ANB LGB Surrogate 0.9

Name: ANB LGB Surrogate 0.9
Creator: Ahmad, Afzal
Published: 2023-04-16T00:00:00+08:00

Figshare2023-04-16 更新2026-04-08 收录

神经网络架构

自动模型研究

数据链接：

https://figshare.com/articles/dataset/ANB_LGB_Surrogate_0_9/22592926/1 数据链接链接失效反馈

官方服务：

资源简介：

Accel-NASBench LGB accuracy surrogate.

提供机构：

Ahmad, Afzal

创建时间：

2023-04-16

carlosqsw/ONNX-Bench

神经网络架构

性能评估

ONNX-Bench是一个包含649,596个神经网络架构的大型基准数据集，这些架构采用统一的ONNX格式，并伴有性能标签。数据集跨越多个NAS搜索空间，支持在CIFAR-10上进行一致性评估，并具有丰富的架构多样性，包括基于单元和分层的架构。数据集经过预简化处理，适合用于性能预测、零样本迁移和通用代理模型训练。

Hugging Face2025-10-12 更新110

nasbench-x11-models-v0.5.zip

神经网络架构

代理模型

Surrogate models for darts, nasbench-101, and nasbench-nlp search space to output full training curves.

DataCite Commons2021-12-08 更新60

Configurations of the model architectures of VGGNet-16, ResNext-50 (32x4d), and Swin-B.

神经网络架构

计算机视觉模型

In the notation [kernel size × kernel size, channels;…] × N, N denotes the number of times a sequence of convolution layers is repeated, with each layer in the sequence defined by its kernel size and

NIAID Data Ecosystem30

Topology and tuned parameters of trained artificial neural networks.

神经网络架构

模型参数调优

Topology and tuned parameters of trained artificial neural networks.

NIAID Data Ecosystem100

Architecture selection results of the ANN model for different training sets with maximum three input nodes.

神经网络架构

模型选择

Architecture selection results of the ANN model for different training sets with maximum three input nodes.

NIAID Data Ecosystem40