DiffEnc-8-nt trained on CIFAR-10
收藏DataCite Commons2024-04-22 更新2024-07-13 收录
下载链接:
https://data.dtu.dk/articles/dataset/DiffEnc-8-nt_trained_on_CIFAR-10/25243063
下载链接
链接失效反馈官方服务:
资源简介:
Checkpoints for an image generation model trained on CIFAR-10.The model was made in Jax. See the github repository for code to load the checkpoints.The model is a variational diffusion model (VDM, https://arxiv.org/abs/2107.00630) with an added non-trainable time-dependent encoder trained for the article "DiffEnc: Variational Diffusion with a Learned Encoder" (https://arxiv.org/abs/2310.19789).The model uses v-parametrization for the loss. The diffusion model is of size 8 and the encoder is non-trainable. That is, the diffusion model uses 8 "down-blocks" in the U-net. See details in article.Random seeds: 1, 2, 13, 42, 70
本数据集包含在CIFAR-10数据集上训练得到的图像生成模型的权重检查点(checkpoint)。该模型基于JAX框架开发,如需获取加载该检查点的代码,请参阅对应GitHub仓库。
本模型为变分扩散模型(variational diffusion model, VDM,https://arxiv.org/abs/2107.00630),并为论文《DiffEnc:带学习编码器的变分扩散模型》(https://arxiv.org/abs/2310.19789)新增了一个不可训练的时变编码器。
该模型的损失函数采用v参数化(v-parametrization)。此扩散模型的U-Net结构包含8个下采样块(down-blocks),且编码器参数不可训练,相关细节可参阅上述论文。
本次实验使用的随机种子为:1、2、13、42、70。
提供机构:
Technical University of Denmark
创建时间:
2024-04-22



