human-analysis/neural-architecture-transfer

Stars
150
Rank 247,323 (Top 5 %)
Language
Python
Created over 4 years ago
Updated over 4 years ago

human-analysis/neural-architecture-transfer

human-analysis

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Neural Architecture Transfer (Arxiv'20), PyTorch Implementation

Neural Architecture Transfer

Code accompanying the paper.

Neural Architecture Transfer

Zhichao Lu, Gautam Sreekumar, Erik Goodman, Wolfgang Banzhaf, Kalyanmoy Deb, and Vishnu Boddeti

arXiv:2005.05859

Requirements

Python >= 3.7.x, PyTorch >= 1.4.0, timm >= 0.1.18

ImageNet Classification

python evaluator.py --data /path/to/dataset --model subnets/imagenet/NAT-{M1,M2,M3,M4}/net.config

Architecture Transfer

python evaluator.py \
  --data /path/to/dataset \
  --dataset {aircraft,cars,cifar10,cifar100,cinic10,dtd,flowers102,food101,pets,stl10} \
  --model subnets/{dataset}/net-img@{xxx}-flops@{xxx}-top1@{xx.x}/net.config

Scalability to Objectives

Tri-Objective

12-Objective

Architecture Visualization

Acknowledgement

Codes are modified from OnceForAll and pytorch-image-models

MUXConv

MUXConv: Information Multiplexing in Convolutional Neural Networks (CVPR '20), Pytorch Implementation

pytorchnet

Generalized Framework for PyTorch

secure-face-matching

MaxEnt-ARL

PyTorch Implementation of CVPR'19 (oral) - Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach

intrinsic-dimensionality

PyTorch Implementation of CVPR'19 - On the Intrinsic Dimensionality of Image Representation

causal-relations-between-representations

diverse3dface

RankGAN

RankGAN: A Maximum Margin Ranking GAN for Generating Faces

LBCNN

Local Binary Convolutional Neural Networks

3dfacefill

Repository for 3DFaceFill: An Analysis-by-Synthesis Approach for Face Completion

hers-encrypted-image-search

HERS: Homomorphically Encrypted Representation Search

encrypted-biometric-fusion

kernel-adversarial-representation-learning

On the Global Optima of Kernelized Adversarial Representation Learning (ICCV'19), PyTorch Implementation

AutoFHE

Official implementation for AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE. The paper is presented at the 33rd USENIX Security Symposium, 2024.

nsganetv1

neural-structural-identification

capacity-generative-face-models

Repository for the paper titled "On the Biometric Capacity of Generative Face Models"

Jupyter Notebook

tensorflownet

moea-nas-framework