214 Commits (18833c92861300a731047619fbffef4cd8ac47c2)

Author SHA1 Message Date
  nihuini 18833c9286 convert asymmetric pad parameter 6 years ago
  nihuini 9a6ee37eef asymmetric padding parameter for convolution and deconvolution family 6 years ago
  nihui 49206ea03c eliminate useless reshape for mbv3 6 years ago
  nihuini f5ca997a66 fuse x * hardsigmoid to hardswish 6 years ago
  nihuini 46bfb4bca9 write hardswish parameter 6 years ago
  nihuini da6a42ed96 fix onnx2ncnn build 6 years ago
  nihuini 012fdd46de convert onnx hardsigmoid hardswish, op chain fusion code reconstructed 6 years ago
  nihuini eced73c186 convert mxnet onnx pooling count_include_pad 6 years ago
  xunings 481fe0808a Write necessary data for memorydata in ncnnoptimize. (#1194) 6 years ago
  Howave a2647b5d29 Fix for MemoryData params in ncnn optimize tool (#1188) 6 years ago
  Howave ac60acfad0 Fix for onnx2ncnn Div op (#1187) 6 years ago
  nihuini 1b910efea5 convert slice properly 6 years ago
  nihuini ad9e0a9725 read reshape shape data from raw_data, fuse onnx reshape-transpose-reshape to shufflechannel 6 years ago
  nihuini 90f4e0f31c update the latest onnx proto 6 years ago
  nihuini 7dd4bccf95 convert mxnet _contrib_BilinearResize2D 6 years ago
  Chang Si d3be711c52 fix onnx2ncnn bug in Slice layer 6 years ago
  Natsu 6d1944f2c3 CMake improvement (#1115) 6 years ago
  tpoisonooo 1ca4387c9c Auto choose conv implementation (#1085) 6 years ago
  wincle fb9309e460 implement reflect padding. 6 years ago
  wincle d1a1a0dbcd fix onnx2ncnn padding bug. fix #1103 6 years ago
  wincle bb6b93568d Tanh Support 6 years ago
  Arnaud Brejeon e30464cdba Fix bug #1093 (#1094) 6 years ago
  daquexian dbe8a32082 Add onnx resize op 7 years ago
  BUG1989 bcfe9f453f initial the ncnn post training quantization tools (#1067) 7 years ago
  nihui affac77b6f
add info for brocolli 7 years ago
  Howave 123ca35e00 fix compile warnings (#1042) 7 years ago
  nihui af950819cd convert add_n and ElementWiseSum, fix #1008 7 years ago
  nihui 07260527fc fix activation params 7 years ago
  nihui 3e003ffd98 fuse sigmoid 7 years ago
  nihui d46c5989e1
mention practical-pytorch-to-onnx-to-ncnn 7 years ago
  nihui 8a3955dde7 delete tensorflow2ncnn/pytorch2ncnn, it never works 7 years ago
  nihuini 7c5fd53855 parse tensor info 7 years ago
  nihuini dbef56df47 write graph 7 years ago
  nihuini ed2e441a1d fix write fp16 weight with tag 7 years ago
  nihuini 81fda4d6d7 ncnnoptimize save fp16 storage weight 7 years ago
  nihuini 01807482f2 parse pt file 7 years ago
  nihuini 48a1cb4052 more optimize routines ... 7 years ago
  ShuangLiu1992 98bb0bb243 Update onnx2ncnn.cpp (#948) 7 years ago
  nihui 2fe769f314 update fused param files, enable ncnnoptimize tool build 7 years ago
  nihui 99b81b2ee9 eliminate dropout 7 years ago
  nihuini 3f85cafc08 fuse relu leakyrelu clip into convolution/deconvolution/innerproduct 7 years ago
  nihuini 5e98a8799c fuse deconvolution batchnorm 7 years ago
  nihuini 7984ffcb4d ncnnoptimize tool 7 years ago
  791136190 e2e8e1b9d7 mxnet2ncnn tool support symbol.softmax op (#938) 7 years ago
  nihuini 1dea9fe353 more elementwise binaryop alias, convert priorbox steps param 7 years ago
  nihui 7ab968e6e1 fix gpu crop, convert crop offset with axis 7 years ago
  Gemfield c625471784 Fix ncnn2mem crash issue (#857) 7 years ago
  Gemfield 506d9f74aa eliminate the warning msg when compile the onnx2ncnn (#850) 7 years ago
  Gemfield d91d7419eb Add upsample linear mode (#846) 7 years ago
  Gemfield 5407deb5ce Apply splitcnn function to graph input (#844) 7 years ago