ncnn - Release 20250503

- C++
Published by github-actions[bot] 10 months ago

ncnn - android ios macos linux windows webassembly watchos tvos visionos 预编译库 20250428 205ca50

编译版本，默认配置，android-ndk-r28b，xcode 15.2，ubuntu-22.04，ubuntu-24.04，vs2015，vs2017，vs2019，vs2022，emscripten-3.1.28 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 + riscv64 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 + riscv64 | |ncnn-apple.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst + watchos + watchos-simulator + tvos + tvos-simulator + visionos + visionos-simulator | arm64 + arm64e + x8664 | |ncnn-apple-vulkan.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst + watchos + watchos-simulator + tvos + tvos-simulator + visionos + visionos-simulator，支持 GPU | arm64 + arm64e + x8664 | |ncnn-ios.zip | ios 静态库 | arm64 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU | arm64 | |ncnn-ios-simulator.zip | ios simulator 静态库 | x8664 + arm64 | |ncnn-ios-simulator-vulkan.zip | ios simulator 静态库，支持 GPU | x8664 + arm64 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-mac-catalyst.zip | mac catalyst 静态库 | x8664 + arm64 | |ncnn-mac-catalyst-vulkan.zip | mac catalyst 静态库，支持 GPU | x8664 + arm64 | |ncnn-watchos.zip | watchos 静态库 | armv7k + arm6432 | |ncnn-watchos-simulator.zip | watchos simulator 静态库 | x8664 + arm64 | |ncnn-tvos.zip | tvos 静态库 | x8664 + arm64 | |ncnn-tvos-vulkan.zip | tvos 静态库，支持 GPU | x8664 + arm64 | |ncnn-tvos-simulator.zip | tvos simulator 静态库 | x8664 + arm64 | |ncnn-tvos-simulator-vulkan.zip | tvos simulator 静态库，支持 GPU | x8664 + arm64 | |ncnn-visionos.zip | visionos 静态库 | arm64 | |ncnn-visionos-vulkan.zip | visionos 静态库，支持 GPU | arm64 | |ncnn-visionos-simulator.zip | visionos simulator 静态库 | x8664 + arm64 | |ncnn-visionos-simulator-vulkan.zip | visionos simulator 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x86_64 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x64 + arm + arm64 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

x86 convolution int8 gemm xop/avx2/avx512/avx512vnni/avxvnni/avxvnniint8优化 risc-v eltwise rvv优化(@xfan1024) risc-v bias rvv优化(@AtomAlpaca) risc-v bnll rvv优化(@AtomAlpaca) risc-v celu rvv优化(@AtomAlpaca) 重构reduction/quantize/dequantize/requantize减小二进制体积 softmax支持4维输入计算，优化支持任意elempack param模型文件支持字符串类型的参数值，支持自然写法的数组 reshape支持表达式动态shape，不再支持reshape内permute参数 crop支持表达式动态slice interp支持表达式动态output size 设置openmp环境变量解决多个openmp冲突问题和绑核失败问题 防止cmake编译器检测的优化导致的误识别 改善windows7+系统中的cpu大小核检测(@futz12) 修复HarmonyOS NEXT getelfhwcap返回空的问题(@peerless2012) 添加apple a18和m4系列的cpu型号识别 修复在cpu l2<1M时可能的convolution int8 gemm计算错误 修复android编译可能的重定义VKUSEPLATFORMANDROIDKHR问题 修复mips/loongarch/risc-v架构开启simplemath编译问题 extractor clear()重置local allocator为0，修复多次clear的警告问题 绕过nvidia新驱动下padding可能的程序卡死问题 ncnn2table量化校准工具支持读取npy数据(@wxqwinner) ncnn2int8量化工具默认使用fp16类型保存权重 改善ncnn单元测试编译耗时 优化cmake ncnnaddlayer()的vulkan shader收集性能(@maxint) 更新最新glslang glsl编译时自动定义设备相关属性和特性的宏 glsl编译时自动定义ncnnglslversion宏 option结构体添加vulkan device index 清理目前comp源码中通用的扩展适配，已自动定义 支持在vulkan shader代码中使用NCNNLOGE函数打印 检测vulkan扩展 VKEXTsubgroupsizecontrol/VKKHRshadersubgroupextendedtypes/VKKHRzeroinitializeworkgroupmemory/VKKHRshadersubgrouprotate/VKEXTshaderatomicfloat/VKEXTshaderatomicfloat2/VKKHRshadernonsemanticinfo 修复risc-v ci c906/908/910/k1静态链接libgomp的错误 支持cmake-4.0编译 pip编译pyncnn支持使用系统cmake和ninja(@mgorny) pnnx更新到torch-2.7 pnnx重构pass-level1代码，实现更快速编译 pnnx支持从tnn模型转换到pytorch/ncnn pnnx支持转换onnx非对称Conv/Depth2Space，添加pixelshuffle/pixelunshuffle单元测试 pnnx支持转换GlobalAvgPool/ReduceL1/ReduceL2，添加onnx adaptive avg/max pool和norm单元测试 pnnx优化expression中的类型转换 pnnx转换gelu fast模式 pnnx兼容默认sdpa scale参数到ncnn的转换 pnnx合并wav2vec风格的mha pnnx修复conv+bias合并中bias shape错误问题 pnnx修复instancenorm2d/instancenorm3d的num_featuers错误问题 pnnx转ncnn正确处理squeeze/unsqueeze引起的batch轴变动 pnnx转ncnn正确处理reshape引起的batch轴变动 pnnx修复i64转ncnn失效的问题(@Baiyuetribe) 重构qnx cmake工具链(@zchrissirhcz) ci更新llvmpipe版本 ci新增自动对比库二进制大小 ci迁移到ubuntu-latest，维持code-format在ubuntu-20.04 ci使用apt中的qemu ci更新riscv64 thead工具链 ci更新riscv elf工具链 修复apple平台glslang打包，移除glslang-default-resource-limits依赖 python预编译包发布armv7l neon版本，移除ppc64le和s390x预编译包，修复sdist编译 添加缺失的协议文件头(@erquren) 更新readme yolov8链接(@whyb) 更新文档不再要求安装vulkan-sdk 更新文档有关docker中无法使用vulkan的解决办法 更新yolov8检测/分割/姿态估计/分类/旋转目标检测示例代码和模型 新增macbook-air-m3性能数据(@chainsx) 新增orion o6性能数据(@TheSnowfield)

