nihui
/
ncnn
Not watched
1
0
Fork 0
Code
Releases 46 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
2022 Commits
5 Branches
354 MB
2 Download
Tree: d6b2ea5aac
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'd6b2ea5aac'
${ noResults }
Commit Graph

2022 Commits (d6b2ea5aacee36141bf4597d8d68a2aafe472559)
 

Author SHA1 Message Date
  nihuini d6b2ea5aac arm neon optimization for convolution 3x3 on small channels 5 years ago
  nihuini 6a397716ca arm neon optimization for instancenorm 5 years ago
  nihuini d095149f59 workaround mxnet op non-unique name issue, fix #2855 5 years ago
  nihuini 687cc857b1 some x86 sse2 optimization for convolution int8 5 years ago
  zhiliu6 ec0f904c16
improve x86 1x1 pack8 convolution performance (#2852) 5 years ago
  seiyaa 478b8f072e
update faq.md - bind to big/little cores (#2851) 5 years ago
  ncnnnnn 4e51d01d78
Update faq.md (#2850) 5 years ago
  791136190 15537ea086
Update faq.md (#2847) 5 years ago
  nihui 3f6d054b8a update test-coverage codecov version 5 years ago
  nihuini 68468dccbd arm neon assembly optimization for padding int8 pack8, convolution int8 out elempack 4 5 years ago
  Evgeny Proydakov ef97e4eab0
Fixed TYPO in README.md. Removed extra space in 'C ++' language name. (#2849) 5 years ago
  nihuini 79927a9eeb update quantized int8 inference doc 5 years ago
  ncnnnnn 3a002add1c
Update faq.md (#2843) 5 years ago
  DC Technology 817058d9ca
Update faq.md (#2842) 5 years ago
  nihuini 31d436c627 more verbose load failure, ncnn2int8 write int8 data properly 5 years ago
  nihuini 56d74580a0 fix uninitialized input and weight 5 years ago
  nihuini 05d457c78f innerproduct int8 support all fused activation types 5 years ago
  nihuini 1bc0126302 fix crash when input cpu blob and extract the same from gpu, update vgg16 int8 model 5 years ago
  nihuini 97903bbe85 fix alerts 5 years ago
  nihuini 2b1f8bea25 fix float locale issue in ncnn2mem, fix long line parsing in ncnn2int8 5 years ago
  nihui 7e1aaa5828
cmake option NCNN_INT8 (#2839) 5 years ago
  nihui 66455c1b95
implement 2823 binary broadcasting type (#2827) 5 years ago
  nihuini 85efe132ff unroll inch 4 for convolution sgemm int8 5 years ago
  wblksheep bd994ddba3
Update faq.md (#2835) 5 years ago
  weida wang b5eef88aba
Update faq.md (#2834) 5 years ago
  runrunrun1994 2879b23382
更新faq (#2833) 5 years ago
  weida wang dd8438558a
Update efficient-roi-resize-rotate.md (#2832) 5 years ago
  runrunrun1994 895ae1f8b4
更新faq文档 (#2831) 5 years ago
  nihui 81f051e372
Update .travis.yml 5 years ago
  Zhuo Zhang 6c5e122266
update faq doc by mention dev tools (#2830) 5 years ago
  weida wang f9dd137a03
Update faq.md (#2829) 5 years ago
  nihui a546ac034a do not trigger ci on docs changes only and restyled bot commits 5 years ago
  nihui 9c744d0109 add faq.md 5 years ago
  nihui c6cd5e8628 fix armv7 no-neon build 5 years ago
  nihuini e38a5fcbe6 fix build 5 years ago
  nihuini 01f5dcb700 arm neon optimization for convolution sgemm pack1 pack8to1 int8 5 years ago
  zhiliu6 c4700c52ca
optimize x86 1x1 pack8 convolution (#2820) 5 years ago
  nihui 0d1d5b66c5 fix arm64 asm build 5 years ago
  nihuini e9ab1acf27 arm neon optimization for convolution sgemm pack1to8 int8 5 years ago
  nihuini e975de1f36 better condition for arm82 conv3x3s1 winograd 5 years ago
  nihuini 41a4bea954 unroll size 8 for conv3x3s1 pack8to1 int8 arm64 5 years ago
  nihuini 3631c1933d non-inlined addref and release slows down overall speed, move them to header 5 years ago
  nihui e9cc637573
arm neon optimization for int8 packing kernels (#2809) 5 years ago
  nihui d7cbc055f3
fix illegal instruction on pi4 when NCNN_ARM82 enabled 5 years ago
  teng cc8e7a13fa
Update operation-param-weight-table (#2811) 5 years ago
  DC Technology 86e53b35db
add Apple M1 benchmark (#2810) 5 years ago
  nihuini 256754bff9 fix build with old gcc, fix #2805 5 years ago
  teng a90a31d340
doc spelling mistakes (#2804) 5 years ago
  zhiliu6 61cd9da55b
optimize x86 3x3 pack8 leftover (#2797) 5 years ago
  nihuini 912e81d086 fix tanh neon, fix #2751 5 years ago