706c4d1964
support 4d mat in more operators ( #6737 )
...
Add 4d Mat handling across generic and optimized backends, extend operator tests, and document supported input and output Mat dimensions.
2026-05-22 15:31:01 +08:00
544230f71d
gemm x86 tile-N threading, drop testutil layer hook function ( #6428 )
...
* test threading
* drop testutil layer hook function
2025-11-28 15:48:48 +08:00
171b9d1bba
use spdx license header, copyright Tencent ( #6152 )
2025-07-08 11:01:29 +08:00
556b79ce4d
create layer decoupled ( #5258 )
...
* create layer decoupled
* no more virtual public
* allow build test with shared library
* decouple cpu vulkan
* drop old scripts
2024-01-05 14:08:15 +08:00
dadc640c66
x86 avx512 optimization ( #3581 )
...
* unified relu avx512
* unifed clip avx512
* unaryop avx512
* sigmoid avx512
* binaryop avx512
* padding convolution avx512
* convolutiondepthwise avx512
* innerproduct avx512
* reshape avx512
* slice avx512
* hardsigmoid hardswish avx512
* swish avx512
* pooling avx512
* crop avx512
* convolution sgemm pack16
* convolution 3x3 winograd pack16
* interp avx512
* convolution sgemm pack1to16
* convolution sgemm pack16to8
* convolution sgemm pack8to16
* convolution sgemm pack16to4
* fix vulkan permute pack8
* fix vulkan convolution gemm pack8to1
2022-04-09 17:23:27 +08:00
f10cc6dd93
initial data structure changes for 3dcnn, conv3d, pooling3d ( #3378 )
...
Co-authored-by: ElvisYu <elvisyuovo@gmail.com >
Co-authored-by: 余浩文 <m18107220188@163.com >
Co-authored-by: Zr2223 <67497651+Zr2223@users.noreply.github.com >
2021-12-02 16:50:55 +08:00
c1ce8ea84d
add more test
2021-06-19 10:48:06 +08:00
07fa2e1fe3
prefer large channels for int8 operator tests
2021-06-18 11:04:37 +08:00
3a77b09c31
fix test failure
2021-06-17 23:51:17 +08:00
934a1a8e32
test flatten packing padding int8
2021-06-17 19:42:45 +08:00
fca04980f3
enhance padding test ( #2580 )
...
* workaround nvidia driver crash
* workaround radv buffer_ld1 zero bug
* fix offset elempack
2021-01-11 14:58:28 +08:00
be49c07e93
fix arm82 fp16s crop padding
2020-11-29 15:56:21 +08:00
e68f15d2f0
padding vulkan vec and image, more padding test
2020-11-29 14:46:40 +08:00
71272d1b99
more padding test
2020-11-26 23:10:34 +08:00
11cffce114
armv8.2 infrastructure ( #1856 )
...
* runtime cpu dispatch
* force thread one
* disable openmp for coverage
* simplify test layer
* print NCNN_TARGET_ARCH
* less ci build variants
* weight fp16 storage option
* test convdw int8
* apple a12 a13
* ncnn_add_layer ncnn_add_shader cmake macro
2020-07-19 19:29:52 +08:00
3ef995ed1e
format code style and setup restyled.io ( #1840 )
2020-06-13 22:17:51 +08:00
da09e5e7f1
Adding channel padding support for blazeface model. ( #1826 )
...
* Add channel padding and blazeface model support.
* remove python binding
* remove std::min usage
* fix reference blob usage
* Increased padding test coverage
* implement requested changes
2020-06-09 19:25:40 +08:00
979dd5fd11
test does not need to provide data type options
2020-04-12 19:28:04 +08:00
0f7e7bca02
shader shape specialization constant and basic local group size partition ( #1523 )
...
* use Mat class for Shape description
* shape specialization constant in compute shader
* wip
* wip
* test forward_inplace, add binaryop unaryop sigmoid test
* fix arm unaryop test
* fix arm binaryop test
* make shape hint optional, cast int8 to fp32, add cast test
* wip
* follow the good and old local size setting for conv1x1
* the optimal local size rewrite
* fix build on msvc
* add permute shader for all packing layout, add permute test
* concat and slice patial shape constant, slice test
* fix slice test
* interp test
* add lrn test, test packing layout implicitly
* add eltwise test
* add normalize test
* add instancenorm test
* reorg shape constant
* simple local group size partition
* add shape constant param
2020-02-17 15:45:29 +08:00
2f16eaa476
fix padding test per channel pad value
2020-01-10 17:53:01 +08:00
c78b8a08fd
padding reflect pack4, add padding test
2020-01-10 17:37:15 +08:00
nihui