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.
471 Commits
5 Branches
354 MB
2 Download
 
 
 
 
 
 
Tree: 9fbaf7fb0b
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '9fbaf7fb0b'
${ noResults }
ncnn/src/layer/arm
nihuini 9fbaf7fb0b coding style changes 7 years ago
..
absval_arm.cpp implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
absval_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
batchnorm_arm.cpp implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
batchnorm_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
bias_arm.cpp implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
bias_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
clip_arm.cpp coding style changes 7 years ago
clip_arm.h coding style changes 7 years ago
convolution_1x1.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
convolution_1x1_int8.h update aarch64 conv1x1s1 int8, speedup 10%. 7 years ago
convolution_2x2.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
convolution_3x3.h aarch64 assembly for conv3x3s1, about 18% speed gain 7 years ago
convolution_3x3_int8.h add aarch64 int8 neon implement 7 years ago
convolution_4x4.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
convolution_5x5.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
convolution_7x7.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
convolution_arm.cpp fix build without neon 8 years ago
convolution_arm.h packed int8 convolution 3x3 stride 1 for armv7, 7%~25% faster than vanilla one, but God knows how hard I try :| 8 years ago
convolutiondepthwise_3x3.h convolution depthwise 3x3 stride 1 with unroll 8 on aarch64 8 years ago
convolutiondepthwise_3x3_int8.h add aarch64 int8 neon implement 7 years ago
convolutiondepthwise_arm.cpp implement the missing dequantize image on armv7, prefer neon-optimized 3-dim dequantize, fix #547 8 years ago
convolutiondepthwise_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
deconvolution_3x3.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
deconvolution_4x4.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
deconvolution_arm.cpp implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
deconvolution_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
deconvolutiondepthwise_arm.cpp fix null sub group elemsize/allocator in depthwise deconvolution, fix #539 8 years ago
deconvolutiondepthwise_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
dequantize_arm.cpp add aarch64 int8 neon implement 7 years ago
dequantize_arm.h armv7 int8 quantize/dequantize and conv1x1s1 8 years ago
eltwise_arm.cpp implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
eltwise_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
innerproduct_arm.cpp core int8 inference, quantize and dequantize, net using flag, caffe2ncnn reads int8 scale table 8 years ago
innerproduct_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
lrn_arm.cpp implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
lrn_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
neon_mathfun.h add ncnn source qwq 9 years ago
pooling_2x2.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
pooling_3x3.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
pooling_arm.cpp implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
pooling_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
prelu_arm.cpp implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
prelu_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
quantize_arm.cpp add aarch64 int8 neon implement 7 years ago
quantize_arm.h armv7 int8 quantize/dequantize and conv1x1s1 8 years ago
relu_arm.cpp implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
relu_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
scale_arm.cpp implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
scale_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
sigmoid_arm.cpp implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
sigmoid_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
softmax_arm.cpp implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 years ago
softmax_arm.h implement ncnn blob/workspace allocator, fine-grained per-layer openmp threads control, fix #469 8 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