nihui
/
ncnn
Not watched
1
0
Fork 0
Code
Releases 46 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
176 Commits
5 Branches
354 MB
2 Download
Tree: 32cd5f2a5c
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '32cd5f2a5c'
${ noResults }
Commit Graph

102 Commits (32cd5f2a5c50e55a9ef1709b0d527a202fac64b2)

Author SHA1 Message Date
  nihui 32cd5f2a5c use mul for the first multiply, drop accumulator clear instructions, about 5% speed performance gains 8 years ago
  nihuini d5da0e84ba fix deconv4x4s2, fix #202 8 years ago
  wind19870521 429e98c91c fix unaryop bug (#200) 8 years ago
  huyn 8b9365a68c fix top_blob not set (#199) 8 years ago
  azrael0fog f232c1a6c5 Update relu_arm.cpp (#189) 8 years ago
  tedder59 4d59d0afda Add depthwise Deconvolution. (#187) 8 years ago
  nihui 790829bc62 partition dot tiles and reuse kernel register, over 20% improvement for tiny image 8 years ago
  nihuini a3be17eb7e special path for 1x1xc innerproduct 8 years ago
  nihuini 50d591cb50 softmax inplace 8 years ago
  peng 39445b5233 no memcpy for small size copy_cut_border/copy_make_boder 8 years ago
  彭 a86cc8f620 memcpy optimize copy_cut_border/copy_make_boder (#179) 8 years ago
  nihuini d99f9d9ac3 implement softmax on vector and image 8 years ago
  liuchang ac3b4768aa fix the missing header file for visual studio. 8 years ago
  nihuini ff3c03cfb1 q9 is useless 8 years ago
  nihuini 8cfd02d633 Merge branch 'master' of https://github.com/Tencent/ncnn 8 years ago
  nihuini 9a55404c72 fix dot on aarch64, still needs improvement ... 8 years ago
  nihui eea3ca577a disable winograd atm ... 8 years ago
  nihui 0385d8e8ad implement winograd64 optimization for convolution 3x3s1 8 years ago
  nihui 20b1330cdb fix lrn within channel 8 years ago
  nihui 8e490d4b68 fix array parsing, first try 8 years ago
  nihui 908a8f48d2 assign same size 8 years ago
  nihui 4fabb4c274 more encapsulation for paramdict 8 years ago
  nihui d6c833a715 scale_data is vec 8 years ago
  nihui fe21cdb525 fix build 8 years ago
  nihui 91c08a390a merge concatv2 dropoutv2 softmaxv2 8 years ago
  nihui 1e2265dd99 new param load api 8 years ago
  nihui 2a8d811a13 introduce dropoutv2 for scale param 8 years ago
  nihui d3f95ab18c fix roipooling 8 years ago
  nihui 39bce09617 implement proposal and roipooling 8 years ago
  nihui 75e175ef48 some trival fix 8 years ago
  lzx1413 7fdda5c7c8 add interp layer support nearest and bilinear 8 years ago
  nihui ecc5fe345a fix lrn within channel, second try 8 years ago
  nihui 3e8a5ba264 fix lrn within channel 8 years ago
  nihui e4e6f6dc3f fix num_aspect_ratio zero case 8 years ago
  nihui 46e7d43d3e fix num_max_size zero condition, fix qsort on empty list 8 years ago
  nihui 19aad1fb13 implement DetectionOutput, top blob is sorted 8 years ago
  nihui 967042f382 introduce SoftmaxV2 for axis param 8 years ago
  nihui 6a8969acb7 rename dim to axis 8 years ago
  nihui 78400d17da implement ssd Normalize Permute PriorBox, introduce ConcatV2 for interleave 8 years ago
  nihui c7a4950096 concat image 8 years ago
  nihui 87bad3420e improve custom layer register 8 years ago
  nihuini a36af39040 improve cpu max frequency detection, fix #146 8 years ago
  nihuini 6a7cf6ee20 ncnn prefer w h c :P 8 years ago
  nihuini f794adeb28 implement expanddims, always copy when param is not appliable 8 years ago
  nihuini fd257c1ec6 squeeze dim option 8 years ago
  nihuini 1befe51f92 implement squeeze, enable reduction 8 years ago
  nihuini 7f2adcd67e rename as PROD 8 years ago
  nihuini 1a29d57ebb implement unaryop reciprocal 8 years ago
  nihuini e231d3e9d6 implement reduction multiply 8 years ago
  nihuini 21d96f4cd9 implement reduction with operator template 8 years ago