Adaptive Convolutions with Per-pixel Dynamic Filter Atom

pytorch structural similarity (SSIM) loss

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系[email protected] 版权所有，违权必究 Tan 2018.06

Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)

Pytorch based Crowd-Counting model to estimate the number of people in crowdy areas such as Stadium, Music festival etc.

The implementation of Context-Aware Crowd Counting(CVPR2019)

The simple implemention of CSRNet.