nihui
/
ncnn
Not watched
1
0
Fork 0
Code
Releases 46 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
369 Commits
5 Branches
354 MB
2 Download
Tree: d2416187dc
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'd2416187dc'
${ noResults }
Commit Graph

214 Commits (d2416187dc16ef3de501ca954ad9f937abc4f2ae)

Author SHA1 Message Date
  kyuusaku d2416187dc fix parameter check for interp (#425) 8 years ago
  nihuini 90643630c2 apple a10/a11 is armv8.2-a 8 years ago
  nihuini 50e1f0e531 const for to_pixels family 8 years ago
  nihuini ce74836e2a yet another winograd convolution implementation, unroll outch 8 tiles 4 inch 4, about 22% faster, more optimization may comes soon :> 8 years ago
  nihui 30b6cc4ecd rdiv binaryop 8 years ago
  nihui 2f90a794ad rsub binaryop 8 years ago
  nihuini a341e7465c reject to load model with empty network, fix #392 8 years ago
  nihuini 356d018771 implement Clip and converter support 8 years ago
  Hyungsuk Yoon 8f56e00b4b make convolution with dilation fast 8 years ago
  nihuini d7c179f39d armv7 assembly implementation for winograd input output transform, compiler is childish 8 years ago
  nihuini 3a27cb715f skip background class in gathering 8 years ago
  nihui 182e92a331 Update benchmark.cpp 8 years ago
  nihui bc1a84dee5 fix mingw32 build 8 years ago
  Hyungsuk Yoon 354f515596 scanf with width specifier need (width + 1) spaces 8 years ago
  Yantao Xie 89c7aa26f8 support the scientific notation when parsing layer's paramters. 8 years ago
  nihui d0bcda70ca arm neon optimize for winograd input output transform, about 4%~22% faster 8 years ago
  nihui c656c572ad use float type for input transform 8 years ago
  nihuini 4f79b89635 comment for reshape flag 8 years ago
  nihuini aee6552360 memcpy is fast :) 8 years ago
  nihui 2abeb038a0 unroll outch for conv3x3s2, about 30% faster :) 8 years ago
  nihui 97025668a9 unroll conv1x1s1 outch 6 inch 4 on armv7, about 2%~18% faster 8 years ago
  nihuini dd0ae756de batchnorm and scale on vector and image, fix #331 8 years ago
  AlanNewImage e77eef3f3d Update priorbox.cpp (#330) 8 years ago
  Yantao Xie cd3617b11d Set ArgMax's one_blob_only as true. (#325) 8 years ago
  Joe 9748c00b44 add image-level feature support (#320) 8 years ago
  Tiancai Ye 3977d32eb9 Fix windows build fails (#321) 8 years ago
  Yantao Xie 73340578c8 Remove the destructor definition from the lstm layer. (#319) 8 years ago
  nihuini e4c1ddbc45 rewrite inner loop in assembly, since gcc is sometimes foolish qaq, fix #312 8 years ago
  nihuini aac70893f8 fix build on gcc 8 years ago
  nihuini 394bca8dbb Merge branch 'master' of https://github.com/Tencent/ncnn 8 years ago
  nihuini 9ac305e160 create 3-dim sub blob for group convolution, fix #315 8 years ago
  Howave 415bfbdfa7 added arm layer compilation for arm-linux system (#316) 8 years ago
  nihuini 318d3abe66 bind register explicitly, fix #306, fix #310, fix #312 8 years ago
  Yantao Xie 2e9da1b95b Add the epsilon parameter to the BatchNorm layer. (fix #303) (#311) 8 years ago
  nihuini 231a52e469 fix build on aarch64 with gcc, fix #309 8 years ago
  BUG1989 af7019d3fc fix compile error (#305) 8 years ago
  nihui 875a188d10 pre interleave kernel memory for winograd4, about 3%~20% speed gains 8 years ago
  dong 6ea09ebf2c Use aarch64 assembly to replace arm intrinsics 8 years ago
  820169199 656de48631 add "#include <float.h>" 8 years ago
  Dong Xu 28154dcb29 fix vst1.f32 of coeff sum at eltwise_arm layer 8 years ago
  nihui 0fd701112e load LRN bias from param 8 years ago
  nihui 7d1e49584d call Innerproduct for convolution on flattened blob 8 years ago
  harhar539 9a8486a823 1.fix pad tail bug in commit d1ea2a3 at pooling layer 8 years ago
  nihui b1aec69ff9 d31 is useless 8 years ago
  nihuini 5e484a47ef fix build, second try 8 years ago
  nihui 5f0fa95f61
fix build 8 years ago
  nihui d1ea2a34b4 rewrite pooling pad scheme, global pooling return continous blob 8 years ago
  nihui 6c4c810fda decouple modelbin of different input types, simplify timestamp function 8 years ago
  nihui 2d4ae30508 fallback to all cores 8 years ago
  nihui 03c1f63c2e switch to winograd4 8 years ago