ZeroQ:[CVPR'20] ZeroQ 源码
ZeroQ:一种新颖的零射击量化框架 介绍 该存储库包含CVPR 2020论文的PyTorch实现。以下是复制分类结果的说明。请参阅以获取再现对象检测结果的说明。 您可以找到有关ZeroQ的简短视频说明。 TLDR; # Code is based on PyTorch 1.2 (Cuda10). Other dependancies could be installed as follows: cd classification pip install -r requirements.txt --user # Set a symbolic link to ImageNet validation data (used only to evaluate model) mkdir data ln -s /path/to/imagenet/ data/ 文件夹结构应与以下相同 zeroq
文件列表
ZeroQ:[CVPR'20] ZeroQ
(预估有个493文件)
sigmoid_focal_loss.cpp
2KB
masked_conv2d_cuda.cpp
3KB
nms_cpu.cpp
7KB
nms_cuda.cpp
576B
grid_sampler_cuda.cu
32KB
grid_sampler_cudnn.cpp
4KB
grid_sampler.cpp
3KB
grid_sampler_cpu.cpp
35KB
roi_pool_cuda.cpp
3KB
affine_grid_cuda.cpp
5KB
暂无评论