nihui
/
ncnn
Not watched
1
0
Fork 0
Code
Releases 46 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
3230 Commits
5 Branches
354 MB
2 Download
 
 
 
 
 
 
Tree: 1e75a2df21
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '1e75a2df21'
${ noResults }
ncnn/src/layer
nihui c4a007406d
windows clang ci (#5469) 		2 years ago
..
arm windows clang ci (#5469) 2 years ago
loongarch update ncnnoptimize layers, lightmode=false keeps original weight (#5414) 2 years ago
mips update ncnnoptimize layers, lightmode=false keeps original weight (#5414) 2 years ago
riscv rnn/lstm/gru dynamic quantization (#5435) 2 years ago
vulkan update ncnnoptimize layers, lightmode=false keeps original weight (#5414) 2 years ago
x86 windows clang ci (#5469) 2 years ago
absval.cpp layer creator function is not necessary for built-in layers 6 years ago
absval.h move vulkan code to subdir, new layer interface create_pipeline and destroy_pipeline for post-loading works 7 years ago
argmax.cpp Support remove libstdc++ denpendency (#2030) 5 years ago
argmax.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
batchnorm.cpp implement simplemath (#4905) 2 years ago
batchnorm.h move vulkan code to subdir, new layer interface create_pipeline and destroy_pipeline for post-loading works 7 years ago
bias.cpp relu3d, batchnorm3d, reshape4d, flatten4d, permute4d (#3397) 4 years ago
bias.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
binaryop.cpp implement simplemath (#4905) 2 years ago
binaryop.h implement atan2 (#4516) 3 years ago
bnll.cpp implement simplemath (#4905) 2 years ago
bnll.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
cast.cpp initial data structure changes for 3dcnn, conv3d, pooling3d (#3378) 4 years ago
cast.h cast between float32 and bfloat16 6 years ago
celu.cpp implement simplemath (#4905) 2 years ago
celu.h Celu layer and export to ncnn (#5019) 2 years ago
clip.cpp clip gelu mish tanh 4d (#4695) 3 years ago
clip.h architecture changes for int8 packing (#2771) 5 years ago
concat.cpp concat 4d (#4528) 3 years ago
concat.h move vulkan code to subdir, new layer interface create_pipeline and destroy_pipeline for post-loading works 7 years ago
convolution.cpp create layer decoupled (#5258) 2 years ago
convolution.h create layer decoupled (#5258) 2 years ago
convolution1d.cpp create layer decoupled (#5258) 2 years ago
convolution1d.h create layer decoupled (#5258) 2 years ago
convolution3d.cpp initial data structure changes for 3dcnn, conv3d, pooling3d (#3378) 4 years ago
convolution3d.h initial data structure changes for 3dcnn, conv3d, pooling3d (#3378) 4 years ago
convolutiondepthwise.cpp create layer decoupled (#5258) 2 years ago
convolutiondepthwise.h create layer decoupled (#5258) 2 years ago
convolutiondepthwise1d.cpp pnnx enhance functionize (#5387) 2 years ago
convolutiondepthwise1d.h create layer decoupled (#5258) 2 years ago
convolutiondepthwise3d.cpp fix too many microtask error in old libomp runtime (#4002) 3 years ago
convolutiondepthwise3d.h initial data structure changes for 3dcnn, conv3d, pooling3d (#3378) 4 years ago
copyto.cpp copyto operator (#4522) 3 years ago
copyto.h copyto operator (#4522) 3 years ago
crop.cpp crop4d (#3402) 4 years ago
crop.h crop4d (#3402) 4 years ago
cumulativesum.cpp Support torch.cumsum (#4505) 3 years ago
cumulativesum.h Support torch.cumsum (#4505) 3 years ago
deconvolution.cpp deconvolution dynamic weight (#5119) 2 years ago
deconvolution.h deconvolution dynamic weight (#5119) 2 years ago
deconvolution1d.cpp deconvolution dynamic weight (#5119) 2 years ago
deconvolution1d.h deconvolution dynamic weight (#5119) 2 years ago
deconvolution3d.cpp fix too many microtask error in old libomp runtime (#4002) 3 years ago
deconvolution3d.h deconv1d deconv3d (#3584) 4 years ago
deconvolutiondepthwise.cpp deconvolution dynamic weight (#5119) 2 years ago
deconvolutiondepthwise.h deconvolution dynamic weight (#5119) 2 years ago
