首页/数据集/Data_pruned_unpruned_VGGish_DCASE21_Net_VGG-16

Data_pruned_unpruned_VGGish_DCASE21_Net_VGG-16

NIAID Data Ecosystem2026-05-01 收录

音频场景分类

神经网络剪枝

数据链接：

https://zenodo.org/record/7119929 数据链接链接失效反馈

官方服务：

资源简介：

Data, Pruned and unpruned networks: VGGish_DCASE21_Net_VGG-16.

应用场景：

创建时间：

2023-03-30

环境声音识别

音频场景分类

This raw dataset presents the data related to the gym, and classroom environments captured with the data acquired from microphone available in off-the-shelf mobile devices.

NIAID Data Ecosystem80

TAU Urban Acoustic Scenes 2019, Development dataset

城市声学场景

音频场景分类

TAU Urban Acoustic Scenes 2019 development dataset consists of 10-seconds audio segments from 10 acoustic scenes: Airport - airport Indoor shopping mall - shopping_mall Metro station

Zenodo2019-03-11 更新50

DCASE2020_v3

声事件检测

音频场景分类

DCASE2020 pretrained weights v3

NIAID Data Ecosystem30

Pre-trained neural network model for pruning example code

神经网络剪枝

模型压缩

Pre-trained neural network models for example codes of neural network pruning. Example pruning codes are published in "https://github.com/FujitsuResearch/automatic_pruning".

Zenodo2022-01-25 更新70

Number of remaining parameters in networks pruned to 93% sparsity.

神经网络剪枝

模型压缩

This table gives the average number of remaining weights in each layer of the networks pruned to 93% sparsity. The variance on the number of connections, as well as the fraction of remaining connectio

Figshare2022-09-27 更新40

Data_pruned_unpruned_VGGish_DCASE21_Net_VGG-16

资源简介：

相关数据集