nihui
/
ncnn
Not watched
1
0
Fork 0
Code
Releases 46 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
1981 Commits
5 Branches
354 MB
2 Download
Tree: 3631c1933d
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '3631c1933d'
${ noResults }
Commit Graph

1981 Commits (3631c1933dadc3b50d4c384bfce548b609f26acc)
 

Author SHA1 Message Date
  nihuini 3631c1933d non-inlined addref and release slows down overall speed, move them to header 5 years ago
  nihui e9cc637573
arm neon optimization for int8 packing kernels (#2809) 5 years ago
  nihui d7cbc055f3
fix illegal instruction on pi4 when NCNN_ARM82 enabled 5 years ago
  teng cc8e7a13fa
Update operation-param-weight-table (#2811) 5 years ago
  DC Technology 86e53b35db
add Apple M1 benchmark (#2810) 5 years ago
  nihuini 256754bff9 fix build with old gcc, fix #2805 5 years ago
  teng a90a31d340
doc spelling mistakes (#2804) 5 years ago
  zhiliu6 61cd9da55b
optimize x86 3x3 pack8 leftover (#2797) 5 years ago
  nihuini 912e81d086 fix tanh neon, fix #2751 5 years ago
  nihuini 6c41822d35 do not remove optional hidden output for lstm/gru/rnn 5 years ago
  nihuini 5e85f447e6 convert mxnet channel padding, fix some lgtm warnings 5 years ago
  Cai Shanli 8011aea8c8
Update release-python.yml (#2794) 5 years ago
  nihui 32b48f0157 fix int8 auto pack layout 5 years ago
  nihui 1ea8bfbd2e x86 avx2 conv3x3s1 pack8 direct optimization, fix #2789 5 years ago
  ncnnnnn 6e6cb9f4f3
simple sort ncnn_add_layer_test (#2790) 5 years ago
  nihui a48bf43ef7 test conv/fc int8 with activation 5 years ago
  nihui 5fe75f19ef
architecture changes for int8 packing (#2771) 5 years ago
  nihui d4a7abc218 fix onnx2ncnn clip without max blob, fix #2788 5 years ago
  nihui eaee64c782 export vkcommand and vkcompute 5 years ago
  nihuini e86799e95f fix get_big_cpu_count return zero on smp cpu 5 years ago
  nihui 7c079b853e
default to big cpu count 5 years ago
  restyled-io[bot] 5f00ba89d2
feat(ncnnoptimize): replace denormals to zero on layers with weights (#2690) 5 years ago
  nihui 19c183cacc fix ncnnoptimize default cut range 5 years ago
  restyled-io[bot] 5e565cfa8a
Restyle add net Cut Function (#2763) 5 years ago
  Cai Shanli e9a61b3e64
fix python return value policy (#2756) 5 years ago
  nihui 67e24e0703
use local pool allocator (#2736) 5 years ago
  Cai Shanli 64ef781a9c
add test python vulkan (#2754) 5 years ago
  nihuini 15d63ec0f5 fuse onnx multiheadattention with same qkv blob 5 years ago
  Cai Shanli f5b307689b
fix net and extractor destroy order when use vulkan (#2732) 5 years ago
  RBelogorodtsevFBase 1212ed6e94
implements gelu activation (#2749) 5 years ago
  PENGUINLIONG 2d31868389
Trouble shooting guide for Vulkan on NVIDIA GPUs (#2731) 5 years ago
  nihui b58cd14678 fix non arm-neon build 5 years ago
  nihui 0870bf45b1 optimize warpaffine family 5 years ago
  nihuini e449435dbe fix mlir2ncnn warning, prettier alignment :) 5 years ago
  nihuini c8ccccf045 adapt mlir changes 5 years ago
  nihuini c17eb4e208 multiheadattention layer 5 years ago
  Zhiqiang Wang 2c370b2c58
Fix typo in docs (#2727) 5 years ago
  nihuini b51959802c fix buffer2host copy, fix #2725 5 years ago
  nihuini b0d16325b1 fuse onnx binaryop with scalar 5 years ago
  Cai Shanli 2edb3ed7a4
nanodet python demo (#2723) 5 years ago
  nihuini f7cbcaa72b fix onnx normalize expand ghost shape 5 years ago
  nihuini c910574b5b fuse onnx multiheadattention 5 years ago
  teng c3466a7798
fix array index out of bounds in examples/yolact.cpp (#2722) 5 years ago
  RangiLyu ecf1f413b4
fix duplicate variable name in examples/nanodet.cpp (#2719) 5 years ago
  nihuini f2a5ea7678 fix layernorm ghost input without affine 5 years ago
  nihuini 7ac23ab34d fuse onnx layernorm, fix 2-dim layernorm implementation, add test 5 years ago
  zhiliu6 57397c418d
Optimize general AVX2 convolution. (#2714) 5 years ago
  Xu Yang fd634e9a58
remove unnecessary mat clone when NCNN_BENCHMARK enabled (#2708) 5 years ago
  Dahan Gong cbd410c237
fix broken inplace forward (#2709) 5 years ago
  restyled-io[bot] 8c9bea2322
Restyle faster bbox calculation by background score (#2693) 5 years ago