nihui
/
ncnn
Not watched
1
0
Fork 0
Code
Releases 46 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
566 Commits
5 Branches
354 MB
2 Download
Tree: ac7121f54b
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'ac7121f54b'
${ noResults }
Commit Graph

249 Commits (ac7121f54b4a0ce128df6fcdba780470c77df81f)

Author SHA1 Message Date
  weiliangweiliang ac7121f54b fix the wrong variable name that cause wrong results. (#741) 7 years ago
  nihui b75516b9b1
add the armv7a conv3x3s2, convdw3x3s1/s2 int8 implement without overflow : ) (#738) 7 years ago
  weiliangweiliang c79a6f7413 fix missing branch in arm 3x3s2 conv (#737) 7 years ago
  BUG1989 229f8fd8db add the armv7a conv3x3s2, convdw3x3s1/s2 int8 implement without overflow 7 years ago
  shujunhua 225d4925c0 fix lstm bug 7 years ago
  BUG1989 4850eeed6f add the armv7a conv1x1s1 sgemm int8 implement without overflow : ) (#713) 7 years ago
  nihuini 6a9ac1581e fix clobber list in convdw5x5s1_neon and convdw5x5s2_neon 7 years ago
  nihuini 69d2c48bb8 improve group deconvolution openmp scheduler 7 years ago
  Eric Liu 9558c27daa Fixed a yolov3 resolution bug (#696) 7 years ago
  nihui adfbb9eb25 fix caffe ssd, somewhat ugly though ... 7 years ago
  nihuini 65be036aa6 mxnet-ssd done 7 years ago
  nihuini c77383f623 mxnet-ssd wip ... 7 years ago
  nihuini 481722648c fix ooops .... :] 7 years ago
  nihuini 94e3a79ee9 fix crash in priorbox when min_sizes or max_sizes is empty 7 years ago
  nihuini 0b34dd59fb trival fix for the last element 7 years ago
  nihuini c44e49d3e9 implement roialign layer 7 years ago
  nihuini 250f6b8bdd fix build 7 years ago
  nihuini 4837af4c25 initial effort for mxnet-ssd 7 years ago
  nihuini 3a69f1c68b implement psroipooling layer 7 years ago
  nihuini a5e57fa22e implement multiscale yolov2, update example model comment 7 years ago
  Jianjun Liu 8c79c90102 variable name should be remain. 7 years ago
  karl2015 201ebb8e44 fix dequantize register error (#653) 7 years ago
  nihuini 8fda293f91 neon optimize for depthwise convolution 5x5 :P 7 years ago
  Ming-Yang Liu dfbed5a0ad Support yolov3 and mobilenet yolov3 7 years ago
  BUG1989 971fe2f639 fix the bug of aarch64 conv1x1 int8 'asm' op less than 30 (#628) 7 years ago
  nihuini 4af3ec223b fix clip arm 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 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
  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 8 years ago
  nihuini 19ad4cf284 fix build without neon 8 years ago
  nihuini 23de61fd07 as we already have the int8_scale_term switch, do not have to rely on the actual scale value 8 years ago
  nihuini dda21b8ea9 convolution depthwise 3x3 stride 1 with unroll 8 on aarch64 8 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 :| 8 years ago
  nihuini a76a07eb3f fix null sub group elemsize/allocator in depthwise deconvolution, fix #539 8 years ago
  nihuini 6f1b0b0a61 quantized padding in convolution, use range sweets 8 years ago
  nihuini bf1c58be46 padding is elemsize aware, copy_make_border is now a padding wrapper 8 years ago
  BUG1989 1b0e33460d add armv7 int8 conv3x3s1,using vaddw to replace vadd and vmovl 8 years ago
  nihui 72411b7a6c restore the old conv3x3s2 as reference, fast dilation convolution fails on striding 8 years ago
  nihui 1f20eb4e8c pack weight and more unroll makes improvement, ~20% faster for conv3x3s2 8 years ago
  chensy 30cc738309 fix asm "invalid operand" error for target iOS armv7 on file dequantize_arm.cpp 8 years ago
  nihuini 2dbaf6f7b7 store int8 scale in binary 8 years ago