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
  Yiheng 09fcf8701e Fix number of filters in ConvTranspose 7 years ago
  nihui 11113c7aaa
Update .travis.yml 7 years ago
  nihui eee2e573fe
Update .travis.yml 7 years ago
  nihui 177e389b68
Update .travis.yml 7 years ago
  nihui c33641c378
enable coverage 7 years ago
  nihui 6afcd2299f
enable ncnn coverage 7 years ago
  nihui e27363b9b7
Update CMakeLists.txt 7 years ago
  nihui fe2cb0f550
Update .travis.yml 7 years ago
  nihui b3edaf8728
Delete .coveralls.yml 7 years ago
  nihui 5753ace859
Update .coveralls.yml 7 years ago
  nihui 87fbe6d6ed
Create .coveralls.yml 7 years ago
  nihuini 4af3ec223b fix clip arm 7 years ago
  nihuini 4e68a29eff fix build on msvc, second try 7 years ago
  nihuini 4a9e452cb5 fix build on msvc, first try 7 years ago
  nihuini 9fbaf7fb0b coding style changes 7 years ago
  BUG1989 c171db255f update aarch64 conv1x1s1 int8, speedup 10%. 7 years ago
  BUG1989 08b39dffb0 add aarch64 int8 neon implement 7 years ago
  RogerOu add45371de fix warning: allocator non-virtual destructor 7 years ago
  RogerOu 0633973bfa clip layer support arm neon 7 years ago
  nihuini 8eeea9ef01 fix reduction dim 2, fix #593 7 years ago
  nihuini a7ddf49271 fix write out of range in permute order 4 7 years ago
  nihuini dada1982e9 Revert "fix warning:non-virtual destructor (#597)" 7 years ago
  RogerOu 80086c6a1d fix warning:non-virtual destructor (#597) 7 years ago
  xinyu391 666ec2820e add Net::load_param_mem(), ParamDict::load_param_mem() load plain text paramters from memory buf. (#587) 7 years ago
  BUG1989 3489d02037 fix the dequantize arm bug (#580) 7 years ago
  BUG1989 7d2d18d31f innerproduce layer with int8 impl,the type of top_blob shoud be integer. (#578) 7 years ago
  nihui a862a3432d aarch64 assembly for conv3x3s1, about 18% speed gain 7 years ago
  BUG1989 5f1e678e7f delete out.fill operate in the armv7 int8 convdw 7 years ago
  BUG1989 9b8e968139 add armv7 int8 convdw3x3 and conv3x3s2 left4 case 7 years ago
  nihuini ef36d79b7e implement the missing dequantize image on armv7, prefer neon-optimized 3-dim dequantize, fix #547 7 years ago
  nihuini 19ad4cf284 fix build without neon 7 years ago
  nihuini c4e3a9cc92 disable the wrong mnasnet benchmark :| 7 years ago
  BUG1989 09b0c72846 Update qcom820,rk3399,rk3288,hisi3519 benchmark (#551) 7 years ago
  nihui 49c956d874
update qcom410 i.mx7 dual benchmark 7 years ago
  nihui a1ce09324e
update qcom810 iphone5s benchmark 7 years ago
  nihuini 6e02923489 add some comment 7 years ago
  nihuini 9a19bd9a55 add mnasnet benchmark 7 years ago
  nihuini 23de61fd07 as we already have the int8_scale_term switch, do not have to rely on the actual scale value 7 years ago
  nihuini dda21b8ea9 convolution depthwise 3x3 stride 1 with unroll 8 on aarch64 7 years ago
  BUG1989 d5df2301cb fix the caffe2ncnn that "DepthwiseConvolution" loss group num param (#540) 7 years ago
  nihuini 9e491446ce NCNN_XADD returns int, though rarely used, fix #538 7 years ago
  nihuini 144f818f88 Mat fill int optimization 7 years ago
  nihuini 8526a69777 packed int8 convolution 3x3 stride 1 for armv7, 7%~25% faster than vanilla one, but God knows how hard I try :| 7 years ago
  nihuini a76a07eb3f fix null sub group elemsize/allocator in depthwise deconvolution, fix #539 7 years ago
  nihuini 6f1b0b0a61 quantized padding in convolution, use range sweets 7 years ago
  nihuini bf1c58be46 padding is elemsize aware, copy_make_border is now a padding wrapper 7 years ago
  nihuini d321d65fc8 Mat range for zero-copy slicing reference 7 years ago
  nihuini f78e8fd8e4 use max threads as cpu count on openmp capable runtime 7 years ago
  nihuini 2790f3c640 fix bus error for int8 storage 7 years ago
  nihuini 28b35b8c4f ShuffleChannel = Reshape + SwapAxis + Reshape 7 years ago