nihui
/
ncnn
Not watched
1
0
Fork 0
Code
Releases 46 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
1518 Commits
5 Branches
354 MB
2 Download
Tree: bedf00a5ed
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'bedf00a5ed'
${ noResults }
Commit Graph

982 Commits (bedf00a5edf85ae8af33bc72ebd85fe325da1271)

Author SHA1 Message Date
  nihui 1e4eaeeacd optimize interleave section for load first, about 5%~10% speed gain 8 years ago
  nihui 6895cbf810 single vldm is faster than two vld1 on armv7, and some pipeline optimize 8 years ago
  nihuini 05d7562a5d reorder kernel weight, pipeline friendly ;) 8 years ago
  nihui b8f4f024a4 implement reorg yolodetectionoutput layer from caffe-yolov2 8 years ago
  nihuini ee98817446 proper first row/col handling in resize family, fix #429 8 years ago
  nihuini 511baa6718 optional image pixel api, fix #434 8 years ago
  nihuini 2368d29a1e more explicit alignment on armv7 8 years ago
  nihuini d172a34329 direct assembly port, enable convolution 1x1 sgemm on armv7 8 years ago
  nihuini b3e24cafc3 openmp++ 8 years ago
  nihuini 0fdb8da60e sgemm convolution 1x1 wip, about 20%~75% faster on aarch64, while armv7 compiler is foolish qaq 8 years ago
  nihuini 2b20bf940c drop armv7 vaddvq_f32 hack 8 years ago
  nihui 72bb261e7a switch to winograd5 8 years ago
  nihuini a234e9240d fix concat on height 8 years ago
  nihuini 003873c55b crop on channel and crop by param 8 years ago
  Chang, Hui-Tang dc2a689d10 fix proposal roi_score_blob bug (#430) 8 years ago
  nihuini 99a343ce70 allocate after permute, reduce peak memory usage 8 years ago
  nihuini 0ce0c11851 load sub-op in advance for group convolution 8 years ago
  nihuini 86f4264c7c arm neon assembly for winograd5 8 years ago
  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