nihuini
|
c4bebc6371
|
x86 conv3x3s1 winograd43 produce wrong result, revert to the good-old winograd23 version
|
6 years ago |
CnybTseng
|
d11c4c1d42
|
修改最新版ncnn/src/layer/vulkan/shader目录下的几个文件,以适配最新版的glslang,本次修改已在大疆Manifold2-G平台上验证通过 (#1231)
|
6 years ago |
nihui
|
46e7ac76ab
|
apply sgemm-like dot in winograd pack4 neon
|
6 years ago |
nihui
|
d6860d93f2
|
fix batchnorm pack4 neon multithreaded
|
6 years ago |
nihui
|
b90a6cf69c
|
split always support packing :)
|
6 years ago |
nihui
|
6b5588ebbe
|
fix batchnorm pack4 out of range write
|
6 years ago |
nihui
|
4dc98ffaab
|
conv1x1s1 and conv3x3s1 winograd pack4 neon optimization, first try
|
6 years ago |
nihui
|
02c811e829
|
fix padding pack4 elempack
|
6 years ago |
nihuini
|
5d1a94826d
|
crop border param, try to make life eaiser
|
6 years ago |
nihui
|
af646b6577
|
workaround for the adjacency same pipeline issue
|
6 years ago |
nihui
|
cb82ccbe20
|
convolution vulkan winograd63 shader compilation is too slow and runs slower in many cases, ok let's drop it
|
6 years ago |
nihuini
|
6db731408c
|
crop vulkan pack1to4 and pack4to1
|
6 years ago |
nihui
|
35990bb5d5
|
instancenorm vulkan
|
6 years ago |
nihuini
|
4b8fb744bc
|
fix potential to_pixels_resize out of range write, fix #1201
|
6 years ago |
nihui
|
c2bc0d1b88
|
padding vulkan reflect mode
|
6 years ago |
nihuini
|
296e0022df
|
deconvolution output adj and output shape
|
6 years ago |
nihuini
|
e4b44d293e
|
more autopad SAME_LOWER
|
6 years ago |
nihuini
|
0e26e3094e
|
autopad SAME_LOWER
|
6 years ago |
nihuini
|
9c1eeb5d5c
|
raise NCNN_MAX_PARAM_COUNT from 20 to 32
|
6 years ago |
nihuini
|
9a6ee37eef
|
asymmetric padding parameter for convolution and deconvolution family
|
6 years ago |
nihui
|
29324771b1
|
Implemented hard swish layer (#1195)
|
6 years ago |
nihuini
|
3d5b7f20ff
|
avgpool count_include_pad
|
7 years ago |
Hao Zeng
|
1f6919fd40
|
Implemented hard swish layer
|
7 years ago |
Natsu
|
637d96c1d2
|
Fix gcc 9 compilation failure (#1189)
* Fix gcc 9 compilation failure
* Fix compilation failure on linux gcc
* Fix compilation failure on old gcc
* Remove C++11 requirement
|
7 years ago |
nihui
|
ff62e7eed9
|
use_packing_layout option works
|
7 years ago |
nihui
|
069e2da6a6
|
cast pack4 arm neon
|
7 years ago |
nihui
|
394f6786b9
|
neon enable support_packing
|
7 years ago |
nihuini
|
1cce18bdde
|
binaryop broadcast vulkan
|
7 years ago |
Natsu
|
77274eb336
|
Fixes clang compilation failure (#1179)
|
7 years ago |
nihui
|
0b6d7b7096
|
use underscored offset
|
7 years ago |
nihuini
|
e62b52ed77
|
eltwise pack4 arm neon
|
7 years ago |
nihuini
|
26c081cc05
|
concat pack4 arm neon
|
7 years ago |
nihuini
|
163fb92537
|
concat vulkan pack1to4 and pack4to1to4
|
7 years ago |
nihuini
|
1b910efea5
|
convert slice properly
|
7 years ago |
nihui
|
cf42e7c254
|
deconvolutiondepthwise pack4 arm neon
|
7 years ago |
nihui
|
b4c388a72a
|
Mat misc function accept option parameter, deconvolution pack4 arm neon
|
7 years ago |
nihui
|
60c0890eaf
|
crop region -234 is rarely used, fix out of channel range write, crop pack4 arm neon
|
7 years ago |
nihuini
|
6a1a8d96a6
|
fix reinterpret u32 to f32, second try
|
7 years ago |
nihuini
|
c46d9d5d65
|
fix reinterpret u32 to f32
|
7 years ago |
nihuini
|
b322db1845
|
tanh arm neon optimize
|
7 years ago |
nihuini
|
e0798faee3
|
binaryop unaryop pack4 arm neon
|
7 years ago |
nihuini
|
77c1f361b7
|
comment for broadcasting rules
|
7 years ago |
nihuini
|
dcff44f19b
|
softmax pack4 arm neon
|
7 years ago |
nihuini
|
85809219d6
|
mat fill float32x4_t type
|
7 years ago |
nihuini
|
730a1243b7
|
dropout pack4 arm neon, fix scale prelu pack4 openmp on vector
|
7 years ago |
nihuini
|
5de87eb667
|
scale pack4 arm neon
|
7 years ago |
nihuini
|
77dc3f024d
|
prelu pack4 arm neon
|
7 years ago |
nihuini
|
7200632af4
|
flatten pack4 arm neon
|
7 years ago |
nihuini
|
640a0372d5
|
pooling pack4 arm neon
|
7 years ago |
tpoisonooo
|
1a0459cffe
|
Update convolution_arm.cpp
add break.
|
7 years ago |