deconvolutiondepthwise1d.cpp deconvolution dynamic weight (#5119) 2 years ago
deconvolutiondepthwise1d.h deconvolution dynamic weight (#5119) 2 years ago
deconvolutiondepthwise3d.cpp fix too many microtask error in old libomp runtime (#4002) 3 years ago
deconvolutiondepthwise3d.h deconv1d deconv3d (#3584) 4 years ago
deepcopy.cpp layer creator function is not necessary for built-in layers 6 years ago
deepcopy.h deepcopy layer 6 years ago
deformableconv2d.cpp reduce double usage (#4671) 3 years ago
deformableconv2d.h Add DeformableConv2D (#4070) 3 years ago
dequantize.cpp architecture changes for int8 packing (#2771) 5 years ago
dequantize.h architecture changes for int8 packing (#2771) 5 years ago
detectionoutput.cpp implement simplemath (#4905) 2 years ago
detectionoutput.h mxnet-ssd wip ... 7 years ago
diag.cpp add diag layer and its converter (#4935) 2 years ago
diag.h add diag layer and its converter (#4935) 2 years ago
dropout.cpp implement simplemath (#4905) 2 years ago
dropout.h move vulkan code to subdir, new layer interface create_pipeline and destroy_pipeline for post-loading works 7 years ago
einsum.cpp implement einsum layer and pnnx conversion (#3768) 4 years ago
einsum.h implement einsum layer and pnnx conversion (#3768) 4 years ago
eltwise.cpp eltwise 4d (#4529) 3 years ago
eltwise.h format code style and setup restyled.io (#1840) 6 years ago
elu.cpp implement simplemath (#4905) 2 years ago
elu.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
embed.cpp layer creator function is not necessary for built-in layers 6 years ago
embed.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
erf.cpp disable rtti and exceptions for msvc (#5167) 2 years ago
erf.h erf implementation (#5012) 2 years ago
exp.cpp implement simplemath (#4905) 2 years ago
exp.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
expanddims.cpp squeeze and expanddims 4d (#4346) 3 years ago
expanddims.h squeeze and expanddims 4d (#4346) 3 years ago
flatten.cpp relu3d, batchnorm3d, reshape4d, flatten4d, permute4d (#3397) 4 years ago
flatten.h move vulkan code to subdir, new layer interface create_pipeline and destroy_pipeline for post-loading works 7 years ago
fold.cpp clear warning: unused variable while building on x86-wsl platform (#5444) 2 years ago
fold.h implement ncnn fold and unfold (#4326) 3 years ago
fused_activation.h create layer decoupled (#5258) 2 years ago
gelu.cpp implement simplemath (#4905) 2 years ago
gelu.h update modelwriter for new operators 4 years ago
gemm.cpp shadowed variable for less openmp task args (#4744) 3 years ago
gemm.h gemm output transpose, prepack c (#4479) 3 years ago
glu.cpp implement simplemath (#4905) 2 years ago
glu.h implement GLU and pnnx conversion (#4283) 3 years ago
gridsample.cpp implement simplemath (#4905) 2 years ago
gridsample.h Grid sample op (#4373) 2 years ago
groupnorm.cpp implement simplemath (#4905) 2 years ago
groupnorm.h fuse onnx groupnorm 5 years ago
gru.cpp rnn/lstm/gru dynamic quantization (#5435) 2 years ago
gru.h rnn/lstm/gru dynamic quantization (#5435) 2 years ago
hardsigmoid.cpp add comment for alpha beta in hardswish and hardsigmoid compared to tf/pytorch implementation (#2859) 5 years ago
hardsigmoid.h Implemented hard sigmoid (#1046) 7 years ago
hardswish.cpp add comment for alpha beta in hardswish and hardsigmoid compared to tf/pytorch implementation (#2859) 5 years ago
hardswish.h Implemented hard swish layer 6 years ago
innerproduct.cpp create layer decoupled (#5258) 2 years ago
innerproduct.h create layer decoupled (#5258) 2 years ago
input.cpp relu3d, batchnorm3d, reshape4d, flatten4d, permute4d (#3397) 4 years ago
input.h relu3d, batchnorm3d, reshape4d, flatten4d, permute4d (#3397) 4 years ago
instancenorm.cpp implement simplemath (#4905) 2 years ago
instancenorm.h instancenorm without affine 5 years ago
