2275 Commits (a490f8a5335f3608a19fdf8a018fbfbd731280d3)
 

Author SHA1 Message Date
  nihuini a490f8a533
fix layernorm with affine 4 years ago
  Feng Wang e887f04d03
update(example): preprocess logic of YOLOX (#3315) 4 years ago
  iotboy a533eea214
Update how-to-build.md (#3314) 4 years ago
  Tijmen Verhulsdonck ac5dc23ccc
added a number of optimized sse layers (#3302) 4 years ago
  ncnnnnn 0d32389efd
Update build-for-VisualStudio.zh.md (#3300) 4 years ago
  zhiliu6 a08f700775
Optimize avx convolution activation (#3299) 4 years ago
  Tijmen Verhulsdonck e3aa893dfb
move custom_layer_to_index to public (#3294) 4 years ago
  nihui 750eab81f5 skip rvm example build with simpleocv 4 years ago
  Nixon Dutta e8a8e0a874
Corrected the path for python version installation (#3293) 4 years ago
  zhiliu6 2ee675d6b8
YOLOv5 example add v6.0 support. (#3292) 4 years ago
  nihui aa9753b2f0
detach mat from local blob allocator so net instance could be destroyed much earlier (#3287) 4 years ago
  YuShiquan 0b12f5ee07
update readme of quantize (#3283) 4 years ago
  Richuanwu 88c294ecc9
remove travis ci arm32 (#3279) 4 years ago
  zhiliu6 814f89ef1a
Fuse HardSwish activation into Convolution and InnerProduct (#3233) 4 years ago
  nihui 647ceffea4
ci test-coverage lavapipe (#3266) 4 years ago
  nihui 4313d23355
update ci swiftshader 20211002 (#2366) 4 years ago
  Tijmen Verhulsdonck 4270b5c502
Fix broken codepaths with AVX only (#3254) 4 years ago
  Zhuo Zhang 492297d2f6
add A15 and M1 macro definitions (#3263) 4 years ago
  dankernel 69c4295681
Update how-to-build.md (#3248) 4 years ago
  nihui b7214c1b76 apply code-format changes 4 years ago
  Martin Han ef402b76e0
Add scrfd crowdhuman model support (#3237) 4 years ago
  FeiGeChuanShu 4cef99b675
Add RobustVideoMatting example code (#3243) 4 years ago
  nihui 52721dd1eb
Update operators.md 4 years ago
  nihui 0902594334
Update operators.md 4 years ago
  nihui 57ad2c138c fix build on c906, fix #3230 4 years ago
  nihui a74c64df78
Update operators.md 4 years ago
  dependabot[bot] 1367dd9ebf
Bump codecov/codecov-action from 2.0.3 to 2.1.0 (#3223) 4 years ago
  Jimmy 52c6502ae7
Feature/ncnntool/add install (#3212) 4 years ago
  zhiliu6 80699dd3f9
fix hardswish test beta param (#3214) 4 years ago
  nihui ceec22cd46
Update convolution_riscv.cpp (#3050) 4 years ago
  Xavier Hsinyuan a2f89e7392
RVV fp16/fp32 optimized Dropout, GRU and Softmax (#3200) 4 years ago
  nihui 3d5f447260
fix onnx negative concat axis, fix #3194 4 years ago
  dependabot[bot] be402bbf4d
Bump codecov/codecov-action from 2.0.2 to 2.0.3 (#3192) 4 years ago
  q.yao 41aa601413
fix fuse expand (#3189) 4 years ago
  TianZer c44a6c7f47
Remove two potential warnings for VisualStudio (#3188) 4 years ago
  ncnnnnn 5553e94152
Update build-for-VisualStudio.zh.md (#3185) 4 years ago
  源源✨ cb4e625fae
Update README.md (#3183) 4 years ago
  源源✨ 119446c530
add build on termux (#3181) 4 years ago
  FeiGeChuanShu eaab441d3c
Update Khadas Vim3 benchmark (#3172) 4 years ago
  nihui 5a35c2b11e
load model memory by reference (#3179) 4 years ago
  nihui e9b5bbcd2d
fix armv7 roundmode (#3176) 4 years ago
  yaobyPerfxlab ec561736a5
Riscv64 c906 d1 (#3159) 4 years ago
  Liuyufanlyf b0f8290657
Update RK3328 CPU benchmark (#3164) 4 years ago
  nihui d7c8d0d9a2
fix coverage glslang (#3158) 4 years ago
  nihui 51652a2280
NCNN_MALLOC_OVERREAD for potential kernel reading data out of allocation size (#3155) 4 years ago
  nihuini a99cc13611
ncnnoptimize generate proper weight for int8 scales, fix non-neon innerproduct int8, fix #3157 4 years ago
  BowShotDS a6667ee6c4
Update RK3568 CPU benchmark (#3145) 4 years ago
  nihui c6cda8d07c
arm neon optimization for requantize leakyrelu (#3144) 4 years ago
  nihui 224040e65c
Create README.md 4 years ago
  nihuini 169614f732
fix build with NCNN_STDIO off 4 years ago