1039 Commits (440db2c8fc37ef3782d3516b07b707f3ec02bcf9)

Author SHA1 Message Date
  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 5 years ago
  nihuini 9c33b6c1c8 conv1x1s1 arm fp16sa 5 years ago
  nihuini 30ff3800d8 conv5x5s1 conv5x5s2 pack8 arm fp16sa neon assembly optimization 5 years ago
  nihuini 62c453b16d conv7x7s2 pack1to8 arm fp16sa neon assembly optimization 5 years ago
  nihuini b5b486fbfa conv3x3s2 pack8 arm fp16sa neon assembly optimization 5 years ago
  Zhuo Zhang 418047661c
fix #1984 & fix cmake (#2000) 5 years ago
  ncnnnnn e2557c1678
fix UNIT64_MAX not declared #2009 (#2010) 5 years ago
  nihui 5a9c99ce00 convdw5x5s1 pack8 arm neon fp16sa assembly optimization 5 years ago
  nihuini e841ae73c6 fix arm fp16s feat output, fix #2003 5 years ago
  nihuini 8df3a02391 unroll 12 for conv1x1s1 and conv3x3s1 winograd pack8 arm fp16sa 5 years ago
  nihui d8e9fc1443 conv3x3s1 conv3x3s2 pack1to8, padding pack8, relu pack8 arm neon fp16sa assmebly optimization 5 years ago
  kingdeviljin ac9cbaca56
#1993 resize_bilinear_c4 fix (#1999) 5 years ago
  nihuini b53f4072ce convdw3x3s1 condw3x3s2 pack8 arm fp16sa 5 years ago
  nihuini f6d808b090 crop pack8 arm fp16s, conv3x3s2 pack1to8 arm fp16sa intrinsic 5 years ago
  nihuini bc05a71a7c conv1x1s1 conv3x3s1 winograd arm fp16sa neon assembly optimization 5 years ago
  nihuini 5d5a3d1434 conv1x1s1 conv1x1s2 conv3x3s1 winograd pack8 arm fp16sa 5 years ago
  nihuini 20a0fc8628 packing honor thread count 5 years ago
  nihui 54e79a62d7 fix crash on non-arm82 build 5 years ago
  nihui c173d51c9b mish sigmoid swish tanh arm fp16s 5 years ago
  nihui 72a27d4776 utility wrapper for neon float32 bfloat16 conversion, deconvolution deconvolutiondepthwise arm fp16s fp16sa bf16s 5 years ago
  nihui e644164873 reshape arm bf16s fp16s, flatten api 5 years ago
  nihui aa68246dc7 more test coverage 5 years ago
  nihui e7abc5fbd7 concat slice arm fp16sa pack8 5 years ago
  nihui aa1a9e90c5 interp shufflechannel arm fp16sa pack8 5 years ago
  nihuini c6d7525367 convolutiondepthwise arm fp16sa pack8 5 years ago
  nihuini bc3822acc3 convolution flatten arm fp16sa pack8 5 years ago
  nihuini dbb761b9a4 binaryop eltwise padding pooling arm fp16sa pack8 5 years ago
  nihuini 91d91ba556 hardsigmoid hardswish arm fp16s fp16sa 5 years ago
  nihuini f23122bb3f since fp16 storage option is on by default, upper-level function may pass fp32 storage with default option, guard with element bits checking 5 years ago
  nihuini a18a9fd8c5 eltwise arm fp16s fp16sa 5 years ago
  nihuini 8385d81afa interp arm fp16s fp16sa 5 years ago
  nihuini 5a4243e44e binaryop arm fp16s 5 years ago
  nihuini 301abe657c relu arm fp16s 5 years ago
  nihui 03c9ed11d2 pooling arm fp16s fp16sa 5 years ago
  nihui 71f86af8a6 fix non-arm82 ci 5 years ago
  nihui 9a2e2a6937 convert fp32 blobs for layers with fp16 storage support 5 years ago
  nihui d4d501a7fe fix innerproduct fp16sa 5 years ago