentiable Rendering with Reparameterized Volume Sampling (AISTATS 2024)
computer-vision monte-carlo nerf 3d-reconstruction reparameterization neural-rendering neural-radiance-fields
T-Basis: a Compact Representation for Neural Networks
compression reproducible-research pytorch tensor reproducibility tensor-decomposition icml weight-sharing tensor-ring reparameterization
Python library for the differentiable hypergeometric distribution
Code for paper: Weight-Inherited Distillation for Task-Agnostic BERT Compression
[BMVC 2022] Wide Feature Projection with Fast and Memory-Economic Attention for Efficient Image Super-Resolution
Differentiable reparameterization of matrices with orthogonal columns.
This repository contains scripts to reparamterize the YOLOv7 model and it's variants. This can help in deployment and further usage.
Charon's weight transforms W = T(raw), taken into neural networks. Same starting network, different route: with plenty of data no transform helps; with few samples and noisy inputs, the power transforms win on 10/10 tasks.
VisionicAI: Ultra-lightweight object detection model optimized for NPU. 1인 주도로 아키텍처 설계 및 학습 파이프라인 전 과정 개발.
An unofficial implementation of sigma reparam [Zhai et al. 2023]
Project page for PHFD-Net, a locally re-parameterized hierarchical spatial-frequency network for single image dehazing (under review at IEEE TCSVT).
What a parameter transform T(w) does to gradient descent: an E=mc²-inspired idea, tested. Every transform is a position-dependent learning rate plus a range; the route changes, the destination doesn't, except when the problem is underdetermined.
Add this topic to your repoTo associate your repository with the reparameterization topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |