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
  nihui d0bcda70ca arm neon optimize for winograd input output transform, about 4%~22% faster 8 years ago
  nihui c656c572ad use float type for input transform 8 years ago
  nihuini 0219f507b7 convert ConvTranspose and InstanceNormalization 8 years ago
  nihuini 9b6445cd05 convert reshape and transpose 8 years ago
  nihuini 4f79b89635 comment for reshape flag 8 years ago
  nihuini aee6552360 memcpy is fast :) 8 years ago
  nihuini db4b04da53 fix slice with implicit slice point 8 years ago
  nihuini bc905288a7 set default CMAKE_BUILD_TYPE before project command, since the later can set CMAKE_BUILD_TYPE itself 8 years ago
  wangyakun c4cbacf8f5 Add support for Reshape in mxnet2ncnn 8 years ago
  Yantao Xie 97d41f8e7d Make debug easy (#341) 8 years ago
  BUG1989 67732a83d8 Add the benchmark of RK3288 (#340) 8 years ago
  BUG1989 2ecad8ab32 Update README.md 8 years ago
  nihuini 593703b71f sleep 10 seconds for cooling down SOC, more warmups 8 years ago
  nihui e2d35702ce
Update README.md 8 years ago
  nihui 0f390ad731
Update README.md 8 years ago
  nihui 89ef9d779d
Update README.md 8 years ago
  nihui addfcbafe0 build onnx2ncnn by default 8 years ago
  nihui b27cd92dfa paste oops 8 years ago
  nihui 2cc6abde6a convert ImageScaler LeakyRelu, tiny-yolov2 works 8 years ago
  nihui 2abeb038a0 unroll outch for conv3x3s2, about 30% faster :) 8 years ago
  nihui 97025668a9 unroll conv1x1s1 outch 6 inch 4 on armv7, about 2%~18% faster 8 years ago
  nihui 0a666c8cb9
Update README.md 8 years ago
  nihuini dd0ae756de batchnorm and scale on vector and image, fix #331 8 years ago
  AlanNewImage e77eef3f3d Update priorbox.cpp (#330) 8 years ago
  daquexian 3a5d7cfcce Fix mobilenet v2's stride (#327) 8 years ago
  Yantao Xie cd3617b11d Set ArgMax's one_blob_only as true. (#325) 8 years ago
  Joe 9748c00b44 add image-level feature support (#320) 8 years ago
  nihui 0e41c37250 convert convolution pad_w pad_h 8 years ago
  Tiancai Ye ea95c7a7fc fix a fix~~~ (#323) 8 years ago
  Tiancai Ye 3977d32eb9 Fix windows build fails (#321) 8 years ago
  Yantao Xie 73340578c8 Remove the destructor definition from the lstm layer. (#319) 8 years ago
  Howave 5e7332e507 align memory start address (#318) 8 years ago
  nihuini fac262658c use android prebuild releas folder, build arm64 jni library 8 years ago
  nihuini 4019505642 use clang, fix build, fix #292 8 years ago
  nihuini e4c1ddbc45 rewrite inner loop in assembly, since gcc is sometimes foolish qaq, fix #312 8 years ago
  nihuini aac70893f8 fix build on gcc 8 years ago
  nihuini 394bca8dbb Merge branch 'master' of https://github.com/Tencent/ncnn 8 years ago
  nihuini 9ac305e160 create 3-dim sub blob for group convolution, fix #315 8 years ago
  Howave 415bfbdfa7 added arm layer compilation for arm-linux system (#316) 8 years ago
  nihuini 318d3abe66 bind register explicitly, fix #306, fix #310, fix #312 8 years ago
  Yantao Xie 2e9da1b95b Add the epsilon parameter to the BatchNorm layer. (fix #303) (#311) 8 years ago
  nihuini 231a52e469 fix build on aarch64 with gcc, fix #309 8 years ago
  BUG1989 4ebab2725d Updata benchmark ReadMe (#308) 8 years ago
  BUG1989 af7019d3fc fix compile error (#305) 8 years ago
  nihui d7e31987fa
Update README.md 8 years ago
  nihui 004632d9e5
Update README.md 8 years ago
  nihui ce9eeaba9a
Update README.md 8 years ago
  nihui 875a188d10 pre interleave kernel memory for winograd4, about 3%~20% speed gains 8 years ago
  nihui d2c01019aa fix convert depthwise deconvolution, fix #300 8 years ago
  dong 6ea09ebf2c Use aarch64 assembly to replace arm intrinsics 8 years ago