nihui/ncnn - ncnn - 开源协同云脑生态支撑系统

Commit Graph

Author	SHA1	Message	Date
lll143653	d355b6dc5b	Add warning and recommend to use pnnx (#5588 )	1 year ago
Amir Ramezani	7e5fa3ade3	shrink operator (#5022 )	2 years ago
Amir Ramezani	0ea587b8c7	celu activation vulkan and onnx conversion (#5018 )	2 years ago
Amir Ramezani	695f770eab	erf implementation (#5012 ) * added erf implementation * added testcase for erf * added onnx2ncnn support of erf	2 years ago
nihui	cd1c0d6eab	fix build with new protobuf target (#4955 )	2 years ago
nihui	39721eeb94	require c++17 for building with new protobuf (#4947 )	2 years ago
huoshuai-dot	f7f6ca0033	Update onnx2ncnn.cpp (#4754 )	3 years ago
Zhang Ge	3fce00b260	fix param parsing issue when layer/blob name exceeds 255 (#4236 ) * fix param parsing issue when layer/blob name exceeds 255 * apply code-format changes Co-authored-by: ZhangGe6 <ZhangGe6@users.noreply.github.com>	3 years ago
tpoisonooo	6fd801b6d7	feat(src/layer): add vision_transformer benchmark (#3730 ) * feat(src/layer): add vision_transformer benchmark and relative layer * refactor(testutil.h): add para for RandomMat	4 years ago
nihui	3181616439	treat old reduction axes param as failure	4 years ago
nihuini	f02b259a15	convert some pnnx reduction family	4 years ago
Jimmy	52c6502ae7	Feature/ncnntool/add install (#3212 )	4 years ago
nihui	3d5f447260	fix onnx negative concat axis, fix #3194	4 years ago
q.yao	41aa601413	fix fuse expand (#3189 )	4 years ago
nihuini	c5d003001c	preserve lstm hidden output	4 years ago
nihuini	9afbfdd9dd	ncnnoptimize fuse rsub rdiv with scalar	4 years ago
li mengyang	be054aacb0	some misspell (#3046 ) * just a spell check * some misspell	4 years ago
nihui	4f135e07bf	implement convolution1d and pooling1d (#3035 ) * implement convolution1d and pooling1d * add conv1d pool1d test * fuse convolution1d activation * update operator doc * fix vulkan adpative pooling	4 years ago
nihuini	72282f8b1a	fix blob count when there are orphaned weight nodes, fix #2969	5 years ago
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 ) * support pytorch adaptive pool * support onnx2ncnn adaptive pool convert * support ncnnoptimize adaptive pool param write * fix adaptive pool out_shape order * fix adaptive pool out_shape order, H and W can be either a int add test case, set support_vulkan = false Pooling_vulkan::create_pipeline * review adaptive pool * fix typo * add adaptive pool forward in pooling_x86.cpp pooling_arm.cpp fix out_w, out_h id naming convention * fix typo * don't support packing, bf16, int8, image for adaptive pool * Restyled by clang-format * Restyled by astyle * Restyled by clang-format * Restyled by astyle Co-authored-by: Restyled.io <commits@restyled.io>	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

1 2 3 4

165 Commits (f1bdc87478c64e0dfdba3d679e6e0dfd4b84df80)