aramachandran2000 Goto Github PK

mindmappings

A reference implementation of the Mind Mappings Framework.

ml_segmentation

Machine learning semantic segmentation - Random Forest, SVM, GBC

mranet

Semantic Segmentation of remotely sensed images for post disaster assessment

pdpu

PDPU: An Open-Source Posit Dot-Product Unit for Deep Learning Applications

posit-fmau

A multiple-precision vectorized fused multiply accumulate arithmetic unit for posit

posit-hls

Generating Posit-Based Accelerators With High-Level Synthesis

pruning-vs-quantization

psaq-vit

[ECCV 2022] Patch Similarity Aware Data-Free Quantization for Vision Transformers

pysigmoid

A Python Implementation of Posits and Quires (Drop-in replacement for IEEE Floats)

qpytorch

Low Precision Arithmetic Simulation in PyTorch - extension for posit and beyond

resource-efficient-neural-networks-using-hessian-based-pruning

HAP is an advanced structured pruning library written for PyTorch. HAP prunes channels based on their second-order sensitivity. Channels are sorted based on this metric, and only insensitive channels are pruned.

semantic-segmentation-cityscapes

Using Fully Convolutional Networks for semantic segmentation on Cityscapes dataset

smallposithdl

sparq

Post-training sparsity-aware quantization

spqr

squant

SQuant [ICLR22]

squeezellm

SqueezeLLM: Dense-and-Sparse Quantization

ssql-eccv2022

PyTorch implementation of SSQL (Accepted to ECCV2022 oral presentation)

svite

[NeurIPS'21] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

targeted-supcon

A PyTorch implementation of the paper Targeted Supervised Contrastive Learning for Long-tailed Recognition

tcbnn

torch-pruning

[CVPR 2023] Towards Any Structural Pruning; LLMs / Diffusion / Transformers / YOLOv8 / CNNs

universal-hw

QA test suites for universal arithmetic hardware design

vision_processor

A co-processor for acceleration of image processing applications

wanda

A simple and effective LLM pruning approach.