nihuini
|
7a3a5be4e6
|
fix requantize x86 pack4to1
|
5 years ago |
JuYan
|
05f6d2cf23
|
Pocky群号 (#2956)
|
5 years ago |
nihui
|
f6c49523d2
|
fix convolutiondepthwise 3x3 int8 pack8, fix #2952
|
5 years ago |
dependabot[bot]
|
a3b1377c8b
|
Bump actions/cache from 1 to 2.1.5 (#2946)
Bumps [actions/cache](https://github.com/actions/cache) from 1 to 2.1.5.
- [Release notes](https://github.com/actions/cache/releases)
- [Commits](https://github.com/actions/cache/compare/v1...v2.1.5)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
|
5 years ago |
dependabot[bot]
|
266d8891c7
|
Bump styfle/cancel-workflow-action from 0.7.0 to 0.9.0 (#2945)
Bumps [styfle/cancel-workflow-action](https://github.com/styfle/cancel-workflow-action) from 0.7.0 to 0.9.0.
- [Release notes](https://github.com/styfle/cancel-workflow-action/releases)
- [Commits](https://github.com/styfle/cancel-workflow-action/compare/0.7.0...0.9.0)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
|
5 years ago |
dependabot[bot]
|
4eab6a0a66
|
Bump pypa/gh-action-pypi-publish from 1.4.1 to 1.4.2 (#2944)
Bumps [pypa/gh-action-pypi-publish](https://github.com/pypa/gh-action-pypi-publish) from 1.4.1 to 1.4.2.
- [Release notes](https://github.com/pypa/gh-action-pypi-publish/releases)
- [Commits](https://github.com/pypa/gh-action-pypi-publish/compare/v1.4.1...v1.4.2)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
|
5 years ago |
dependabot[bot]
|
3774514767
|
Bump codecov/codecov-action from 1.4.1 to 1.5.0 (#2943)
Bumps [codecov/codecov-action](https://github.com/codecov/codecov-action) from 1.4.1 to 1.5.0.
- [Release notes](https://github.com/codecov/codecov-action/releases)
- [Changelog](https://github.com/codecov/codecov-action/blob/master/CHANGELOG.md)
- [Commits](https://github.com/codecov/codecov-action/compare/v1.4.1...v1.5.0)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
|
5 years ago |
nihuini
|
cdb8ec218d
|
Revert "trigger release-python"
This reverts commit 882f114a8d.
|
5 years ago |
Zhiqiang Wang
|
be5a912052
|
Fixing Python classifiers and disable aarch64 (#2949)
* Fixing classifiers of Pypi for local compliler
* Disable aarch64 in building Python
|
5 years ago |
Zhiqiang Wang
|
d7f972dff3
|
Fixing Python classifiers of Pypi (#2948)
|
5 years ago |
nihuini
|
882f114a8d
|
trigger release-python
|
5 years ago |
nihuini
|
fd485c4da1
|
add dependabot
|
5 years ago |
nihui
|
b3cd06e69a
|
force upload python artifacts
|
5 years ago |
nihuini
|
9b5cb959b9
|
auto convert int8 to fp32 on extract
|
5 years ago |
nihuini
|
535f5ed037
|
fix convolutiondepthwise int8 scale weight saving
|
5 years ago |
nihuini
|
1ad37fae1e
|
generate random weight when null bin passed
|
5 years ago |
nihuini
|
d20a144ebf
|
fix glslang framework packing
|
5 years ago |
nihuini
|
26ea87cc25
|
do not define android macro for jetson, fix #2939
|
5 years ago |
nihui
|
61eb52e21e
|
add downloads badge
|
5 years ago |
nihuini
|
1d80aa0d83
|
package ncnn quantize tool binary
|
5 years ago |
nihuini
|
00b0094b2f
|
copy-pasta makes msvc happy
|
5 years ago |
nihuini
|
9a12597dff
|
build ncnn quantization tool even opencv not found
|
5 years ago |
nihuini
|
0e35c66f50
|
mention pixel drawing in build-minimal-library.md
|
5 years ago |
nihui
|
49f3e1ea09
|
drawing api and stb_image (#2913)
* drawing api
* add drawing test
* yuv420sp drawing
* enable simpleocv in webassembly build
|
5 years ago |
nihuini
|
26dc9820e4
|
custom mlir ncnn optimize pass, add efficientnetv2_b0 benchmark
|
5 years ago |
nihuini
|
b7959a4fc7
|
fuse mlir swish and conv-addv2
|
5 years ago |
ZHEQIUSHUI
|
397309a796
|
Update ncnn-android-scrfd link and demo screenshot (#2925)
* Update ncnn-android-scrfd link and demo picture
* Update ncnn-android-scrfd link and demo screenshot
|
5 years ago |
nihui
|
ad37c34d25
|
disable NCNN_ARM82DOT whenever NCNN_ARM82 disabled
|
5 years ago |
FusionBolt
|
322812de2d
|
Fix typo (#2922)
|
5 years ago |
Cai Shanli
|
8cc8cd716a
|
Add get input and output names (#2890)
|
5 years ago |
nihuini
|
afc02d57f9
|
runtime detect armv8.2 dotprod
|
5 years ago |
nihui
|
5f62fdec87
|
allow more concurrent gpu submits on device with low queue count
|
5 years ago |
nihui
|
5d6f03dbbd
|
asm word for risc-v without v
|
5 years ago |
deepage
|
6614807002
|
Update faq.md (#2907)
* Update faq.md
* Update faq.md
handle channel gap and transfer data owner
|
5 years ago |
nihuini
|
e548344965
|
fix scrfd rgb input
|
5 years ago |
nihuini
|
43e1d83a84
|
add scrfd example
|
5 years ago |
nihui
|
a1b06baec8
|
fix build
|
5 years ago |
nihui
|
17936e9f54
|
fix packing risc-v test, add cpu_riscv_vlenb()
|
5 years ago |
nihui
|
da40cc6ec8
|
risc-v v optimization for math functions of all LMUL
|
5 years ago |
nihui
|
b2b9957cba
|
update imx7d benchmark
|
5 years ago |
Cai Shanli
|
f465ad8acc
|
test release python (#2892)
remove build s390x python wheels
|
5 years ago |
Cai Shanli
|
52e27af3a4
|
Update how-to-build.md (#2896)
fix typo
|
5 years ago |
nihuini
|
ae14ca91ac
|
update qcom855+ benchmark
|
5 years ago |
nihui
|
6a4abfa344
|
improve benchmark readme format
|
5 years ago |
nihuini
|
d0d8120335
|
force lrn vulkan accumulator always use fp32, fix #2882
|
5 years ago |
nihuini
|
7a1e015d72
|
fix bias error in conv1x1s1 sgemm pack8to4 fp16sa, fix #2880
|
5 years ago |
nihuini
|
e34edfb672
|
fix caffe2ncnn input shape for 1-dim and 2-dim blob
|
5 years ago |
nihui
|
655fb3b5eb
|
fix rv64gcv test coverage build
|
5 years ago |
nihui
|
11958424c2
|
runtime riscv v and zfh dispatch, riscv v optimization for cast
|
5 years ago |
nihui
|
48d5dbf33f
|
ci riscv rvv coverage (#2886)
|
5 years ago |