转移时可以朴素地O(1)O(1)转移,注意j≡1( mod m)j≡1(modm)时可以从fi−1fi−1的任意一个kk转过来,于是需要在 DP 的同时维护一下和以防复杂度退化。 回到G2,考虑上文的状态就已经是三次方,首先要优化这个东西。这一步是容易的,因为fifi仅有fi−1fi−1而来,滚动数组即可。 接...
(it's a beast). It'd be nice if the models didn't take two to three days to train on a 1080TI as well (typical of GANs, unfortunately). In the meantime though this is going to be my baby and I'll be actively updating and improving the code over the forseeable future. I'll ...
Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise Learning CVPR code 39 Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam ICML code 38 BlockDrop: Dynamic Inference Paths in Residual Networks CVPR code 38 Weakly-Supervised Semantic Segmentation...