nihui
/
ncnn
Not watched
1
0
Fork 0
Code
Releases 46 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
1518 Commits
5 Branches
354 MB
2 Download
Tree: bedf00a5ed
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'bedf00a5ed'
${ noResults }
Commit Graph

982 Commits (bedf00a5edf85ae8af33bc72ebd85fe325da1271)

Author SHA1 Message Date
  lyfe667 3c7863d341 fix line 1142 bug (#1397) 6 years ago
  nihuini 279e67bb88 normalize vulkan 6 years ago
  nihuini e917796f97 normalize support inplace 6 years ago
  nihuini 095efc5471 load param value type 6 years ago
  nihuini 5dcd5667ad fix wrong prelu vulkan pack4 slope data 6 years ago
  nihuini 50e8b5e4e8 multiple transfers may run concurrently if there is no dependency with each other, do not share staging buffer memory to fix potential data race 6 years ago
  nihuini dce75e1f07 pooling vulkan pad auto SAME mode, fix avgpool_count_include_pad handling 6 years ago
  nihuini 5eae1b8325 always write normalize scale data, do not break optimize tool 6 years ago
  nihuini 33956cbfc3 pretty error info 6 years ago
  nihuini af3643ed81 normalize eps mode for different training framework conventions 6 years ago
  nihui b29e8b0e09 check and enable more vulkan extensions 6 years ago
  nihuini bffb2af2ff fix build on armv7 without neon 6 years ago
  nihuini dc589351c1 link android 6 years ago
  nihuini a170ef1acf remove the default option usage in layer interface, fix write out of range in cast arm pack4, handle fp16p conversion on cpu/gpu transfer 6 years ago
  nihuini 336d1c1edd remove the ncnn namespace for in source Option 6 years ago
  nihui 90f04bab26 minor index optimization 6 years ago
  nihuini e73b06bbb8 fix build with NCNN_STRING=OFF 6 years ago
  zyvv bbcd5db817 Improvement for winograd43 int8 convolution (#1354) 6 years ago
  andywangII 66d7ac2463 arm-hisim100-linux make error convolutiondepthwise_3x3_int8.h for asm (#1310) 6 years ago
  Natsu f11b772dd1 Fix min/max macro issue (#1346) 6 years ago
  Joshua 96a2499051 fix spp::copy_make_border (#1345) 6 years ago
  Christopher 2f26697aea fix err in priorbox (#1343) 6 years ago
  nihui a4a162e36d workaround validation layer complains about Cannot form constants of 8- or 16-bit types, due to specialization constants conversion 6 years ago
  nihuini b2758bd9a0 fix deconvolution vulkan output crop 6 years ago
  yehao 60d4ff09d0 add mobilenetv3-ssd (#1335) 6 years ago
  ShuangLiu1992 ecfc09bbc8 position independent code (#1333) 6 years ago
  nihui 2905639890 fix null fp handling 6 years ago
  Guocai He bbbaedda57 fix Crop bugs (#1326) 6 years ago
  nihuini 64333429bb data reader wrapper, fix #1325 6 years ago
  nihuini 567e2bd501 a dirty hack for resolving int8 pack4 crash 6 years ago
  bindog 9dfd1b05d3 fix bug in reduction (#1321) 6 years ago
  nihuini e8bb88830d convert mxnet squeeze expanddims, convert onnx squeeze unsqueeze 6 years ago
  nihuini a6c60068e6 convert numpy style slice to crop 6 years ago
  nihuini 009c4d9a75 convert mxnet reduce axis and keepdims, pad reflect, fix #739 6 years ago
  nihuini c4b84262d9 fix arm neon sgemm, fix #1283 6 years ago
  nihuini 65ce6bccfd faster weight transform for optimized kernel 6 years ago
  BUG1989 69e2693c87 fix the bug of SMP cpu powersave not supported. 6 years ago
  nihuini cd4be6d0fa call vulkan create_pipeline on the vkdev condition, drop opt_cpu hacks 6 years ago
  nihuini 81a028547a fix bus error on armv7 6 years ago
  nihuini 19d75955d6 arm neon assembly optimization for conv3x3s1 winograd pack4to1 6 years ago
  bindog 04b4b02324 [WIP] add reduce op support for onnx (#1308) 6 years ago
  nihuini 22a2be4e6c fix crop pack4 with reference blob 6 years ago
  nihuini 6a8e5c58da fix build on armv7 6 years ago
  nihuini e63e2449fd arm neon assembly optimization for conv7x7s2 pack1to4 6 years ago
  nihui 56fd26a2da arm neon assembly optimization for conv1x1s1 pack4to1 6 years ago
  nihui 7ad514917b fix potential out of write on unroll 12 remainder 6 years ago
  nihuini 15e86dc8e9 reduce pack4 weight memory usage for specialized kernel, reduce runtime memory usage in conv3x3s1 winograd 6 years ago
  nihuini 581a06d471 since innerproduct pack4 always consumes flattened blob, which layout is same as pack1 branch, so reuse pack1 implementation to reduce memory usage 6 years ago
  nihuini c5f1dc3fe4 arm neon assembly optimization for conv3x3s1 pack4to1 6 years ago
  nihui 2f8b31c3b4 unroll outch 2 for conv3x3s1 pack1to4 6 years ago