New Contributors

• @mgorny made their first contribution in https://github.com/Tencent/ncnn/pull/5899
• @erquren made their first contribution in https://github.com/Tencent/ncnn/pull/5925
• @futz12 made their first contribution in https://github.com/Tencent/ncnn/pull/5927
• @wxqwinner made their first contribution in https://github.com/Tencent/ncnn/pull/5930
• @TheSnowfield made their first contribution in https://github.com/Tencent/ncnn/pull/5943
• @peerless2012 made their first contribution in https://github.com/Tencent/ncnn/pull/5951
• @AtomAlpaca made their first contribution in https://github.com/Tencent/ncnn/pull/6005

Full Changelog: https://github.com/Tencent/ncnn/compare/20241226...20250428

- C++
Published by github-actions[bot] 10 months ago

ncnn - android ios macos linux windows webassembly watchos tvos visionos 预编译库 20241226 5285895

编译版本，默认配置，android-ndk-r27c，xcode 15.2，ubuntu-20.04，ubuntu-22.04，ubuntu-24.04，vs2015，vs2017，vs2019，vs2022，emscripten-3.1.28 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 + riscv64 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 + riscv64 | |ncnn-apple.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst + watchos + watchos-simulator + tvos + tvos-simulator + visionos + visionos-simulator | arm64 + arm64e + x8664 | |ncnn-apple-vulkan.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst + watchos + watchos-simulator + tvos + tvos-simulator + visionos + visionos-simulator，支持 GPU | arm64 + arm64e + x8664 | |ncnn-ios.zip | ios 静态库 | arm64 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU | arm64 | |ncnn-ios-simulator.zip | ios simulator 静态库 | x8664 + arm64 | |ncnn-ios-simulator-vulkan.zip | ios simulator 静态库，支持 GPU | x8664 + arm64 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-mac-catalyst.zip | mac catalyst 静态库 | x8664 + arm64 | |ncnn-mac-catalyst-vulkan.zip | mac catalyst 静态库，支持 GPU | x8664 + arm64 | |ncnn-watchos.zip | watchos 静态库 | armv7k + arm6432 | |ncnn-watchos-simulator.zip | watchos simulator 静态库 | x8664 + arm64 | |ncnn-tvos.zip | tvos 静态库 | x8664 + arm64 | |ncnn-tvos-vulkan.zip | tvos 静态库，支持 GPU | x8664 + arm64 | |ncnn-tvos-simulator.zip | tvos simulator 静态库 | x8664 + arm64 | |ncnn-tvos-simulator-vulkan.zip | tvos simulator 静态库，支持 GPU | x8664 + arm64 | |ncnn-visionos.zip | visionos 静态库 | arm64 | |ncnn-visionos-vulkan.zip | visionos 静态库，支持 GPU | arm64 | |ncnn-visionos-simulator.zip | visionos simulator 静态库 | x8664 + arm64 | |ncnn-visionos-simulator-vulkan.zip | visionos simulator 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x86_64 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x64 + arm + arm64 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

embed 支持int8量化 gemm 支持int8量化 multiheadattention 支持int8量化 新增spectrogram和inverse spectrogram实现 arm rmsnorm neon优化 arm layernorm neon fp32/bf16s/fp16s优化 x86 rmsnorm sse2/avx/avx512优化 x86 layernorm sse2/avx/avx512优化 x86 gemm int8 sse2/xop/avx/avx512/vnni/vnniint8优化 更新riscv vector标准到1.0，重写全部ncnn riscv优化代码，自动探测rvv/zfh/zvfh/xtheadvector并分发 riscv gemm rvv优化支持128bit/256bit vlen 禁用x86倒数优化避免可能的精度损失 改善harmonyos cpu拓扑结构abi兼容性 暂时禁用mesa驱动的vulkan矩阵扩展支持 兼容ndk-21编译asimdfhm目标的错误导致的问题 兼容clang-18编译avx512bf16时编译器崩溃的问题 禁用msvc对windows arm平台exp/tanh的svml优化以解决计算错误 探测avxvnniint8/avxvnniint16/avxneconvert指令集 runtime cpu开启时仅使用ncnn cmake内置的编译参数 删除windows arm32支持(@Shironana817) android默认启用16kb pagesize编译，android-api升级到21 vkCreateDevice失败时不直接崩溃(@Upliner) 为powerpc架构跳过0.5附近数值的unaryop round测试用例 pnnx更新到torch-2.5 pnnx支持从traced inputs自动设定inputshape pnnx编译不再输出来自torch头文件的警告 pnnx重排pass level2内的全部顺序，并复用pattern pnnx不再保存debug中间模型(@LJoson) pnnx输出python脚本的onnx导出代码更新到export(@whyb) pnnx合并t5-layernorm为rmsnorm pnnx不再折叠具有动态shape的tensor pnnx在输出的python脚本中使用隐含的int转换避免trace时常数化 pnnx转换Tensor.select为ncnn crop+squeeze pnnx转换onnx constantofshape为torch.zeros/ones pnnx修正onnx clip在可选min/max缺失时的转换问题 ci更新riscv64工具链 ci添加c908/spacemit-x60 ci webassembly兼容node>20 ci android添加riscv64目标并打包 添加vim3 vulkan跑分数据(@GIBEREZ)

New Contributors

• @ankushgoel27 made their first contribution in https://github.com/Tencent/ncnn/pull/5709
• @Shironana817 made their first contribution in https://github.com/Tencent/ncnn/pull/5811
• @GIBEREZ made their first contribution in https://github.com/Tencent/ncnn/pull/5821

