nihui
322667a2ab
pnnx fix fused tensor_split operator insert order ( #4006 )
4 years ago
Jie Li
434e55c0f8
fix(examples): load_param always failed ( #4001 )
4 years ago
nihui
1892c25360
pnnx fuse megvii style shufflechannel slice ( #3999 )
4 years ago
nihui
94786308bd
pnnx fuse binaryop eltwise as weighted sum ( #4000 )
4 years ago
dependabot[bot]
8d28fc91b5
Bump pypa/cibuildwheel from 2.7.0 to 2.8.0 ( #3995 )
Bumps [pypa/cibuildwheel](https://github.com/pypa/cibuildwheel ) from 2.7.0 to 2.8.0.
- [Release notes](https://github.com/pypa/cibuildwheel/releases )
- [Changelog](https://github.com/pypa/cibuildwheel/blob/main/docs/changelog.md )
- [Commits](https://github.com/pypa/cibuildwheel/compare/2.7.0...v2.8.0 )
---
updated-dependencies:
- dependency-name: pypa/cibuildwheel
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
4 years ago
nihui
a5fb92db51
optimize innerproduct fp16s transform kernel ( #3994 )
4 years ago
nihui
d4a704de0e
pnnx eliminate noop upsample ( #3991 )
4 years ago
nihui
b4bae2c9e4
pnnx convert torch.tensor_split, fuse full dim size slice to tensor_split ( #3988 )
4 years ago
sodo
3b3605eec4
add pkgconfig ( #3984 )
Signed-off-by: sodo <djdisodo@gmail.com>
4 years ago
Zhuo Zhang
c04a1bccce
fix(examples): exit program if load_param, load_model failed for clear message ( #3983 )
* fix(examples): exit program if load_param, load_model failed for clear error messsage
* ignore .cache dir for clangd
* check non-zero instead of -1 for load functions
4 years ago
tpoisonooo
207ca0e0bb
Improve protobuf FAQ doc ( #3973 )
4 years ago
nihui
044467b2c6
pnnx support torch 1.12 ( #3981 )
4 years ago
nihui
0de869e8e3
ci release copy and zip preserve links ( #3980 )
4 years ago
nihui
d2fc473d8f
update qcom810 benchmark data
4 years ago
nihui
b9b5f9b119
ci release python fix, install strip ( #3977 )
* fix release python
* Update release-python.yml
* install strip
* there is no strip target for ios
* install libomp on macos
* uninstall libomp atm
* force remove
4 years ago
nihui
eeb969ad2c
update qcom855plus benchmark data. set adreno gpu frequency.
4 years ago
nihui
f8c76e730a
fix ci release optimization with cmake >= 3.21 and ndk23 ( #3976 )
* Update release.yml
* Update how-to-build.md
4 years ago
nihui
eeac683c70
fix release python ( #3974 )
4 years ago
nihui
14588023b5
release ubuntu 22.04 package, fix ndk debug flag for r23+ ( #3972 )
4 years ago
nihui
531506d602
improve pattern value match, always treat inplace operator as non-inplace version ( #3970 )
4 years ago
nihui
8dbedf8a19
use cmake gnuinstalldirs for install destination ( #3968 )
4 years ago
nihui
43912c7f42
more strict compiler avx512fp16 support detection ( #3966 )
4 years ago
moozae
94ec06a8a5
delete unused variables ( #3965 )
4 years ago
nihui
f597619e94
pnnx export weight inside moduleop ( #3902 )
4 years ago
nihui
b85bfb6085
armv8.2 asimdfhm and armv8.4 bf16 i8mm and armv8.6 sve sve2 compiler flags and runtime detection functions ( #3964 )
4 years ago
nihui
be8e195630
add avx512 spr ci ( #3960 )
4 years ago
nihui
5ae827c745
convert inplace relu6, match more hardswish pattern ( #3952 )
* convert inplace relu6, match more hardswish pattern
* upgrade requests
4 years ago
nihui
bc8e939c85
insert reshape for nn.Linear with 4d/5d inputs ( #3959 )
* insert reshape for nn.Linear with 4d/5d inputs
* batch index aware reshape, add test
4 years ago
Yoh
a4ccad3325
Fix gcc4 simd conflict ( #3957 )
* fix mat::fill gcc4 avx sse conflict bug
* fix build and crash with gcc 4.4.0
Co-authored-by: nihui <shuizhuyuanluo@126.com>
4 years ago
dankernel
01655613d1
Create build-for-VisualStudio.en.md ( #3956 )
- Translated Chinese documents into English
- Updated to VS2022 version
4 years ago
Jianbo-Ning
4fad760a64
add faq.en.md ( #3901 )
4 years ago
nihui
28e0c9132a
fix cmake find thread on mips
4 years ago
nihui
27dc780005
mips msa optimization for innerproduct fp16s ( #3953 )
4 years ago
nihui
706831f8a9
arm vfpv4 optimization for innerproduct ( #3950 )
4 years ago
nihui
440bfdd2cc
x86 f16c optimization for innerproduct ( #3944 )
4 years ago
nihui
08e2dd5a0c
pnnx ncnn fp16 storage conversion as a pass ( #3939 )
4 years ago
nihui
1fd7138d2f
armv7 vfpv4 infrastructure ( #3929 )
* armv7 vfpv4 infrastructure
* optional fp16 format ieee
* arm neon assembly optimization for cast fp16/bf16
4 years ago
dependabot[bot]
3a0ba55c6f
Bump pypa/cibuildwheel from 2.6.1 to 2.7.0 ( #3931 )
4 years ago
nihui
067e8e1d92
mips unified elempack for elementwise layers ( #3928 )
4 years ago
nihui
d4ee0853a5
mips msa optimization for cast fp16 ( #3927 )
4 years ago
nihui
1377acf945
avx512 bf16 fp16 infrastructure ( #3926 )
4 years ago
nihui
8c06103132
riscv convolution winograd dot function and strategy ( #3921 )
* riscv convolution dot function
* move rvv ci to centos
* apply code-format changes
* fix gcov path
* move newlib riscv ci to centos
4 years ago
nihui
e7ca89853e
mips convolution winograd dot function and strategy ( #3925 )
4 years ago
nihui
20a14bf5ae
arm convolution winograd dot function, adjust arm convolution winograd strategy ( #3915 )
4 years ago
nihui
ca0ba4b25f
fine grained winograd options, adjust x86 convolution winograd strategy ( #3908 )
* fine grained winograd options
* x86 optimization for convolution winograd f23 pack4/pack8/pack16
* fix avx512 and t4 ci
* fix fast direct conv path
* winograd63 is actually slower than winograd43 on very large channel
4 years ago
nihui
a692a8fce7
move loongarch64 ci to centos machine ( #3904 )
4 years ago
Evgeny Proydakov
184c479b64
Added a simple unittest for Power layer. ( #3893 )
4 years ago
Evgeny Proydakov
1c8f1ba7c6
Fixed LGTM warnings ( #3891 )
src/stb_image.h
src/layer/detectionoutput.cpp
tools/quantize/imreadwrite.cpp
4 years ago
dependabot[bot]
2e73a4c62e
Bump actions/setup-python from 3 to 4 ( #3900 )
4 years ago
nihui
5400028e12
fix ncnn2table crash in lightmode ( #3898 )
* fix crash in ncnn2table for missing weight data in lightmode
* Update modelwriter.h
4 years ago