nihui
/
ncnn
Not watched
1
0
Fork 0
Code
Releases 46 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
685 Commits
5 Branches
354 MB
1 Download
Tree: a3a2548aa2
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'a3a2548aa2'
${ noResults }
Commit Graph

685 Commits (a3a2548aa28a9ff7924f76d5085fabe94de79ddb)
 

Author SHA1 Message Date
  Hyungsuk Yoon 2f16642f9f bug fix for conv1x1s2 on ARMv8 neon 8 years ago
  Hyungsuk Yoon c641db8034 Fix bug for convolution on x86 8 years ago
  nihuini f8dc80f756 generate layer type enum file 8 years ago
  Hyungsuk Yoon 574b010ca4 Rename mismatched signatures 8 years ago
  nihuini ba6026d853 fix valid padding pooling, fix #121 8 years ago
  nihuini f57018d337 convert Pad 8 years ago
  nihuini da8ff91cb0 fix padding load param 8 years ago
  nihuini b064d3cc9e add padding layer 8 years ago
  tedder59 a26914d6c8 注册用户网络层小bug 8 years ago
  nihuini 195193f919 fix reshape dim order, first try 8 years ago
  nihuini 04cd833cae convert Maximum 8 years ago
  nihuini 92eef2bbc4 write Identity const, write scalar const 8 years ago
  nihuini 776c1ff471 convert Floor, use c++98 map erase 8 years ago
  nihuini eb2ad9b7f8 Merge branch 'master' of https://github.com/Tencent/ncnn 8 years ago
  nihuini 7914a8ad21 binaryop with scalar const 8 years ago
  vicwer 1b0a3d2600 Update relu.cpp 8 years ago
  Hyungsuk Yoon 36e6219770 minor bug fix 8 years ago
  nihuini a203e3bac3 convert Identity-Const to MemoryData, handle all consts before binaryop, fix #119 8 years ago
  nihuini 55822398a5 unary_op_xxx 8 years ago
  nihuini 091a43676a implement binaryop and unaryop with operator template, binaryop between blobs with different dims 8 years ago
  nihuini 91f3281a1d enable memorydata by default 8 years ago
  nihuini 640242ceda memorydata is zero-to-one type layer 8 years ago
  nihuini b3b3b42326 fix BinaryOp add type 8 years ago
  nihuini c0b1ae6e2b convert Const as MemoryData, used as one of BinaryOp input 8 years ago
  nihuini 59d34e6a9c model data may not be 128bit aligned, copy data anyway 8 years ago
  nihuini a6d24fdc79 implement memorydata as general const blob producer 8 years ago
  nihuini 47218db6e5 fix minus padding SAME, fix #116 8 years ago
  gzygzy9211 c85c4df44c wing fix vs std::min std::max compile problem 8 years ago
  nihuini 45b2e7cd57 fix #110 8 years ago
  nihuini a638cf632e convert ELU parameter, fix #109 8 years ago
  nihuini cccacc7957 fix build 8 years ago
  nihuini 1464b9f6ea convert concat concatv2, axis not supported 8 years ago
  nihuini 94025f1ad3 convert reduce max and reduce sum 8 years ago
  nihuini 70eaf0b9b1 name changes 8 years ago
  nihuini ac819d06a4 more reduce dim, wip ... 8 years ago
  nihuini 152f300129 reduction max min 8 years ago
  nihuini ca4af98948 convert LRN 8 years ago
  nihuini 0edd2b78c5 arm neon optimize for bilinear_resize, about 40% faster 8 years ago
  nihuini 613028aa17 implement Mat resize_bilinear 8 years ago
  nihuini 7830b3da42 fix potential overread when bias_term is zero 8 years ago
  nihuini b4e3615ee4 depth-wise optimize 8 years ago
  nihuini 934f48cb5e arm neon optimize for group convolution 8 years ago
  nihuini ac76e4ba02 include algorithm for std::max 8 years ago
  nihuini aefb9830fc space fix 8 years ago
  nihuini 9f51c21322 implement depth-wise convolution 8 years ago
  nihuini 6de9b4f8ce fix #95 8 years ago
  nihuini 0b508266f6 update android.toolchain.cmake 8 years ago
  nihuini a93e26d983 more ops ... 8 years ago
  nihuini fcdf37387d fix convolution 4x4s4 and 5x5s1 8 years ago
  nihuini 3c23873704 use binaryop 8 years ago