Full Changelog: https://github.com/Tencent/ncnn/compare/20240820...20241226

- C++
Published by github-actions[bot] about 1 year ago

ncnn - android ios macos linux windows webassembly 预编译库 20240820 a6d3ef5

编译版本，默认配置，android-ndk-r27，xcode 15.2，ubuntu-20.04，ubuntu-22.04，ubuntu-24.04，vs2015，vs2017，vs2019，vs2022，emscripten-3.1.28 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-apple.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst + watchos + watchos-simulator + tvos + tvos-simulator + visionos + visionos-simulator | arm64 + arm64e + x8664 | |ncnn-apple-vulkan.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst + watchos + watchos-simulator + tvos + tvos-simulator + visionos + visionos-simulator，支持 GPU | arm64 + arm64e + x8664 | |ncnn-ios.zip | ios 静态库 | arm64 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU | arm64 | |ncnn-ios-simulator.zip | ios simulator 静态库 | x8664 + arm64 | |ncnn-ios-simulator-vulkan.zip | ios simulator 静态库，支持 GPU | x8664 + arm64 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-mac-catalyst.zip | mac catalyst 静态库 | x8664 + arm64 | |ncnn-mac-catalyst-vulkan.zip | mac catalyst 静态库，支持 GPU | x8664 + arm64 | |ncnn-watchos.zip | watchos 静态库 | armv7k + arm6432 | |ncnn-watchos-simulator.zip | watchos simulator 静态库 | x8664 + arm64 | |ncnn-tvos.zip | tvos 静态库 | x8664 + arm64 | |ncnn-tvos-vulkan.zip | tvos 静态库，支持 GPU | x8664 + arm64 | |ncnn-tvos-simulator.zip | tvos simulator 静态库 | x8664 + arm64 | |ncnn-tvos-simulator-vulkan.zip | tvos simulator 静态库，支持 GPU | x8664 + arm64 | |ncnn-visionos.zip | visionos 静态库 | arm64 | |ncnn-visionos-vulkan.zip | visionos 静态库，支持 GPU | arm64 | |ncnn-visionos-simulator.zip | visionos simulator 静态库 | x8664 + arm64 | |ncnn-visionos-simulator-vulkan.zip | visionos simulator 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x86_64 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x64 + arm + arm64 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

新增RMSNorm层和对应的pnnx转换，单元测试 x86 convolution tiled gemm优化 量化工具支持 rnn/lstm/gru 动态量化 x86 lstm int8 sse2/xop/avx2/avx512/avx512vnni/avxvnni优化 arm rnn/lstm/gru int8 neon/asimdhp/asimddp优化 multiheadattention支持qdim参数与embeddim不同 multiheadattention支持scale参数 更新pybind11到2.12支持numpy2 添加wasi支持(@quink-black) 添加x86/arm convolution/slice/concat oom单元测试 onnx2ncnn工具添加警告和推荐使用pnnx的信息输出(@lll143653) 修复x86 avx512 vnni指令派发失效的问题 增强x86/arm计算内核在内存不足时的错误返回 仅在windows arm平台使用ruapu指令集探测 windows mingw编译时支持大小核和SMT探测 修复powerpc vsx计算abs可能的错误 修复arm vfpv4条件下可能的fp16s/bf16s同时启用的冲突 修复aarch64架构l2-cache很小时因gemm K分块可能的越界读错误 修复riscv v tanh计算错误(@zhangyang2057) arm/convolution3x3pack1to8fp16s使用ldr/str替代ld1/st1优化(@quink-black) 修复capi无参数函数声明(@quink-black) capi添加setvulkandevice接口(@Baiyuetribe) pyncnn添加从python bytes内存加载模型的接口(@joeyballentine) 为VkAndroidHardwareBufferImageAllocator添加NCNNPLATFORMAPI宏(@Xyzhao1999) 修复mingw64编译时avx崩溃和termux编译错误(@TianZerL) 修复在关闭NCNNBF16时arm riscv编译错误 修复x86-wsl编译时的无用变量警告(@Tabbleman) creategpuinstance()中不进行destroygpu_instance()(@Asd-g) 更新ruapu.h(@lazyparser) 修复ndk-r27在cmake阶段的编译错误(@Galasnow) 添加yolov8示例代码(@whyb) pnnx支持转换dynamo导出的onnx pnnx默认编译onnx2pnnx支持，支持转换conv/convtranspose/pad/linear/softmax/relu/resize/upsample/avgpool/maxpool/batchnorm/lrn/layernorm/instancenorm/groupnorm/rnn/lstm/gru/prelu/gelu/elu/leakyrelu/relu6/celu/hardshrink/hardsigmoid/hardswish/clip/multiheadattention/reducemin/reducemax/reducemean/reducesum/reduceprod/logsoftmax/logsigmoid/mish/selu/sigmoid/silu/softmin/softplus/softshrink/softsign/tanh/tanhshrink/expand/permute/repeat/reshape/select/slice/cat/ceil/chunk/flatten/floor/maximum/minimum/split/squeeze/stack/transpose/unbind/unsqueeze pnnx支持转换onnx指定inputshape pnnx转换onnx遇到动态shape时尝试折叠非动态轴相关的常量 pnnx转换onnx合并简单的shape运算pattern pnnx清除onnx中无用的cast pnnx接受bf16的模型转换和输入输出类型 pnnx转换torch.tile/torch.where/torch.logaddexp pnnx转换无dilation参数的F.maxpool到ncnn pnnx转换1到2个轴参数的torch.roll到ncnn pnnx转换有dim参数的torch.max/torch.min时返回tuple并自动删除没有用到的indice输出 pnnx合并onnx sdpa和qdim mha pnnx识别sdpa的batch轴 pnnx支持torch-2.3和torch-2.4 pnnx不再折叠有就地操作的别名tensor为常量 pnnx转换到的ncnn模型py自动替换long为int ci添加windows clang ci添加harmonyos ci添加mingw(@TianZerL) ci添加esp32和esp32编译文档(@luxincn) 重构release ci脚本 发布ubuntu 24.04预编译包 发布visionos/visionos-simulator vulkan预编译包 pypi发布python 3.13预编译包 更新pytorch/onnx模型转换文档(@whyb) 添加riscv-gnu-toolchain编译文档(@Tabbleman) 添加harmonyos vulkan编译文档(@cugxchen) 修正vulkan-notes文档的错误(@roachsinai) 更新qcom855plus跑分数据 添加RaspberryPi 5 GPU超频跑分数据(@CharlieYu4994) 添加EPYC7742和V100跑分数据(@sakria9) 添加Snapdragon 888跑分数据(@chainsx) 添加RaspberryPi 5 CPU超频跑分数据(@chainsx) 添加OrangePi 5Plus跑分数据(@inspireMeNow) 添加Snapdragon 765G跑分数据(@inspireMeNow) 添加CVITEK SG2000跑分数据(@inspireMeNow) 添加OrangePi CM4跑分数据(@py1066) 添加Axera AX630C跑分数据(@UOPiceman) 添加Kunpeng 920 7260跑分数据(@violet73)

