596 Commits (c4bebc63714662aa2d7446be1728bb0feca07361)

Author SHA1 Message Date
  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 6 years ago
  nihui af646b6577 workaround for the adjacency same pipeline issue 6 years ago
  nihui cb82ccbe20 convolution vulkan winograd63 shader compilation is too slow and runs slower in many cases, ok let's drop it 6 years ago
  nihuini 6db731408c crop vulkan pack1to4 and pack4to1 6 years ago
  nihui 35990bb5d5 instancenorm vulkan 6 years ago
  nihuini 4b8fb744bc fix potential to_pixels_resize out of range write, fix #1201 6 years ago
  nihui c2bc0d1b88 padding vulkan reflect mode 6 years ago
  nihuini 296e0022df deconvolution output adj and output shape 6 years ago
  nihuini e4b44d293e more autopad SAME_LOWER 6 years ago
  nihuini 0e26e3094e autopad SAME_LOWER 6 years ago
  nihuini 9c1eeb5d5c raise NCNN_MAX_PARAM_COUNT from 20 to 32 6 years ago
  nihuini 9a6ee37eef asymmetric padding parameter for convolution and deconvolution family 6 years ago
  nihui 29324771b1
Implemented hard swish layer (#1195) 6 years ago
  nihuini 3d5b7f20ff avgpool count_include_pad 7 years ago
  Hao Zeng 1f6919fd40 Implemented hard swish layer 7 years ago
  Natsu 637d96c1d2 Fix gcc 9 compilation failure (#1189) 7 years ago
  nihui ff62e7eed9 use_packing_layout option works 7 years ago
  nihui 069e2da6a6 cast pack4 arm neon 7 years ago
  nihui 394f6786b9 neon enable support_packing 7 years ago
  nihuini 1cce18bdde binaryop broadcast vulkan 7 years ago
  Natsu 77274eb336 Fixes clang compilation failure (#1179) 7 years ago
  nihui 0b6d7b7096 use underscored offset 7 years ago
  nihuini e62b52ed77 eltwise pack4 arm neon 7 years ago
  nihuini 26c081cc05 concat pack4 arm neon 7 years ago
  nihuini 163fb92537 concat vulkan pack1to4 and pack4to1to4 7 years ago
  nihuini 1b910efea5 convert slice properly 7 years ago
  nihui cf42e7c254 deconvolutiondepthwise pack4 arm neon 7 years ago
  nihui b4c388a72a Mat misc function accept option parameter, deconvolution pack4 arm neon 7 years ago
  nihui 60c0890eaf crop region -234 is rarely used, fix out of channel range write, crop pack4 arm neon 7 years ago
  nihuini 6a1a8d96a6 fix reinterpret u32 to f32, second try 7 years ago
  nihuini c46d9d5d65 fix reinterpret u32 to f32 7 years ago
  nihuini b322db1845 tanh arm neon optimize 7 years ago
  nihuini e0798faee3 binaryop unaryop pack4 arm neon 7 years ago
  nihuini 77c1f361b7 comment for broadcasting rules 7 years ago
  nihuini dcff44f19b softmax pack4 arm neon 7 years ago
  nihuini 85809219d6 mat fill float32x4_t type 7 years ago
  nihuini 730a1243b7 dropout pack4 arm neon, fix scale prelu pack4 openmp on vector 7 years ago
  nihuini 5de87eb667 scale pack4 arm neon 7 years ago
  nihuini 77dc3f024d prelu pack4 arm neon 7 years ago
  nihuini 7200632af4 flatten pack4 arm neon 7 years ago
  nihuini 640a0372d5 pooling pack4 arm neon 7 years ago
  tpoisonooo 1a0459cffe Update convolution_arm.cpp 7 years ago