Dual Attention Network for Scene Segmentation

场景分割的对偶注意力网络.

Pytorch构建自己的数据集

Build my Dataset in Pytorch.

Generating Diverse High-Fidelity Images with VQ-VAE-2

VQ-VAE-2：改进VQ-VAE生成高保真度图像.

Neural Discrete Representation Learning

VQ-VAE：向量量化的变分自编码器.

Fixup Initialization: Residual Learning Without Normalization

Fixup初始化: 没有归一化的残差学习.

CCNet: Criss-Cross Attention for Semantic Segmentation

CCNet：语义分割中的交叉注意力机制.