New Contributors

• @quink-black made their first contribution in https://github.com/Tencent/ncnn/pull/5436
• @Tabbleman made their first contribution in https://github.com/Tencent/ncnn/pull/5444
• @roachsinai made their first contribution in https://github.com/Tencent/ncnn/pull/5472
• @Asd-g made their first contribution in https://github.com/Tencent/ncnn/pull/5437
• @lazyparser made their first contribution in https://github.com/Tencent/ncnn/pull/5499
• @CharlieYu4994 made their first contribution in https://github.com/Tencent/ncnn/pull/5518
• @Xyzhao1999 made their first contribution in https://github.com/Tencent/ncnn/pull/5521
• @sakria9 made their first contribution in https://github.com/Tencent/ncnn/pull/5528
• @inspireMeNow made their first contribution in https://github.com/Tencent/ncnn/pull/5550
• @py1066 made their first contribution in https://github.com/Tencent/ncnn/pull/5551
• @UOPiceman made their first contribution in https://github.com/Tencent/ncnn/pull/5559
• @luxincn made their first contribution in https://github.com/Tencent/ncnn/pull/5567
• @zhangyang2057 made their first contribution in https://github.com/Tencent/ncnn/pull/5584
• @violet73 made their first contribution in https://github.com/Tencent/ncnn/pull/5606

Full Changelog: https://github.com/Tencent/ncnn/compare/20240410...20240820

- C++
Published by github-actions[bot] over 1 year ago

ncnn - android ios macos linux windows webassembly 预编译库 20240410 56775de

编译版本，默认配置，android-ndk-r26c，xcode 15.2，ubuntu-20.04，ubuntu-22.04，vs2015，vs2017，vs2019，vs2022，emscripten-3.1.28 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-apple.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst + watchos + watchos-simulator + tvos + tvos-simulator + visionos + visionos-simulator | arm64 + arm64e + x8664 | |ncnn-apple-vulkan.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst + watchos + watchos-simulator + tvos + tvos-simulator + visionos + visionos-simulator，支持 GPU | arm64 + arm64e + x8664 | |ncnn-ios.zip | ios 静态库 | arm64 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU | arm64 | |ncnn-ios-simulator.zip | ios simulator 静态库 | x8664 + arm64 | |ncnn-ios-simulator-vulkan.zip | ios simulator 静态库，支持 GPU | x8664 + arm64 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-mac-catalyst.zip | mac catalyst 静态库 | x8664 + arm64 | |ncnn-mac-catalyst-vulkan.zip | mac catalyst 静态库，支持 GPU | x8664 + arm64 | |ncnn-watchos.zip | watchos 静态库 | armv7k + arm6432 | |ncnn-watchos-simulator.zip | watchos simulator 静态库 | x8664 + arm64 | |ncnn-tvos.zip | tvos 静态库 | x8664 + arm64 | |ncnn-tvos-vulkan.zip | tvos 静态库，支持 GPU | x8664 + arm64 | |ncnn-tvos-simulator.zip | tvos simulator 静态库 | x8664 + arm64 | |ncnn-tvos-simulator-vulkan.zip | tvos simulator 静态库，支持 GPU | x8664 + arm64 | |ncnn-visionos.zip | visionos 静态库 | arm64 | |ncnn-visionos-simulator.zip | visionos simulator 静态库 | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x8664 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x64 + arm + arm64 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

解耦合layer cpu和vulkan，不再使用virtual public继承 支持编译动态库时编译单元测试 单层特性掩码支持禁用多线程 extractor setnumthreads和setvulkancompute现在是无操作 gpu shader增加uniform类型改善adreno上fp16兼容性 检测vulkan矩阵扩展8x8x16配置，fp16a条件下默认使用fp16累加 更新stbimage rvv/neon优化 x86 mish avx512优化(@wnqn1597) riscv gemm fp32 rvv优化(@Xinyu302) 加载模型上传权重时不保留无用的临时数据 c-api新增draw rectangle/text/circle/line接口(@Deepdive543443) 修复armv7平台加载fp16模型sigbus错误 修复reduction L2norm denormal产生inf的问题 修复arm平台pixelresize rounding导致的数值误差 修复softmax arm fp16计算错误 修复risc-v rvv输出fp16没有自动转换的问题 修复destroygpuinstance在驱动加载不完整时crash的问题(@shatyuka) destroygpuinstance等待全部设备idle(@whyb) 修复low-level api没有loadparam直接createpipeline可能的崩溃 修复ncnnoptimize在shape推断的崩溃 ncnnoptimize支持更多新算子，修复gemm权重丢失问题 被调试时候禁用signal指令集检测 windows-arm平台使用ruapu cpu指令集检测 arm vfpv4支持时启用自动转换fp16 在arm64架构中总是报告支持neon和vfpv4 simplevk寻找更多已知的vulkan驱动路径 修复旧cpp标准下risc-v rvv编译错误 修复某些老编译器在debug模式下编译错误 修复uwp平台编译 修复testreduction运行时的警告 修复NCNNPIXELDRAWING禁用时候编译错误(@shatyuka) 支持MSVC使用LLVM openmp运行时的配合编译(@shatyuka) 修复yolov8 python示例返回空发生错误(@dsplvd) pnnx解耦torchscript加载，清理cxxabi hack，修复whole-archive链接 pnnx加载dynamo onnx，默认不启用编译 pnnx改善函数化，支持更多slice+inplace复合操作 pnnx转换torch.maskedselect/torch.slicescatter pnnx支持超过4G的模型 pnnx macos编译universal wheel pnnx添加entrypoint脚本 pnnx支持动态slice下标 pnnx转换softmin logsoftmax dtype参数 pnnx处理indexput传入空indices和标量数值 pnnx转换一些cudnn conv2d变种 pnnx合并完整slices为tensorsplit pnnx合并静态embedding pnnx不消除会导致shape变化的数学操作 pnnx改善torch-2.1 mha attnmask探测 pnnx修复无bias tensor的nn.Conv2d转换 pnnx转换torch.stack负数dim pnnx添加torch.arange单元测试 pnnx修复图匹配失败时可能的越界访问问题 pnnx识别embedding输入的batch轴为0 pnnx python添加控制fp16参数(@MollySophia) pnnx添加torch-2.2 ci github ci使用4并行编译 更新cmake ios工具链，添加visionos ci，watchos支持arm6432架构 添加apple a17和m3 cpu名称 不再编译apple平台32bit支持，不再编译ios arm64e架构，提升最低部署版本到ios-13 统一android python macos ci 不再打包和发布apple bitcode和32bit预编译包，新增visionos预编译包，新增tvos-gpu预编译包，更新openmp到18.1.2 改善a53/a55双发射文档(@luqiang-guo) 添加windows上protobuf>=22.0编译文档(@Galasnow) 更新macos编译文档(@lll143653) 清理无用的代码警告(@hokamilkv) 修正FAQ的拼写错误(@eltociear) 修正拼写错误(@hugo-syn) 修正拼写错误(@afredooo) 修正convolutionx86注释错误(@strongtz) 添加markdown文档代码辅助标志(@hugo-syn) 添加OneCloud跑分数据(@mizu-bai) 添加AWS c5.4xlarge跑分数据(@mizu-bai) 添加Xeon Phi 3120A跑分数据(@mizu-bai) 添加orangepi zero2跑分数据(@wonderfullook) 添加Dimensity 9300 MT6989跑分数据(@MollySophia) 添加PhytiumPi跑分数据(@HalfSweet) 添加remipi跑分数据(@dreamcmi) 添加radxa zero 3w跑分数据(@Qengineering)

