982 Commits (bedf00a5edf85ae8af33bc72ebd85fe325da1271)

Author SHA1 Message Date
  nihui e0f6e3f669 pre-interleave 8-channel weight data on aarch64, conv1x1s1 version 6 years ago
  nihuini d11bf14d44 pre-interleave 8-channel weight data on aarch64 6 years ago
  nihui 7173b6e38e arm neon assembly optimization for conv3x3s2 pack4 6 years ago
  nihuini cf0c49dd71 arm neon assembly optimization for conv5x5s1 pack4 and conv5x5s2 pack4 6 years ago
  nihui 9e529354fb arm neon optimization for conv1x1s2 pack4 6 years ago
  nihuini f8f3b0b5aa shufflechannel pack4 6 years ago
  nihuini 50d5896ce7 reshape pack4 6 years ago
  nihuini 624291e2b2 use subop optimization for group convolution deconvolution pack4 family 6 years ago
  nihui 48e3e7d49c move neon activation into a wrapper function 6 years ago
  nihui 8c1b87b1a2 fallback to cpu if no vulkan device found 6 years ago
  nihui b37ecab630 auto flatten before innerproduct pack4 6 years ago
  nihui afd1f08194 arm neon assembly optimization for pooling2x2s2 max pack4 6 years ago
  nihui e19b7097df arm neon assembly optimization for conv3x3s1 pack1to4 6 years ago
  nihui 3ac6335ba3 hardsigmoid and hardswish pack4 6 years ago
  nihui 21e74487b4 arm neon optimization for convdw5x5 pack4 6 years ago
  volvet ecd64fb36b Fixed lots of compile warnings (#1286) 6 years ago
  nihui 3e1bad4880 arm neon assembly optimization for pooling3x3s2 max pack4 6 years ago
  nihui 08a97c169f arm neon assembly optimization for relu pack4 6 years ago
  nihui a1bd88fb4a arm neon assembly optimization for padding constant pack4 6 years ago
  nihui 17f343e7e4 convdw3x3 pack4 arm neon assembly optimization 6 years ago
  nihui 6703286831 the very long ld1, one less load 6 years ago
  nihui 22a3ade6ce unroll size 12 for conv1x1s1 and conv3x3s1 winograd pack4 on aarch64 6 years ago
  nihui 3a452f734a arm neon assembly optimization for conv3x3s2 pack1to4 6 years ago
  nihui 6edd42f566 arm neon assembly for conv1x1s1 and conv3x3s1 winograd pack4 6 years ago
  nihuini c0a4ffcf66 convolution pad_value param 6 years ago
  nihuini 587a67eb51 the noop layer 6 years ago
  nihuini b7085ceec0 deconvolution apply output adj first, then crop the padding 6 years ago
  tpoisonooo 8dbafe7764 constraint input value to [-127, +127] (#1258) 6 years ago
  nihui e56fcc77c5 optimize dot memory layout 6 years ago
  nihuini 8a7b4b035e radv crash with large local group size, workaround 6 years ago
  nihuini 80f898b079 unaryop tanh vulkan 6 years ago
  nihuini 70f3198703 conversion between ncnn Mat and android Bitmap makes life easier :D 6 years ago
  nihuini 8f72256d1f mat pixel rgb2rgba bgr2rgba gray2rgba 6 years ago
  nihuini 91ef4eea4f fix unaryop arm, fix #1241 6 years ago
  nihuini 3e3189736c fix msvc build, fix #1237 6 years ago
  Xu Yang 31cf7f3c5b fix ConvolutionDepthWise int8_requantize (#1233) 6 years ago
  nihuini c4bebc6371 x86 conv3x3s1 winograd43 produce wrong result, revert to the good-old winograd23 version 6 years ago
  CnybTseng d11c4c1d42 修改最新版ncnn/src/layer/vulkan/shader目录下的几个文件,以适配最新版的glslang,本次修改已在大疆Manifold2-G平台上验证通过 (#1231) 6 years ago
  nihui 46e7ac76ab apply sgemm-like dot in winograd pack4 neon 6 years ago
  nihui d6860d93f2 fix batchnorm pack4 neon multithreaded 6 years ago
  nihui b90a6cf69c split always support packing :) 6 years ago
  nihui 6b5588ebbe fix batchnorm pack4 out of range write 6 years ago
  nihui 4dc98ffaab conv1x1s1 and conv3x3s1 winograd pack4 neon optimization, first try 6 years ago
  nihui 02c811e829 fix padding pack4 elempack 6 years ago
  nihuini 5d1a94826d crop border param, try to make life eaiser 7 years ago
  nihui af646b6577 workaround for the adjacency same pipeline issue 7 years ago
  nihui cb82ccbe20 convolution vulkan winograd63 shader compilation is too slow and runs slower in many cases, ok let's drop it 7 years ago
  nihuini 6db731408c crop vulkan pack1to4 and pack4to1 7 years ago
  nihui 35990bb5d5 instancenorm vulkan 7 years ago
  nihuini 4b8fb744bc fix potential to_pixels_resize out of range write, fix #1201 7 years ago