lsdustc
|
61af40cfbd
|
Fix Innerproduct gemm forgot to add an offset of w in int8 forward (#3084)
|
4 years ago |
nihui
|
dba7348f17
|
add loongson 2k1000 benchmark
|
4 years ago |
zhiliu6
|
190207a173
|
fix AVX2 compiled as AVX problem (#3090)
|
4 years ago |
nihui
|
052b2a1653
|
apply code-format changes
|
4 years ago |
chenxiemin
|
9bd8a50b96
|
fix vulkan memory leak issue (#3088)
|
4 years ago |
zhiliu6
|
c6bb70622b
|
fix convolution padding when pad=0 (#3087)
|
4 years ago |
nihui
|
a2844bbf6c
|
Update build-minimal-library.md
|
4 years ago |
nihui
|
cdf45a6512
|
cmake option NCNN_BF16 (#3068)
|
4 years ago |
Tijmen Verhulsdonck
|
eaa7e24db6
|
Added ability to switch AVX/AVX2 during runtime (#3076)
|
4 years ago |
nihui
|
9391fae741
|
optimize arm neon tanh (#3079)
|
4 years ago |
lsdustc
|
fd1d5bb2ba
|
Update ncnn2table.cpp (#3081)
修正eq 校准中imagelists错误的索引
|
4 years ago |
ncnnnnn
|
f0d1426b01
|
scrfd cao (#3080)
|
4 years ago |
deepage
|
5841f667a6
|
optimize arm neon tanh fma (#3078)
Co-authored-by: chao.tang <chao.tang@lynxi.com>
|
4 years ago |
nihui
|
06a7086daa
|
optimize arm neon exp log sincos fma (#3077)
|
4 years ago |
nihui
|
b413fd3a3d
|
auto code-format bot and disable restyled (#3075)
|
4 years ago |
Tijmen Verhulsdonck
|
a7f301a99d
|
Add clang compatiblity (#3071)
* Add clang compatiblity
Add ability to build NCNN lib on windows with clang GNU
* Restyled/pull 3071 (#16)
* [skip ci] Restyled by clang-format
* [skip ci] Restyled by astyle
* [skip ci] Restyled by clang-format
* [skip ci] Restyled by astyle
Co-authored-by: Restyled.io <commits@restyled.io>
Co-authored-by: Restyled.io <commits@restyled.io>
|
4 years ago |
Zhuo Zhang
|
5049aaeabd
|
fix invalid read for yuv420sp2rgb on arm32 (#3066)
|
4 years ago |
nihui
|
927e34278c
|
mips msa optimization part2 (#3063)
* mips msa optimization for convolution 3x3 pack1to4, 7x7s2 pack1to4, dropout, eltwise, hardsigmoid, hardswish, packing, flatten, prelu
* prefetch convdw3x3 and convdw5x5
* fix mips convolution sgemm pack4to1
* more prefetch helps
|
4 years ago |
nihui
|
49cda73420
|
mips msa optimization for convolution sgemm and winograd (#3055)
* mips msa optimization for convolution sgemm and 3x3s1 winograd, use msa fmadd
* mips msa optimization for convolution sgemm pack4to1
* mips msa optimization for swish, improve sgemm kernel
* unroll 12x4, use prefetch
|
4 years ago |
nihui
|
8a40b98348
|
mips optimization (#3051)
* mips msa optimization for crop deconvolution deconvolutiondepthwise general cases
* mips msa activation support pack4
* mips msa optimization for concat slice interp
* mips msa optimization for binaryop unaryop
|
4 years ago |
nihui
|
90b38ba145
|
fix mips convolutiondepthwise
|
4 years ago |
nihui
|
a133f4be92
|
mips msa optimization for pooling general cases, fix test on ls2k
|
4 years ago |
nihui
|
1f49fc4b67
|
mips msa optimization for padding packing flatten innerproduct convolution convolutiondepthwise general cases
|
4 years ago |
DaydreamCoding
|
f42d0e5dc9
|
fix warpaffine_bilinear_yuv420sp uv matrix (#3048)
|
4 years ago |
li mengyang
|
be054aacb0
|
some misspell (#3046)
* just a spell check
* some misspell
|
4 years ago |
BUG1989
|
2112a4d7c3
|
add the param file of nanodet_m in benchmark (#3047)
* add the param file of nanodet_m in benchmark
* add Noop layer into nanodet_m param for benchmark
* update nanodet_m.param
|
4 years ago |
nihui
|
b8e03ced3c
|
allow examples building with simpleocv
|
4 years ago |
li mengyang
|
0d0b9a522f
|
just a spell check (#3045)
|
4 years ago |
kalcohol
|
72778f7d1f
|
add benchmark for v1605b (#3039)
|
4 years ago |
nihui
|
f2d2a6d51b
|
drop fprintf
|
4 years ago |
nihuini
|
e63bb1f79e
|
riscv v optimization for convolution 3x3s1 3x3s2 7x7s2 pack1ton
|
4 years ago |
nihui
|
589609b37a
|
fix test on c906
|
4 years ago |
nihuini
|
41a64e5efe
|
riscv v optimization for convolution sgemm pack1ton packnto1
|
4 years ago |
nihui
|
b2e8a8d87d
|
split noop support riscv zfh
|
4 years ago |
nihui
|
4f135e07bf
|
implement convolution1d and pooling1d (#3035)
* implement convolution1d and pooling1d
* add conv1d pool1d test
* fuse convolution1d activation
* update operator doc
* fix vulkan adpative pooling
|
4 years ago |
nihuini
|
e526934a48
|
riscv v optimization for convolutiondepthwise 3x3 5x5 packn
|
4 years ago |
nihui
|
abd0b26994
|
fix test on c906
|
4 years ago |
nihuini
|
44e60b8dd9
|
fix over allocated workspace blobs for fp16sa in convolution sgemm rvv
|
4 years ago |
nihuini
|
400aa23e57
|
riscv v optimization for convolution sgemm pack1
|
4 years ago |
nihuini
|
e9a7b5ac96
|
riscv v optimization for convolution 3x3s1 packn winograd42 and winograd64
|
4 years ago |
zhiliu6
|
1a9bb708f1
|
darknet2ncnn: add sam layer support, add letter_box detection. (#3037)
|
4 years ago |
nihui
|
2cbece80ad
|
fix build on c906
|
4 years ago |
nihuini
|
c7ceee8768
|
riscv v optimization for convolution sgemm and conv1x1 packn
|
4 years ago |
nihui
|
64092d0c7c
|
mips msa optimization for log_ps and mish
|
5 years ago |
nihui
|
832fc3eb72
|
fix mips tanh
|
5 years ago |
nihui
|
1c31ac2549
|
runtime cpu dispatch for mips msa and loongson mmi
|
5 years ago |
nihui
|
2f70343aec
|
cmake clean (#3032)
|
5 years ago |
nihui
|
56446391bb
|
at least all tests passed on d1
|
5 years ago |
tpoisonooo
|
87fed87906
|
feat(template): add issue templates (#3029)
* feat(template): add issue templates
* feat(issue): add emoji
* update
|
5 years ago |
nihui
|
4c2457ae43
|
fix build for c906
|
5 years ago |