New Contributors

• @wonderfullook made their first contribution in https://github.com/Tencent/ncnn/pull/5277
• @hugo-syn made their first contribution in https://github.com/Tencent/ncnn/pull/5301
• @FartSimps0n made their first contribution in https://github.com/Tencent/ncnn/pull/5304
• @HalfSweet made their first contribution in https://github.com/Tencent/ncnn/pull/5312
• @strongtz made their first contribution in https://github.com/Tencent/ncnn/pull/5310
• @afredooo made their first contribution in https://github.com/Tencent/ncnn/pull/5339
• @shatyuka made their first contribution in https://github.com/Tencent/ncnn/pull/5346
• @dsplvd made their first contribution in https://github.com/Tencent/ncnn/pull/5345
• @Galasnow made their first contribution in https://github.com/Tencent/ncnn/pull/5359
• @hokamilkv made their first contribution in https://github.com/Tencent/ncnn/pull/5365

Full Changelog: https://github.com/Tencent/ncnn/compare/20240102...20240410

- C++
Published by github-actions[bot] almost 2 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20240102 1e88fb8

编译版本，默认配置，android-ndk-r26b，xcode 13.4.1，ubuntu-20.04，ubuntu-22.04，vs2015，vs2017，vs2019，vs2022，emscripten-3.1.28 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-apple.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-apple-vulkan.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e | |ncnn-ios-simulator.zip | ios simulator 静态库，with and w/o bitcode | i386 + x8664 + arm64 | |ncnn-ios-simulator-vulkan.zip | ios simulator 静态库，支持 GPU，with and w/o bitcode | x8664 + arm64 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-mac-catalyst.zip | mac catalyst 静态库，with and w/o bitcode | x8664 + arm64 | |ncnn-mac-catalyst-vulkan.zip | mac catalyst 静态库，支持 GPU，with and w/o bitcode | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x86_64 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x64 + arm + arm64 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

内建vulkan驱动加载功能，不依赖vulkan-sdk编译gpu功能，可直接加载显卡驱动文件 msvc编译启用arm neon指令加速，启用arm64 asimdhp编译 实现python pnnx pypi包和python调用接口/文档(@Hideousmon) arm convolution int8 直接卷积重构支持任意elempack 优化 vulkan global pooling性能 优化resize bilinear性能 压缩字体数据减小二进制体积 deconvolution支持动态权重和对应pnnx转换 新增跑分数据rank card(@Qengineering) 支持big-endian架构平台，powerpc32位 添加woa linux ci 添加msvc禁用exceptions/rtti的编译开关 在macos上使用信号探测avx512指令集支持情况 支持寻找32位显卡驱动文件(@whyb) 启用benchmark编译打印4维shape(@Deepdive543443) 修复riscv-int8 sigmoid激活的测试失败问题(@MollySophia) 修复deconvolution x86 bias非对齐访问的问题 修复prelu x86 sse指令非对齐访问的问题(@AIOa) 修复windows上openmp设置线程数为0的警告 修复在支持16bit/8bit的gpu上有关fp16sa shader使用fp16 shared变量的警告 修复nvidia vulkan驱动在程序退出的crash 修复vkimagemat fromandroidhardwarebuffer缺失的elemsize参数错误 修复simpleocv Mat模板ptr的偏移错误 添加更过的gpu相关python绑定接口(@joeyballentine) android vulkan包的api版本降低到14/21 pnnx支持转换recomputescalefactor=True的nn.Upsample 新增nn.Identity测试 修复pnnx路径切分的问题 修复pnnx生成ncnn py空格对齐(@cmdbug) pnnx生成的py可以直接执行推理 python pnnx返回优化后的torch模型 删除无用的代码(@ningjiang233) 改善cmake toolchain文件(@zchrissirhcz) 新增watchos和tvos ci 修复linux sde ci的运行错误 更新POWER clang版本信息的文档(@JeremyRand) 更新有关vulkan/libomp-dev依赖的文档(@JeremyRand) 更新有关编译python模块CMAKETOOLCHAIN_FILE环境变量的文档(@JeremyRand) 修复Rasberry拼写错误(@JeremyRand) FAQ新增有关pyncnn数据连续性的文档(@lll143653) 更新readme下载页表格 添加Nintendo 3DS编译信息(@Deepdive543443) 添加oncloud amlogic s805跑分数据(@mizu-bai) 添加树莓派5 gpu跑分数据(@FantasyGmm) 添加Jetson TX2跑分数据(@FantasyGmm) 添加8gen2跑分数据(@mahirumahiru) 添加2K2000跑分数据(@RevySR) 更新Jetson Orin Nano/树莓派5跑分数据(@Qengineering) 添加visionfive2跑分数据(@wzyforgit)

New Contributors

• @Deepdive543443 made their first contribution in https://github.com/Tencent/ncnn/pull/5116
• @ningjiang233 made their first contribution in https://github.com/Tencent/ncnn/pull/5139
• @FantasyGmm made their first contribution in https://github.com/Tencent/ncnn/pull/5152
• @mahirumahiru made their first contribution in https://github.com/Tencent/ncnn/pull/5180
• @Qengineering made their first contribution in https://github.com/Tencent/ncnn/pull/5216
• @lll143653 made their first contribution in https://github.com/Tencent/ncnn/pull/5220
• @joeyballentine made their first contribution in https://github.com/Tencent/ncnn/pull/5165

Full Changelog: https://github.com/Tencent/ncnn/compare/20231027...20240102

- C++
Published by github-actions[bot] about 2 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20231027 3116e02

