nihui/ncnn - ncnn - 开源协同云脑生态支撑系统

Commit Graph

Author	SHA1	Message	Date
nihuini	4cf4c92ee6	better shape format for per-layer benchmark	5 years ago
nihui	db814e1640	reduce innerproduct gemm gpu memory usage (#2618 )	5 years ago
nihui	4cd1a5c0e3	simplify innerproduct x86 arm packing class	5 years ago
nihui	80499bd64a	enable VK_LAYER_KHRONOS_validation layer in modern vulkan sdk	5 years ago
Evgeny Proydakov	db8a747351	Fixed compile warning in 'eltwise_vulkan.cpp'. [-Wunused-variable] (#2612 )	5 years ago
nihui	74451897cb	handle gemm in innerproduct (#2607 )	5 years ago
nihui	af7d8184aa	handle image allocation failure properly	5 years ago
nihui	0a59ac9b16	integer warpaffine (#2604 ) * integer warpaffine * fix some corner case * fix yuv420sp border value	5 years ago
nihuini	34557fb134	memorydata upload packed data, fix #2599	5 years ago
nihui	4f2907d129	arm neon optimization for rnn (#2601 )	5 years ago
nihui	6672b09a37	arm neon optimization for gru (#2597 )	5 years ago
nihui	0b35540c72	arm neon optimization for lstm (#2595 )	5 years ago
nihui	e243edf991	interp align_corner vulkan implementation	5 years ago
nihuini	f3eddada51	fix arm82 packing	5 years ago
nihuini	3915b5d496	arm neon optimization for packing fp16/bf16 pack8 family	5 years ago
nihui	fca04980f3	enhance padding test (#2580 ) * workaround nvidia driver crash * workaround radv buffer_ld1 zero bug * fix offset elempack	5 years ago
nihui	09b2bf6213	Break down forward_layer (#2577 )	5 years ago
nihui	ef3550b52f	gru and rnn layer (#2572 )	5 years ago
Guoxia Wang	13d0bfcfd0	fix onnx2ncnn adaptive pool conversion bug, remove no used weights node (#2570 )	5 years ago
nihuini	9b949d65b3	fuse onnx lstm, codeformat exclude pybind11, fix #2562	5 years ago
ncnnnnn	f1c19c1090	pooling_x86_unused_opt (#2565 )	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
Zhuo Zhang	aac39e917f	fix mingw-x64 compilation for PC SIMD (#2554 )	5 years ago
tpoisonooo	baf49574c4	innerproduct aarch64 use gemm (#2521 ) * perf(innerproduct-arm): add aarch64 gemm * fix(innerproduct): fix compilation errror * fix(armv7-innerproduct): fix armv7 compilation error * fix(innerproduct): fix gemm param * fix(int8): update mock scales and fix runtime error * fix(compilation): fix compilation error	5 years ago
nihui	ce7ac39a96	include arm82 on native macos arm64, supp fix	5 years ago
nihui	54c0a13b9f	build shared library (#2525 ) * build shared lib and enable lto * reserved for layer and option * allocator pimpl * datareader pimpl * paramdict pimpl, disable copy assign for allocator and datareader * modelbin pimpl * net extractor pimpl * gpu pimple * disable copy assign vulkandevice, code format * command pimpl, dummy image readonly * pipeline pipelinecache pimpl, export platform class * code format, export simple family * update ci * disable lto on android armv7, merge webassembly ci * link libgcc, fix macos dylib version * pipeline pimpl, gpu info pimpl * destroy gpu info after vulkan device * ignore msvc stl class warning * fix ncnn_paramdict_get_float return type * fix vktransfer upload fp16 without flatten, add command test	5 years ago
Zhuo Zhang	a0a8c8e10a	fix typo in mat.h's comment (#2537 ) * fix typo in mat.h's comment * inplacc => inplace	5 years ago
Zhuo Zhang	0bade9e6d0	fix typo in cpu.h's comment (#2538 )	5 years ago
Cai Shanli	bf845a6fe3	add python (#2514 ) * add python * check elempack when convert ncnn.Mat to numpy.ndarray fix build with NCNN_STRING=OFF	5 years ago
nihuini	fbf0ffda53	pixelshuffle nhwc mode, convert onnx DepthToSpace mode DCR, convert mlir tf.DepthToSpace	5 years ago
nihuini	b35b06be6d	reorg nhwc mode, code format	5 years ago
nihui	82c4acc187	conv1x1s1 and packing pack4 x86 optimization, fix #2510 fix #2509	5 years ago
nihui	25506cfba0	fix build	5 years ago
nihui	1040f40c8b	update c api for custom allocator datareader modelbin and layer registration, add cookie userdata to layer	5 years ago
nihui	2b7b92b726	update c api allocator	5 years ago
nihui	017440c1ca	update c api allocator	5 years ago
nihuini	27e9795198	update c api	5 years ago
nihuini	4114d333c9	low-level op api for C api	5 years ago
nihui	79efe33fdc	cmake option for platform api uses (#2502 ) * cmake option for platform api uses * adroid gpu ci does not rely on glslangvalidator, add android termux ci	5 years ago
nihui	343bc3b7dc	single blob consumer (#2493 )	5 years ago
Zhuo Zhang	3c99287da5	fix src/net.cpp missing-field-initializers warning (#2494 )	5 years ago
nihui	c324149709	ci vs2015 (#2492 ) * add vs2015 ci * build x86 binary	5 years ago
maxfy1992	0f325d7910	add decrease unpack pack overhead (#2489 ) Co-authored-by: yangfengmax <yangfengmax@didichuxing.com>	5 years ago
nihuini	2b6213cc1e	link jnigraphics for android bitmap api	5 years ago
Cai Shanli	a9df4f6c59	add custom layer destroyer (#2481 ) * add custom layer destroyer * set default layer destroyer with 0	5 years ago
Zhuo Zhang	361847c827	check NCNN_MAX_PARAM_COUNT (#2458 )	5 years ago
sunnycase	124d2c3d85	Support V831 (#2478 )	5 years ago
nihuini	5650b77054	fix gpu extension conditions	5 years ago
nihuini	e2cb635a35	fix header install	5 years ago
nihui	1f44e5c6a3	enable ios arm64e (#2475 ) * enable ios arm64e * fix build with old vulkan sdk * link vulkan loader on macos, fix ios moltenvk library path * there is no moltenvk arm64e library atm, link moltenvk directly for macos-arm64	5 years ago

1 2 3 4 5 ...

1196 Commits (4cf4c92ee69bcc7c367d75c6cfb51bc967d9062f)