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.
1169 Commits
5 Branches
354 MB
1 Download
 
 
 
 
 
 
Tree: e2bd4eae6e
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'e2bd4eae6e'
${ noResults }
ncnn/src
nihui e2bd4eae6e write shape as 4-number tuple 6 years ago
..
layer fix compile warnings (#1518) 6 years ago
CMakeLists.txt add cmake folder property (#1483) 6 years ago
allocator.cpp do not enforce coherent memory type, queue transfer after uploading model weight 6 years ago
allocator.h the initial auto test (#1464) 6 years ago
benchmark.cpp new int8 implement,better accuracy (#749) 7 years ago
benchmark.h decouple modelbin of different input types, simplify timestamp function 8 years ago
blob.cpp layer holds bottom blob scale, depthwise convolution read group scales 7 years ago
blob.h ncnnoptimize shape inference, load shape hint 6 years ago
command.cpp staging buffer has its offset 6 years ago
command.h do not enforce coherent memory type, queue transfer after uploading model weight 6 years ago
convert_ycbcr.comp reimplement sfp afp conversion macro as function style buffer load store, drop lds shader for the moment 6 years ago
cpu.cpp fix null fp handling 6 years ago
cpu.h add ncnn source qwq 9 years ago
datareader.cpp Fix warnings on Visual Studio (#1422) 6 years ago
datareader.h Fix warnings on Visual Studio (#1422) 6 years ago
gpu.cpp do not enforce coherent memory type, queue transfer after uploading model weight 6 years ago
gpu.h the initial auto test (#1464) 6 years ago
layer.cpp new layer attribute support_packing 7 years ago
layer.h ncnnoptimize shape inference, load shape hint 6 years ago
layer_declaration.h.in fix: avoid rebuilding after cmake 7 years ago
layer_registry.h.in fix: avoid rebuilding after cmake 7 years ago
layer_shader_registry.h.in [WIP] vulkan compute (#618) 7 years ago
layer_shader_spv_data.h.in [WIP] vulkan compute (#618) 7 years ago
layer_type.h move layer type enum to separate header 8 years ago
layer_type_enum.h.in fix: avoid rebuilding after cmake 7 years ago
mat.cpp int8 code refactoring wip, add int8 test 6 years ago
mat.h ncnnoptimize shape inference, load shape hint 6 years ago
mat_pixel.cpp Fix warnings on Visual Studio (#1428) 6 years ago
mat_pixel_android.cpp vkimagemat, vkimageallocator, convenient construct from android hardware buffer 6 years ago
mat_pixel_resize.cpp Fix warnings on Visual Studio (#1428) 6 years ago
mat_pixel_rotate.cpp fix build with ndk-r16b 6 years ago
modelbin.cpp Fix warnings on Visual Studio (#1428) 6 years ago
modelbin.h data reader wrapper, fix #1325 6 years ago
net.cpp write shape as 4-number tuple 6 years ago
net.h shader pack8 option works 6 years ago
opencv.cpp optional image pixel api, fix #434 8 years ago
opencv.h Fix min/max macro issue (#1346) 6 years ago
option.cpp shader pack8 option works 6 years ago
option.h shader pack8 option works 6 years ago
paramdict.cpp Fix warnings on Visual Studio (#1422) 6 years ago
paramdict.h load param value type 6 years ago
pipeline.cpp vkimagemat, vkimageallocator, convenient construct from android hardware buffer 6 years ago
pipeline.h baseclass Pipeline use virtual destruction (#1504) 6 years ago
platform.h.in fix build with android api >= 26 6 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