interp.cpp fix interp nearest by scale factor, fix issue #3555 (#3565) 4 years ago
interp.h add interp param align_corner (#2236) 5 years ago
layernorm.cpp implement simplemath (#4905) 2 years ago
layernorm.h fuse onnx layernorm, fix 2-dim layernorm implementation, add test 5 years ago
log.cpp implement simplemath (#4905) 2 years ago
log.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
lrn.cpp implement simplemath (#4905) 2 years ago
lrn.h format code style and setup restyled.io (#1840) 6 years ago
lstm.cpp rnn/lstm/gru dynamic quantization (#5435) 2 years ago
lstm.h rnn/lstm/gru dynamic quantization (#5435) 2 years ago
matmul.cpp convert torch.matmul, eliminate noop pad and identity op, fuse transpose matmul, fuse select to unbind (#3554) 4 years ago
matmul.h convert torch.matmul, eliminate noop pad and identity op, fuse transpose matmul, fuse select to unbind (#3554) 4 years ago
memorydata.cpp support tag in memorydata layer (#5061) 2 years ago
memorydata.h support tag in memorydata layer (#5061) 2 years ago
mish.cpp implement simplemath (#4905) 2 years ago
mish.h Add mish layer (#1733) 6 years ago
multiheadattention.cpp multiheadattention attn mask (#4668) 3 years ago
multiheadattention.h multiheadattention attn mask (#4668) 3 years ago
mvn.cpp implement simplemath (#4905) 2 years ago
mvn.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
noop.cpp create layer decoupled (#5258) 2 years ago
noop.h create layer decoupled (#5258) 2 years ago
normalize.cpp implement simplemath (#4905) 2 years ago
normalize.h normalize support inplace 6 years ago
packing.cpp initial data structure changes for 3dcnn, conv3d, pooling3d (#3378) 4 years ago
packing.h fuse packing cast storage, binaryop image shader, dummy buffer and image, device-wide utility packing converter operators, fix multi-blob layer test 6 years ago
padding.cpp initial data structure changes for 3dcnn, conv3d, pooling3d (#3378) 4 years ago
padding.h initial data structure changes for 3dcnn, conv3d, pooling3d (#3378) 4 years ago
permute.cpp relu3d, batchnorm3d, reshape4d, flatten4d, permute4d (#3397) 4 years ago
permute.h move vulkan code to subdir, new layer interface create_pipeline and destroy_pipeline for post-loading works 7 years ago
pixelshuffle.cpp pixelshuffle nhwc mode, convert onnx DepthToSpace mode DCR, convert mlir tf.DepthToSpace 5 years ago
pixelshuffle.h pixelshuffle nhwc mode, convert onnx DepthToSpace mode DCR, convert mlir tf.DepthToSpace 5 years ago
pooling.cpp fuse adaptive pool dynamic output size, implement ncnn adaptive pooling dynamic outsize (#5043) 2 years ago
pooling.h support PyTorch AdaptiveAvgPool2d and AdaptiveMaxPool2d (#2546) 5 years ago
pooling1d.cpp use int ceil/floor div (#3333) 4 years ago
pooling1d.h implement convolution1d and pooling1d (#3035) 5 years ago
pooling3d.cpp fuse adaptive pool dynamic output size, implement ncnn adaptive pooling dynamic outsize (#5043) 2 years ago
pooling3d.h initial data structure changes for 3dcnn, conv3d, pooling3d (#3378) 4 years ago
power.cpp implement simplemath (#4905) 2 years ago
power.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
prelu.cpp layer creator function is not necessary for built-in layers 6 years ago
prelu.h move vulkan code to subdir, new layer interface create_pipeline and destroy_pipeline for post-loading works 7 years ago
priorbox.cpp implement simplemath (#4905) 2 years ago
priorbox.h add mobilenetv3-ssd (#1335) 6 years ago
proposal.cpp implement simplemath (#4905) 2 years ago
proposal.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
psroipooling.cpp implement simplemath (#4905) 2 years ago
psroipooling.h implement psroipooling layer 7 years ago
quantize.cpp implement simplemath (#4905) 2 years ago
quantize.h architecture changes for int8 packing (#2771) 5 years ago
reduction.cpp workaround l2 norm produce -inf value with subnormals (#5272) 2 years ago
reduction.h format code style and setup restyled.io (#1840) 6 years ago