编译版本，默认配置，android-ndk-r25c，xcode 13.4.1，ubuntu-20.04，ubuntu-22.04，vs2015，vs2017，vs2019，vs2022，emscripten-3.1.28 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-apple.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-apple-vulkan.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e | |ncnn-ios-simulator.zip | ios simulator 静态库，with and w/o bitcode | i386 + x8664 + arm64 | |ncnn-ios-simulator-vulkan.zip | ios simulator 静态库，支持 GPU，with and w/o bitcode | x8664 + arm64 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-mac-catalyst.zip | mac catalyst 静态库，with and w/o bitcode | x8664 + arm64 | |ncnn-mac-catalyst-vulkan.zip | mac catalyst 静态库，支持 GPU，with and w/o bitcode | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x86_64 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x64 + arm + arm64 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

x86 convolution int8 gemm重构支持任意elempack x86 convolution int8 winograd重构支持任意elempack arm convolution int8 gemm重构支持任意elempack arm convolution int8 winograd重构支持任意elempack gelu vulkan优化(@FhqTreap) convolution1d vulkan优化(@FhqTreap) gridsample x86优化(@Yoh-Z) riscv gemm fp32优化(@Xinyu302) 新增erf/shrink和onnx转换(@brightening-eyes) 新增diag和pnnx转换(@wnqn1597) 新增celu和pnnx转换(@wnqn1597) 新增simplemath，允许不依赖libm编译使用数学函数(@HonestDeng) pooling adaptive支持动态的输出尺寸和pnnx转换 elu selu支持4维输入输出 slice支持indices参数 memorydata支持tag参数和fp16存储 x86 selu shufflechannel优化(@wnqn1597) 修复convolution vulkan在固定shape时的结果错误 修复权重tag潜在的溢出(@lrw04) 按层加载模型减少内存占用(@daquexian) 修复老版本gcc编译avx2 gather的错误(@chainsx) 修复老版本gcc编译mm256setm128的错误(@whyb) 修复新版本protobuf编译问题 修复老版本glibc round编译问题 修复c906工具链编译错误 pyncnn启用vulkan支持(@Hideousmon) pyncnn添加loadparammem接口(@JeremyRand @theflyingzamboni) pnnx支持torch-2.1 pnnx消除moduleop的输出unpack pnnx moduleop将权重shape作为参数写入param，内部权重顺序为使用顺序 pnnx改善reflect replicated pad匹配 pnnx合并conv3d-bn和deconv3d-bn pnnx转换torch.narrow(@zyt1024) pnnx转换torch.lgamma(@shudorcl) pnnx转换torch.positive(@nicochen1118) pnnx转换torch.cumprod(@Jiang-Weibo) pnnx转换torch.mv/nn.ReplicationPad3d(@ShuRaymond) pnnx转换F.pairwisedistance(@Marsyule) pnnx转换torch.viewasreal/torch.viewascomplex(@Baiyuetribe) 修复pnnx与新版本protobuf编译问题(@HuPengsheet) 修复pnnx改变目录下划线的错误 onnx2ncnn支持celu转换(@brightening-eyes) 自动为pull request添加label 修复ohos工具链编译错误 改进codeformat脚本使用函数(@xiezheng-XD) 添加rk3566 rk3588s跑分数据(@chainsx) 添加Allwinner T527跑分数据(@YuzukiTsuru) 添加树莓派5b跑分数据(@Pillar1989) 添加RTX A3000跑分数据(@chainsx) 添加多款pc跑分数据(@whyb)

New Contributors

• @chainsx made their first contribution in https://github.com/Tencent/ncnn/pull/4959
• @xiezheng-XD made their first contribution in https://github.com/Tencent/ncnn/pull/4993
• @zyt1024 made their first contribution in https://github.com/Tencent/ncnn/pull/4918
• @FhqTreap made their first contribution in https://github.com/Tencent/ncnn/pull/5001
• @shudorcl made their first contribution in https://github.com/Tencent/ncnn/pull/4976
• @nicochen1118 made their first contribution in https://github.com/Tencent/ncnn/pull/4999
• @Jiang-Weibo made their first contribution in https://github.com/Tencent/ncnn/pull/5002
• @brightening-eyes made their first contribution in https://github.com/Tencent/ncnn/pull/5012
• @wnqn1597 made their first contribution in https://github.com/Tencent/ncnn/pull/4935
• @ShuRaymond made their first contribution in https://github.com/Tencent/ncnn/pull/4974
• @HuPengsheet made their first contribution in https://github.com/Tencent/ncnn/pull/5034
• @Marsyule made their first contribution in https://github.com/Tencent/ncnn/pull/4942
• @Pillar1989 made their first contribution in https://github.com/Tencent/ncnn/pull/5058
• @Xinyu302 made their first contribution in https://github.com/Tencent/ncnn/pull/4903
• @Hideousmon made their first contribution in https://github.com/Tencent/ncnn/pull/5020
• @HonestDeng made their first contribution in https://github.com/Tencent/ncnn/pull/4905

Full Changelog: https://github.com/Tencent/ncnn/compare/20230816...20231027

- C++
Published by github-actions[bot] over 2 years ago

ncnn - Release 20230816

- C++
Published by github-actions[bot] over 2 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20230517 903ec7c

编译版本，默认配置，android-ndk-r25c，xcode 13.4.1，ubuntu-20.04，ubuntu-22.04，vs2015，vs2017，vs2019，vs2022，emscripten-3.1.28 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-apple.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-apple-vulkan.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e | |ncnn-ios-simulator.zip | ios simulator 静态库，with and w/o bitcode | i386 + x8664 + arm64 | |ncnn-ios-simulator-vulkan.zip | ios simulator 静态库，支持 GPU，with and w/o bitcode | x8664 + arm64 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-mac-catalyst.zip | mac catalyst 静态库，with and w/o bitcode | x8664 + arm64 | |ncnn-mac-catalyst-vulkan.zip | mac catalyst 静态库，支持 GPU，with and w/o bitcode | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x86_64 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x64 + arm + arm64 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

