amirgholami

PyHessian

PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

ZeroQ

[CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework

adahessian

ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning

ai_and_memory_wall

AI and Memory Wall

SqueezeNext

anode

[IJCAI'19, NeurIPS'19] Anode: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs

HessianFlow

accfft

A Massively Parallel FFT Library for CPU/GPU

TRAttack

[CVPR'19] Trust Region Based Adversarial Attack

2019_visual_wake_words_challenge

ada-hessian

Easy-to-use AdaHessian optimizer (PyTorch)

inplace

CUDA and OpenMP implementations of C2R/R2C inplace transposition

parallel_tf

pytorch-optimizer

torch-optimizer -- collection of optimizers for Pytorch

QPyTorch

Low Precision Arithmetic Simulation in PyTorch

caffe

Caffe: a fast open framework for deep learning.

caffe-1

This fork of BVLC/Caffe is dedicated to improving performance of this deep learning framework when running on CPU, in particular Intel® Xeon processors (HSW+) and Intel® Xeon Phi processors

clFFT

a software library containing FFT functions written in OpenCL

convnet-burden

Memory consumption and FLOP count estimates for convnets

DCP

Code for “Discrimination-aware-Channel-Pruning-for-Deep-Neural-Networks”

pvfmm

pywin32doc

talon

torchdiffeq

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.