relu.cpp initial data structure changes for 3dcnn, conv3d, pooling3d (#3378) 4 years ago
relu.h architecture changes for int8 packing (#2771) 5 years ago
reorg.cpp pixelshuffle nhwc mode, convert onnx DepthToSpace mode DCR, convert mlir tf.DepthToSpace 5 years ago
reorg.h reorg nhwc mode, code format 5 years ago
requantize.cpp requantize: Use activation_ss in fused_activation.h (#5245) 2 years ago
requantize.h architecture changes for int8 packing (#2771) 5 years ago
reshape.cpp relu3d, batchnorm3d, reshape4d, flatten4d, permute4d (#3397) 4 years ago
reshape.h relu3d, batchnorm3d, reshape4d, flatten4d, permute4d (#3397) 4 years ago
rnn.cpp rnn/lstm/gru dynamic quantization (#5435) 2 years ago
rnn.h rnn/lstm/gru dynamic quantization (#5435) 2 years ago
roialign.cpp implement simplemath (#4905) 2 years ago
roialign.h Improve ROIAlign (accelerate ROIAlign, support sampling ratio and aligned ROIAlign) (#1820) 6 years ago
roipooling.cpp implement simplemath (#4905) 2 years ago
roipooling.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
scale.cpp layer creator function is not necessary for built-in layers 6 years ago
scale.h move vulkan code to subdir, new layer interface create_pipeline and destroy_pipeline for post-loading works 7 years ago
selu.cpp implement simplemath (#4905) 2 years ago
selu.h implemented selu activation (#1051) 7 years ago
shrink.cpp shrink operator (#5022) 2 years ago
shrink.h shrink operator (#5022) 2 years ago
shufflechannel.cpp fix shufflechannel.cpp integer multiply may overflow (#2212) 5 years ago
shufflechannel.h shufflechannel reverse group style 6 years ago
sigmoid.cpp implement simplemath (#4905) 2 years ago
sigmoid.h move vulkan code to subdir, new layer interface create_pipeline and destroy_pipeline for post-loading works 7 years ago
slice.cpp slice with indices (#5103) 2 years ago
slice.h slice with indices (#5103) 2 years ago
softmax.cpp implement simplemath (#4905) 2 years ago
softmax.h move vulkan code to subdir, new layer interface create_pipeline and destroy_pipeline for post-loading works 7 years ago
softplus.cpp implement simplemath (#4905) 2 years ago
softplus.h softplus inplace (#2156) 5 years ago
split.cpp create layer decoupled (#5258) 2 years ago
split.h create layer decoupled (#5258) 2 years ago
spp.cpp implement simplemath (#4905) 2 years ago
spp.h format code style and setup restyled.io (#1840) 6 years ago
squeeze.cpp squeeze and expanddims 4d (#4346) 3 years ago
squeeze.h squeeze and expanddims 4d (#4346) 3 years ago
statisticspooling.cpp implement simplemath (#4905) 2 years ago
statisticspooling.h add statisticspooling layer (#1768) 6 years ago
swish.cpp implement simplemath (#4905) 2 years ago
swish.h Add Swish layer (#1799) 6 years ago
tanh.cpp implement simplemath (#4905) 2 years ago
tanh.h move vulkan code to subdir, new layer interface create_pipeline and destroy_pipeline for post-loading works 7 years ago
threshold.cpp layer creator function is not necessary for built-in layers 6 years ago
threshold.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
tile.cpp layer tile (#3491) 4 years ago
tile.h layer tile (#3491) 4 years ago
unaryop.cpp implement simplemath (#4905) 2 years ago
unaryop.h pnnx convert torch round trunc (#4813) 3 years ago
unfold.cpp implement ncnn fold and unfold (#4326) 3 years ago
unfold.h implement ncnn fold and unfold (#4326) 3 years ago
yolodetectionoutput.cpp create layer decoupled (#5258) 2 years ago
yolodetectionoutput.h move vulkan code to subdir, new layer interface create_pipeline and destroy_pipeline for post-loading works 7 years ago
yolov3detectionoutput.cpp create layer decoupled (#5258) 2 years ago
yolov3detectionoutput.h Add yolov3detectionoutput test and AVX optimization (#1994) 5 years ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

No Description

C++ C Python Text Protocol Buffer other