arm convolution winograd重构支持任意elempack arm convolution sgemm重构支持任意elempack arm convolution直接卷积重构支持任意elempack arm deconvolution/matmul 调用 gemm 完成计算 arm softmax支持任意elempack和bf16/fp16优化 arm multiheadattention fp16sa softmax优化 arm/x86 convolution1d直接卷积重构支持任意elempack和优化 粗糙的vulkan gemm和multiheadattention优化 multiheadattention支持输入attention mask sigmoid/swish/clip/gelu/mish/tanh支持4d输入 减少double类型的使用(@zhiliu6) arm a53/a55架构检测和流水线优化 允许注册自定义层替代内置实现 x86 asin/acos/atan/atan2 sse2/avx/avx512优化(@MouriNaruto) ssemathfunc迁移floor/ceil(@Yoh-Z) x86 mathfun迁移abs(@Yoh-Z) simpleocv新增cv::imdecode内存加载图片(@AlOa) 新增配合vulkan vma使用的三种扩展支持(@whyb) 新增获取vkinstance的接口(@whyb) 新增通用的sleep接口(@whyb) innerproduct允许2维高度1的输入输出 修复multiheadattention分配内存存在的多线程竞争问题 修复在获取不到cache信息时的除0错误 修复scale avx512计算错误 修复exynos9810非法指令错误 老旧adreno驱动中禁用fp16a以解决计算错误 绕过n卡padding shader编译错误 移除platform.h中无用的aarch64判断(@dreamcmi) 修正modelwriter squeeze层参数id错误(@irexyc) 修复gcc-13编译错误(@hillwoodroc) 修复gcc-5.2 aarch64编译错误 修复aosp编译错误(@caofx0418) 修复n卡上benchmark退出时的crash(@triple-Mu) 修复获取cpu cache信息潜在的fd泄漏 优化lightmode循环条件(@MambaWong) 绕过新版moltenvk的兼容性问题 绕过n卡在multiheadattention softmax结果偶发nan的兼容性问题 调用cpu.h接口时强制初始化全局cpu信息 pnnx支持torch-2.0 pnnx支持complex数据类型 pnnx转换torch.baddbmm/torch.mm/torch.stft家族/torch.std/F.scaleddotproductattention pnnx支持fp16权重的torchscript pnnx支持非forward的其他函数入口 pnnx当只有一个动态维时候折叠reshape的shape表达式 pnnx识别常数常量和表达式中的折叠 pnnx自动删除maxpool无indices输出项 pnnx总是删除convtransposed outputsize参数 pnnx合并gelu表达式 pnnx合并vit/clip/diffusers attention 修正pnnx的RNN/GRU省略输出项的python代码生成 修正pnnx转换ir时潜在的负INTMAX下溢问题 修正pnnx fprintf类型不匹配(@kernelbin) 修复pnnx windows编译错误(@Yoh-Z) pyncnn model zoo添加yolov7-tiny(@kennybradley) pyncnn model zoo添加yolov8s(@triple-Mu) macos pypi包使用完整版本号 改善wasm ci编译效率 更新ci swiftshader版本 更新cmake ios toolchain，新增ios-simulator arm64和mac catalyst ci 添加qnx toolchain和编译步骤(@zchrissirhcz) 删除ubuntu-18.04的ci 更新3A5000 benchmark数据(@wzyforgit) 新增2K1000LA benchmark数据(@lrzlin) 新增icpc icc benchmark数据(@mizu-bai) 新增Hyper-V Linux Guest benchmark数据(@MouriNaruto) 新增和更新op4lts/op5/VF2/FT2000/3A4000 benchmark数据(@MobtgZhang) 更新centos编译文档(@inisis) 更新windows msvc编译文档(@kernelbin) faq新增关于cmake版本升级的内容(@inisis) faq新增关于显卡节能模式的内容(@whyb) 修正citation和benchmark文档中的拼写错误(@zchrissirhcz) 修正pnnx代码和readme中的拼写错误(@jsyzdej @zchrissirhcz)

New Contributors

• @whyb made their first contribution in https://github.com/Tencent/ncnn/pull/4614
• @AlOa made their first contribution in https://github.com/Tencent/ncnn/pull/4557
• @caofx0418 made their first contribution in https://github.com/Tencent/ncnn/pull/4622
• @dreamcmi made their first contribution in https://github.com/Tencent/ncnn/pull/4628
• @kernelbin made their first contribution in https://github.com/Tencent/ncnn/pull/4647
• @lrzlin made their first contribution in https://github.com/Tencent/ncnn/pull/4656
• @irexyc made their first contribution in https://github.com/Tencent/ncnn/pull/4658
• @jsyzdej made their first contribution in https://github.com/Tencent/ncnn/pull/4665
• @hillwoodroc made their first contribution in https://github.com/Tencent/ncnn/pull/4684
• @MobtgZhang made their first contribution in https://github.com/Tencent/ncnn/pull/4687
• @kennybradley made their first contribution in https://github.com/Tencent/ncnn/pull/4693

Full Changelog: https://github.com/Tencent/ncnn/compare/20230223...20230517

- C++
Published by github-actions[bot] almost 3 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20230223 ff80ac2

编译版本，默认配置，android-ndk-r25c，xcode 14.0.1，ubuntu-18.04，ubuntu-20.04，ubuntu-22.04，vs2015，vs2017，vs2019，vs2022，emscripten-3.1.28 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x86_64 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x64 + arm + arm64 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

扩充binaryop broadcast规则 新增copyto算子，对应于torch inplace slice copy操作 x86 gemm优化，新增 transposeoutput 参数 x86 multiheadattention优化 x86 groupnorm优化(@EdVince) arm gemm优化，包括fp16s/fp16sa arm gelu优化(@EdVince) arm multiheadattention优化(@EdVince) 新增获取cpu l2/l3 cache大小接口，通过sysconf/win32-api和linux sysfs x86 gemm 依据l2 cache分块的优化 x86 convolution/deconvolution/deformableconv2d/matmul 调用 gemm 完成计算 x86 convolution winograd重构支持任意elempack x86 convolution直接卷积重构支持任意elempack x86公共的bfloat转换函数 slice/eltwise/concat支持4d输入 c api新增获取output indexes names接口 改善vulkan winograd f43 fp16计算数值稳定性 修复gpu信息bug bliz初始化问题(@weirdseed) 修正arm bfloat2float和float2bfloat命名相反的问题 更新riscv winograd f32系数，修复一些警告 更好的riscv rvv tanh实现 为ncnnoptimize/ncnn2int8添加新加的算子和参数 修复musl libc编译问题 更新stb image和image write，启用arm neon优化 更新emsdk版本到3.1.28，开启SIMPLEOCV(@ncnnnnn) pnnx新增torch.cumsum转换(@csukuangfj) pnnx新增torch.atan2/log10转换 pnnx自动替换pow(x,2)为square(x) 修正pnnx windows slice end参数问题(@Yoh-Z) pnnx自动删除无用的Tensor.clone(@Yoh-Z) pnnx自动展开模型输入tuple和list类型 pnnx转ncnn时分析binaryop broadcast规则并插入适当的reshape pnnx折叠常数常量，修复常数转换MemoryData兼容性问题 pnnx合并pixel unshuffle(@Yoh-Z) 去除pnnx readme多余空行(@inisis) 去除pnnx无用的include(@XiangYyang) 修正pyncnn outputindexes接口错误(@wyushun) 修复最新macos vulkan sdk兼容性问题(@w1ndseeker) 删除python代码无用的import(@dianjiaogit) 修复macos ci的xcode版本和vulkan sdk安装问题 更新ci中已废弃的create release步骤 添加CITATION.cff(@tpoisonooo) 更新cpu benchmark数据(@wzyforgit) 修复README编译状态badge(@tpoisonooo) 修复README编译链接(@tuduweb) 修正拼写错误(@hwdef @hiteshhedwig) 添加ncnn-fortran例子(@mizu-bai) 添加sherpa-ncnn实时语音识别例子(@csukuangfj)

