2456 Commits (cfcb1cffa961f2a35e900a6c8aad083191b7eb2f)
 

Author SHA1 Message Date
  nihui cfcb1cffa9
massive vulkan optimization part2 (#3621) 4 years ago
  tpoisonooo edd3a78ffe
style(src/layer): remove unused para and var (#3623) 4 years ago
  tpoisonooo 6e12647985
docs(how-to-build.md): update jetson description (#3622) 4 years ago
  tpoisonooo b8f36c258e
Update how-to-build.md (#3619) 4 years ago
  nihui f9663d7726
pnnx support torch 1.11.0 (#3617) 4 years ago
  nihui 6e19ab26ba
massive vulkan optimization (#3602) 4 years ago
  nihui 8f25ba0cab enable fp16a on mali-g31 4 years ago
  Kenji Mouri 8e29c42080
Improve SSE2 implementations in x86 targets. (#3605) 4 years ago
  Kenji Mouri 2b4a2125e6
Add SSE2 implementation of floor and ceil in x86 targets. (#3595) 4 years ago
  MouriNaruto f4f4cfd784 apply code-format changes 4 years ago
  nihui 8af8e52cb0 add nanodetplus pnnx example 4 years ago
  Kenji Mouri 3ba5d9765f
Add arm and arm64 targets support for MSVC. (#3592) 4 years ago
  Kenji Mouri e4f6b118a2
Fix comment typo because it should be itm[6][6]. (#3591) 4 years ago
  nihuini b053a8c6d5
fix unlocked pool allocator destroyed too early issue in gpu convdw and deconvdw inference 4 years ago
  nihui 30e106b185
add another mali g52 device id 4 years ago
  nihui 41cd40ac1f
convert pnnx torch.unbind and torch.ones/ones_like family (#3583) 4 years ago
  dependabot[bot] 8b68ec050d
Bump actions/checkout from 2 to 3 (#3588) 4 years ago
  nihui 2880eff264
deconv1d deconv3d (#3584) 4 years ago
  dependabot[bot] 556aeb675b
Bump actions/setup-python from 2 to 3 (#3586) 4 years ago
  Yoh f5b90a5333
Add unaryop x86 (#3579) 4 years ago
  nihuini bc188ece58
update modelwriter for new operators 4 years ago
  nihui 457e066eb5
x86 f16c infrastructure (#3577) 4 years ago
  nihui 38ae671391 add yolov5 pnnx example 4 years ago
  Yoh 4b68e3f9c1
Opt avxmath (#3563) 4 years ago
  nihui 920aa79f04
drop x86 avx2 fp16 (#3568) 4 years ago
  nihui 6b2495cc24
add reshape before and after pooling 123d with no batch dimension (#3566) 4 years ago
  nihui 76e32e9ee6
fix interp nearest by scale factor, fix issue #3555 (#3565) 4 years ago
  nihuini 6ee5ab72f6
handle reshape 5d with batch index 0 4 years ago
  tpoisonooo cfacba273f
improvement(binaryop): use MAKE_FUNCTION macro (#3559) 4 years ago
  nihui 68d0c8bccb apply code-format changes 4 years ago
  nihui fb5d5c011a convert F.pad with negative pads, eliminate noop expression 4 years ago
  nihui d452eca28f
convert torch.matmul, eliminate noop pad and identity op, fuse transpose matmul, fuse select to unbind (#3554) 4 years ago
  nihui b352221ba3 handle pnnx half weight when converting to ncnn 4 years ago
  nihui 4654030541
decouple x86 fma avx2 (#3560) 4 years ago
  nihui e1a8c87bc8
wrap namespace for function objects (#3558) 4 years ago
  nihui 3a5bb6c315
update ci swiftshader 20220211 (#3557) 4 years ago
  nihuini 69737ad169
fix permute vulkan 4 years ago
  nihuini d6df25c73f
fix avx512 ci 4 years ago
  nihuini 57a7101fc6
fix ci, second try 4 years ago
  nihuini cfedcfdc57
fix ci, first try 4 years ago
  Yuzhong Yan 681141ff42
[YZ] Fix bug in unit test (#3556) 4 years ago
  Evgeny Proydakov 6f824c57a1
Removed travis CI from sourcetree & readme. (#3488) 4 years ago
  nihui aa89529839
disable lto in ci build for oom issue (#3552) 4 years ago
  nihui d276ecd401
fix avx512 illegal instruction (#3550) 4 years ago
  nihuini 51ecc33d9d
check avx512vl extension for discarding old-slow avx512 chips, enable avx512 option by default 4 years ago
  nihui 3f2799d706
always build tightly packed weight, fix #3545 (#3547) 4 years ago
  nihui a46edcf720
x86 optimization for interp (#3546) 4 years ago
  nihui 139554b36e
rewrite convolution x86 sgemm pack1 (#3544) 4 years ago
  Yoh d2999b8d53
Optimize scale x86 (#3540) 4 years ago
  nihui fb6283c8b0
x86 avx fma optimization (#3543) 4 years ago