1073 Commits (b766c8cd9e487ada4d309d7b03250a61405505c9)

Author SHA1 Message Date
  nihuini b766c8cd9e fix potential divide by zero fault when bf16s / fp16s enabled, fix #2125 5 years ago
  youzainn 1c5af3d83c
add device_name field for class GpuInfo (#2122) 5 years ago
  nihui b6d9a65cb1 fix fp16 overflow in instancenorm vulkan 5 years ago
  nihuini da7989bda3 yuv420sp2rgb_nv12 5 years ago
  tpoisonooo 2c8288555c
fix(cpu): cpu number bigger than 64 (#2083) 5 years ago
  nihui d695005744 innerproduct fp16sa bf16s pack 5 years ago
  nihui 41840d0461 unaryop fp16s bf16s, sin cos fp16sa 5 years ago
  Zhuo Zhang 95d6ab401e
add ncnn debug lib postfix 'd' in cmake (#2091) 5 years ago
  nihuini c35af03166 delete dead code 5 years ago
  nihui 759b0b19d2 fix bus error in from_pixels with stride on armv7 5 years ago
  nihuini a334513b5e fp16a option fix 5 years ago
  nihuini 9047741129 always disable fp16/int8 arithmetic for gpu uop 5 years ago
  nihuini 6238bfd77f roi variant for from pixels family, enable fp16a by default 5 years ago
  nihuini d5f2220ee7 fuse onnx groupnorm 5 years ago
  nihuini 195fe2062b prelu arm fp16sa 5 years ago
  nihui 7ace8a933d
powerpc64, fix #2054 (#2058), workaround gcc altivec bug 5 years ago
  Leo b1c8afa94c
[ncnn] fix simplestl header not installed (#2053) 5 years ago
  nihuini 0be0b52df0 fix instancenorm vulkan without affine 5 years ago
  nihuini d04c05651f interp with reference target size blob 5 years ago
  nihui 9f5b660483 compile spirv 5 years ago
  Leo 5afd318b86
Support remove libstdc++ denpendency (#2030) 5 years ago
  zhiliu6 3726b17ab2
fix wrong for loop range on VOC and custom data (#2043) 5 years ago
  nihui 2964814857
Fix vs2019 ci (#2041) 5 years ago
  nihui bf297a0742
fix sprintf overflow for the zero terminator 5 years ago
  nihuini dacfccfa65 instancenorm without affine 5 years ago
  nihui 9fe137a3c2 fix build, second try 5 years ago
  nihui 061e378638 fix build 5 years ago
  nihui f11bebdcf5 batchnorm convdw3x3 arm fp16sa 5 years ago
  nihui 6f26f57d9c deconv4x4s2 arm fp16sa 5 years ago
  nihui 60b3c638aa tanh mish arm fp16sa neon optimization 5 years ago
  nihui bf09af21be exp arm fp16sa neon optimization 5 years ago
  nihui 39bbb34ffc conv1x1s1 conv3x3s1 pack4 pack8to4 arm fp16sa neon assembly optimization 5 years ago
  nihuini 985c15ed33 packing pack8 conversion arm fp16s 5 years ago
  nihuini 11b8dc9597 shufflechannel group2 acorss pack4 pack8 arm neon optimization 5 years ago
  nihuini 440db2c8fc conv1x1 pack4 arm fp16sa 5 years ago
  nihui b0457e3ecd conv1x1 pack8to1 arm fp16sa unroll size 4 5 years ago
  nihuini b5be1449d9 conv3x3s1 winograd pack8to4 arm fp16sa 5 years ago
  nihuini d17c26e925 conv1x1s1 pack4to8 pack8to4 arm fp16sa 5 years ago
  nihuini f5c5b79293 layernorm layer 5 years ago
  nihuini 4ad5230c2a groupnorm layer 5 years ago
  nihuini 332399c05f add gemm layer 5 years ago
  nihuini b35b5d7a3c gemm layer 5 years ago
  Zhuo Zhang 686a426935
fix #2012, cmake find vulkan issue (#2017) 5 years ago
  zhiliu6 952faf6668
Add yolov3detectionoutput test and AVX optimization (#1994) 5 years ago
  nihui 036c94499e fix conv1x1s1 vulkan 5 years ago
  nihui db5f05c6f0 conv1x1s1 conv3x3s1 winograd pack8to1 arm fp16sa 5 years ago
  nihui f6fb757672 fix convdw3x3s1 pack8 arm fp16sa 5 years ago
  nihuini bf0eb69bfe convdw3x3s2 pack8 arm fp16sa neon assembly optimization 6 years ago
  nihuini 9c33b6c1c8 conv1x1s1 arm fp16sa 6 years ago
  nihuini 30ff3800d8 conv5x5s1 conv5x5s2 pack8 arm fp16sa neon assembly optimization 6 years ago