763 Commits (4ad5230c2aa8ffdc2ae94aaa351c1415ecf6f789)

Author SHA1 Message Date
  nihuini 4ad5230c2a groupnorm layer 5 years ago
  nihuini b35b5d7a3c gemm layer 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
  nihui 5a9c99ce00 convdw5x5s1 pack8 arm neon fp16sa assembly optimization 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
  nihuini b53f4072ce convdw3x3s1 condw3x3s2 pack8 arm fp16sa 6 years ago
  nihuini f6d808b090 crop pack8 arm fp16s, conv3x3s2 pack1to8 arm fp16sa intrinsic 6 years ago
  nihuini bc05a71a7c conv1x1s1 conv3x3s1 winograd arm fp16sa neon assembly optimization 6 years ago
  nihuini 5d5a3d1434 conv1x1s1 conv1x1s2 conv3x3s1 winograd pack8 arm fp16sa 6 years ago
  nihuini 20a0fc8628 packing honor thread count 6 years ago
  nihui c173d51c9b mish sigmoid swish tanh arm fp16s 6 years ago
  nihui 72a27d4776 utility wrapper for neon float32 bfloat16 conversion, deconvolution deconvolutiondepthwise arm fp16s fp16sa bf16s 6 years ago
  nihui e644164873 reshape arm bf16s fp16s, flatten api 6 years ago
  nihui aa68246dc7 more test coverage 6 years ago
  nihui e7abc5fbd7 concat slice arm fp16sa pack8 6 years ago
  nihui aa1a9e90c5 interp shufflechannel arm fp16sa pack8 6 years ago
  nihuini c6d7525367 convolutiondepthwise arm fp16sa pack8 6 years ago
  nihuini bc3822acc3 convolution flatten arm fp16sa pack8 6 years ago
  nihuini dbb761b9a4 binaryop eltwise padding pooling arm fp16sa pack8 6 years ago
  nihuini 91d91ba556 hardsigmoid hardswish arm fp16s fp16sa 6 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 6 years ago
  nihuini a18a9fd8c5 eltwise arm fp16s fp16sa 6 years ago
  nihuini 8385d81afa interp arm fp16s fp16sa 6 years ago
  nihuini 5a4243e44e binaryop arm fp16s 6 years ago
  nihuini 301abe657c relu arm fp16s 6 years ago
  nihui 03c9ed11d2 pooling arm fp16s fp16sa 6 years ago
  nihui d4d501a7fe fix innerproduct fp16sa 6 years ago
  nihui e9c71a1ead innerproduct arm fp16s fp16sa 6 years ago
  nihui 1a57600bd7 fix ci crash 6 years ago
  nihuini 11f5033249 convolutiondepthwise arm fp16s fp16sa 6 years ago
  nihuini 6ab284bc3a convolution arm fp16s fp16sa 6 years ago
  nihuini 6d2c0e5683 flatten fp16s 6 years ago
  nihuini 47ae0c151a some shared arm bf16s fp16s implementation 6 years ago
  zchrissirhcz b80b84fda5
fix #1542; fix avx2 uint16_t including (#1968) 6 years ago
  nihuini 8700985540 yet another workaround for nexus6p gpu 6 years ago
  nihui 21762e09e5
fix dilated convolution (#1956) 6 years ago
  nihuini 4d2d625432 fix avx2 build, second try, fix #1953 6 years ago
  nihuini 8b0890999a fix avx2 build, fix #1953 6 years ago
  nihui 88367f4164
Ci enable mips msa (#1949) 6 years ago
  nihui bb5bfe3841
avx2 infrastructure (#1943) 6 years ago
  nihui 11cffce114
armv8.2 infrastructure (#1856) 6 years ago