CNN-Filter-DB

<strong>A diverse database of over 1.4B 3x3 convolution filters extracted from CNN models trained for various tasks in diverse image domains.</strong> We collected a total of 647 publicly available CNN models that have been pre-trained for various 2D visual tasks. In order to provide a heterogeneous and diverse representation of convolution filters "in the wild", we retrieved pre-trained models for 11 different tasks e.g. such as classification, segmentation} and image generation. We also recorded various meta-data such as depth and frequency of included operations for each model, and manually categorized the variety of used training sets into 16 visually distinctive groups like natural scenes, medical ct, seismic, or astronomy. In total, the models were trained on 71 different data sets. The dominant subset is formed by image classification models trained on ImageNet1k (355 models). <strong>More details:</strong> https://github.com/paulgavrikov/cnn-filter-db

本数据集为一个多样化数据库，包含从针对不同图像领域各类任务训练的卷积神经网络（Convolutional Neural Network, CNN）模型中提取的超14亿个3×3卷积滤波器（convolution filters）。本次共收集了647个公开可用的、针对各类二维视觉任务预训练的CNN模型。为了呈现“真实场景”下卷积滤波器的异质多样化分布，我们检索了覆盖11类不同任务的预训练模型，例如分类、分割以及图像生成任务。我们还记录了各类元数据（meta-data），包括每个模型的网络深度与所含操作的出现频次；同时将所用的全部训练集手动划分为16个视觉特征迥异的类别，例如自然场景、医学CT、地震数据以及天文数据等。总体而言，这些模型均基于71个不同的数据集进行训练，其中占比最高的子集为在ImageNet1k数据集上训练的图像分类模型，共计355个。<strong>更多详情：</strong> https://github.com/paulgavrikov/cnn-filter-db