nihui/ncnn - ncnn - 开源协同云脑生态支撑系统

Commit Graph

Author	SHA1	Message	Date
Zhuo Zhang	d5d69e32a8	fix tools/mxnet/mxnet2ncnn.cpp sign-compare warning (#2394 )	5 years ago
Zhuo Zhang	d8866eba56	fix tools/ncnnoptimize.cpp sign-compare warning (#2393 )	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	ba364791e8	reshape x86 pack4	5 years ago
nihui	60df2740a7	fix potential int64 overflow in int array conversion	5 years ago
nihui	60b6cc32ef	replace_reduction_with_global_pooling replace_prelu_with_leaky_relu	5 years ago
nihuini	c5b8e2957e	convert onnx channel pad	5 years ago
Leo	cab255f107	Fix compile failure when NCNN_PIXEL off (#2260 ) * fix compiling failure on cxx14 * fix compile failure when NCNN_PIXEL off * do not export pixel api when NCNN_PIXEL off * disable squeezenet test when NCNN_PIXEL off * do not build ncnn2table and examples when NCNN_PIXEL off * make cmakedefine header independent * restore platform.h.in Co-authored-by: nihui <shuizhuyuanluo@126.com> Co-authored-by: nihuini <nihuini@tencent.com>	5 years ago
nihuini	7836a143ec	print input and output blob names, print estimated runtime memory footprint	5 years ago
maxfy1992	a106baa3b8	add interp param align_corner (#2236 ) * add interp param align_corner add check support_vulkan after create_pipeline for tests * code style Co-authored-by: yangfengmax <yangfengmax@didichuxing.com>	5 years ago
nihuini	b3bbc1b8e9	update tensorflow dialect, adpat mlir api changes	5 years ago
Martin Han	c110e5ca6d	Add docs for keras2ncnn tools (#2286 ) * Add readme for keras2ncnn * Add supported model variants * Fix supported model variants	5 years ago
nihuini	88d1efc9b1	convert onnx MatMul to Gemm	5 years ago
ncnnnnn	c44a521dbc	removewarn onnx2ncnn vs2017 c4267 (#2271 )	5 years ago
ncnnnnn	21974d8218	removewarn ncnnmerge C4267 (#2269 ) * fix vs2017 nmake warning C4267: 'initializing': conversion from 'size_t' to 'int' * removewarn vs2017 nmake warning C4267: '+=': conversion from 'size_t' to 'int', possible loss of data Co-authored-by: sf <sf@sf.sf>	5 years ago
nihuini	a742979fea	do not fuse mlir scalar mul-add pattern	5 years ago
nihuini	d0e6b256f9	drop obsoleted aarch64 auto conv mode, print mac after ncnnoptimize shape inference	5 years ago
nihuini	ac47a05488	fix onnx groupnorm conversion, ncnnoptimize support groupnorm, fix #2142	5 years ago
nihuini	0a533dcaac	mlir2ncnn fuse keras batchnorm, handle instancenorm affine in ncnnoptimize	5 years ago
nihui	a00beac906	ncnnmerge for merging multiple models into one	5 years ago
nihuini	245e31ebca	adapt mlir api changes	5 years ago
Zhuo Zhang	3f739a4e6e	fix onnx2ncnn.cpp integer multiply may overflow (#2214 )	5 years ago
Zhuo Zhang	cf31fda387	fix darknet2ncnn.cpp warnings (#2209 ) * fix darknet2ncnn.cpp warnings * revoke extra warning check	5 years ago
Evgeny Proydakov	4973773b35	Fixed compile warnings for gcc linux build. [-Wunused-result] (#2199 )	5 years ago
fawdlstty	1d1cb29869	Fixed compile warning due to default cast (#2201 )	5 years ago
deepage	322095e629	Update onnx2ncnn.cpp (#2189 )	5 years ago
deepage	0690995b1a	Update caffe2ncnn.cpp (#2188 )	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
Evgeny Proydakov	a5b8ca8502	Fixed compile warning for macos in caffe2ncnn (-Wformat) (#2162 )	5 years ago
nihuini	7b5b829143	adapt mlir api changes	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
nihuini	cd7f59d25b	adapt mlir dialect registration changes	5 years ago
youzainn	266382a832	fix cmake 3.5.1 config error (#2067 ) * fix cmake 3.5.1 config error * fix ubuntu16.04 build error	5 years ago
youzainn	3b1b41ec0b	Add some compile options, add vulkan dependency export (#2062 ) * vulkan cmake export templete * 1) vulkan cmake dependency export. 2) support opencv_world import. 3) add BUILD_WITH_STATIC_CRT option * Threads dependency * NCNN_BUILD_WITH_STATIC_CRT option * we do not support cmake before version 3.15 for option NCNN_BUILD_WITH_STATIC_CRT	5 years ago
ruru5697	e58a35aa65	fix darknet2ncnn maxpool padding size (#2038 ) * fix maxpool padding size * restyle	5 years ago
Zhuo Zhang	0fc5ee1383	fix #2056 (#2057 )	5 years ago
nihuini	63247a32a7	mlir fix keras conv2d dense bias, fix pooling type	5 years ago
nihuini	6a15cb1a0e	mlir fuse keras conv2d dense	5 years ago
nihuini	d279e1f514	mlir fuse instancenorm without affine	5 years ago
nihuini	78580dc648	sync tf dialect, mlir fuse instancenorm	5 years ago
nihuini	ea17a46b34	fuse memorydata split binaryop	5 years ago
nihui	1cb55454eb	fix onnx2ncnn resize crash with optional sizes	5 years ago
nihuini	7b3ab5024d	convert to gemm layer	5 years ago
nihuini	4b470949c2	update tf2 dialect, adapt new mlir api, convert tf.Maximum tf.Minimum tf.ResizeBilinear	6 years ago

1 2 3 4 5 ...

376 Commits (d5d69e32a8a439e19e3ffb5a01c8fa2431aaa8f7)