nihui
/
ncnn
Not watched
1
0
Fork 0
Code
Releases 46 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
2092 Commits
5 Branches
354 MB
2 Download
Tree: 3774514767
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '3774514767'
${ noResults }
Commit Graph

139 Commits (37745147670441fe042c168b63232fb9e8636310)

Author SHA1 Message Date
  nihuini f9e42d4ee4 drop fp16 and int8 mode from caffe2ncnn, ncnnoptimize and ncnn2int8 should be used instead 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
  nihui d4a7abc218 fix onnx2ncnn clip without max blob, fix #2788 5 years ago
  nihuini 15d63ec0f5 fuse onnx multiheadattention with same qkv blob 5 years ago
  nihuini c17eb4e208 multiheadattention layer 5 years ago
  nihuini b0d16325b1 fuse onnx binaryop with scalar 5 years ago
  nihuini f7cbcaa72b fix onnx normalize expand ghost shape 5 years ago
  nihuini c910574b5b fuse onnx multiheadattention 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
  nihuini 5b72a37544 fix megvii style shufflechannel blob count mismatch 5 years ago
  nihuini f47fbcbf83 preserve the very first onnx constant dimension size when we guess it is not the batchsize one, fix #2487 5 years ago
  nihuini 0e79532975 topological sort onnx nodes, convert onnxruntime bert ops 5 years ago
  nihuini 11c569fc52 fix in-between empty input node 5 years ago
  nihuini 5bd07030ab remove onnx expand shape node 5 years ago
  nihuini 6572e98f66 handle onnx transpose 102 201 after lstm 5 years ago
  nihui ef3550b52f
gru and rnn layer (#2572) 5 years ago
  nihuini cf853bd3ce convert onnx gru rnn graph 5 years ago
  Guoxia Wang 13d0bfcfd0
fix onnx2ncnn adaptive pool conversion bug, remove no used weights node (#2570) 5 years ago
  nihuini 8790de3507 better onnx lstm fusion 5 years ago
  nihuini 9b949d65b3 fuse onnx lstm, codeformat exclude pybind11, fix #2562 5 years ago
  Guoxia Wang 609f63c57e
support PyTorch AdaptiveAvgPool2d and AdaptiveMaxPool2d (#2546) 5 years ago
  nihuini fbf0ffda53 pixelshuffle nhwc mode, convert onnx DepthToSpace mode DCR, convert mlir tf.DepthToSpace 5 years ago
  nihuini 417b6874f8 fix onnx2ncnn printf format error 5 years ago
  nihuini 1963672332 rewrite most onnx2ncnn node_reference and binary weight logic 5 years ago
  Zhuo Zhang 62cdc14200
fix onnx2ncnn.cpp shadowed variables warning (#2443) 5 years ago
  nihuini 75c1f09b5d do not count onnx constant node twice, fix #2425 5 years ago
  nihuini b7440cad2d reserve onnx gemm memorydata, mention #2427 5 years ago
  ncnnnnn 375c4abb6c
remove vs w4305 w4477 (#2422) 5 years ago
  Zhuo Zhang 0de350ad3e
fix tools/onnx/onnx2ncnn.cpp sign-compare warning (#2395) 5 years ago
  nihuini 14ba698034 onnx matmul can have input from memorydata 5 years ago
  nihuini a260a19619 fuse onnx expand before broadcasting binaryop 5 years ago
  ncnnnnn 79ae0028c9
try onnx2ncnn add softplus (#2361) 5 years ago
  nihui 60df2740a7 fix potential int64 overflow in int array conversion 5 years ago
  nihuini c5b8e2957e convert onnx channel pad 5 years ago
  maxfy1992 a106baa3b8
add interp param align_corner (#2236) 5 years ago
  nihuini 88d1efc9b1 convert onnx MatMul to Gemm 5 years ago
  ncnnnnn c44a521dbc
removewarn onnx2ncnn vs2017 c4267 (#2271) 5 years ago
  nihuini ac47a05488 fix onnx groupnorm conversion, ncnnoptimize support groupnorm, fix #2142 5 years ago
  Zhuo Zhang 3f739a4e6e
fix onnx2ncnn.cpp integer multiply may overflow (#2214) 5 years ago
  deepage 322095e629
Update onnx2ncnn.cpp (#2189) 5 years ago
  Evgeny Proydakov 3d7feb7cce
Fixed compile warning for clang linux onnx2ncnn.cpp [-Wformat] (#2185) 5 years ago
  Evgeny Proydakov ecc63a6d52
Fixed compile warning for macos in caffe2ncnn/onnx2ncnn (-Wdeprecated-declarations) (#2180) 5 years ago
  Evgeny Proydakov b93775a272
Fixed compile warning for macos clang in onnx2ncnn (-Wformat) (#2175) 5 years ago
  nihui 2384fad8e0 recognize more binaryop with constant 5 years ago
  nihuini 3a4d716db4 onnx2ncnn fuse pixelshuffle downsample to reorg 5 years ago
  nihuini d5f2220ee7 fuse onnx groupnorm 5 years ago
  nihui 1cb55454eb fix onnx2ncnn resize crash with optional sizes 5 years ago
  nihuini 7b3ab5024d convert to gemm layer 5 years ago