New Contributors

• @mizu-bai made their first contribution in https://github.com/Tencent/ncnn/pull/4423
• @inisis made their first contribution in https://github.com/Tencent/ncnn/pull/4428
• @dianjiaogit made their first contribution in https://github.com/Tencent/ncnn/pull/4378
• @wyushun made their first contribution in https://github.com/Tencent/ncnn/pull/4453
• @w1ndseeker made their first contribution in https://github.com/Tencent/ncnn/pull/4472
• @hiteshhedwig made their first contribution in https://github.com/Tencent/ncnn/pull/4486
• @weirdseed made their first contribution in https://github.com/Tencent/ncnn/pull/4493
• @XiangYyang made their first contribution in https://github.com/Tencent/ncnn/pull/4497
• @tuduweb made their first contribution in https://github.com/Tencent/ncnn/pull/4530

Full Changelog: https://github.com/Tencent/ncnn/compare/20221128...20230223

- C++
Published by github-actions[bot] about 3 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20221128 03550ba

编译版本，默认配置，android-ndk-r25b，xcode 12.4，ubuntu-18.04，ubuntu-20.04，ubuntu-22.04，vs2015，vs2017，vs2019，vs2022，emscripten-2.0.8 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x86_64 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x64 + arm + arm64 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

新增loongarch64 lsx向量指令集优化，包括absval/batchnorm/bias/binaryop/cast/clip/concat/convolution1d/convolutiondepthwise/convolution/crop/deconvolutiondepthwise/deconvolution/dequantize/dropout/eltwise/flatten/hardsigmoid/hardswish/innerproduct/interp/mish/packing/padding/pooling/prelu/quantize/relu/requantize/sigmoid/slice/softmax/swish/tanh/unaryop算子(@junchao-loongson) layernorm x86优化(@LinHeLurking @LRY89757) batchnorm/elu/prelu/gelu x86优化(@LRY89757) softmax arm neon优化(@luqiang-guo) batchnorm/instancenorm riscv vector优化(@thelastlin) deformableconv2d x86优化(@miemie2013) elu vulkan优化(@Yoh-Z) convolution int8 x86 sse2/avx2优化 更新riscv vector segment load/store(@thelastlin) 改善内存池回收机制(@LinHeLurking) 新增获取cpu物理核心数量api，默认线程数设为物理大核心数量 实现控制单层运算特性是否启用的参数 更通用的macos/ios cpu特性探测过程，a15/a16/m2启用bf16和i8mm指令集 统一innerproduct x86 fp32/fp16s内核代码 修复在android省电模式cpu离线导致openmp崩溃的问题 实现glu算子与对应的pnnx转换(@csukuangfj) 新增fold和unfold算子 新增gridsample算子与对应的pnnx转换(@LRY89757) lstm支持projsize参数 groupnorm支持1d/2d/4d输入计算 squeeze/expanddims支持4d输入输出 multiheadattention支持kdim vdim参数 修复convolutiondepthwise allocator的错误设置(@w8501) 修正windows arm环境中convolution权重为空的问题 修复onnx2ncnn blob名字超出255长度的问题(@ZhangGe6) 修正expanddims axes参数id错误的问题(@LiuYi-Up) 修正c api allocator无法工作的问题(@qiqikit) 更严格的编译器armv7 fp16功能检查和兼容 修复老版本gcc编译avx512代码的编译错误(@bestpower) 修复windows-arm64编译(@zchrissirhcz) 修复在老版本ndk引用ncnn链接atomic内置函数失败的问题 修复新版本pybind11编译错误(@tpoisonooo) python模块支持mat.numpy()(@csukuangfj) 更新pybind11和glslang子模块 pyncnn发布python 3.11包和windows arm版本 pnnx支持pytorch 1.13 pnnx现已支持在cpu上加载gpu导出的torchscript pnnx保存onnx-zero模型文件 pnnx转换时将常量存储在临时文件减少内存占用 pnnx新增命令行参数fp16=0/1控制是否用fp16保存onnx-zero/ncnn模型 pnnx支持大部分数学函数转换，新增nn.Softmax2d/nn.Fold/nn.Unfold/F.fold/F.unfold/bitwiseleftshift/bitwiserightshift转换 pnnx改善和匹配inplace slice copy操作 融合更多静态的F.convND/F.linear为nn module 合并临接的reshape 合并pad到conv中 改善pnnx F.softmax转换对dtype兼容性(@EdVince) 修正pnnx softmax/normalize/slice负数axis转换错误的问题 修正pnnx slice end下标错误问题 修正pnnx转ncnn保存fp16权重没考虑对齐的问题 pnnx遇到动态size时不再折叠为常量 pnnx自动折叠newfull/full_like yolov5示例支持yolov5 6.2(@shaoshengsong) 修复编译警告(@tpoisonooo @veahow) 删除无用空行(@MollySophia @Menci) 修正空格对齐(@tonori) 修正拼写错误(@LRY89757 @Zepan @eltociear) 忽略.xmake目录，CMakeSettings.json，Visual Studio CMake文件(@zchrissirhcz) 重构README(@septs) 改善README布局(@magicse) 添加一些示例项目链接(@magicse @shaoshengsong) faq新增有关禁用fp16设置的内容(@MisakaBit) 更新riscv rvv ci 新增c906 ci 新增loongarch64 lsx ci 迁移部分github action ci到腾讯ci 新增TH1520 cmake toolchain(@luyanaa) 切分大型单元测试加快多进程测试速度 新增Intel Celeron M 420跑分(@MouriNaruto) 新增T-Head TH1520跑分(@YuzukiTsuru) 新增rock5b rk3588跑分(@hwdef)

New Contributors

• @LinHeLurking made their first contribution in https://github.com/Tencent/ncnn/pull/4065
• @septs made their first contribution in https://github.com/Tencent/ncnn/pull/4114
• @w8501 made their first contribution in https://github.com/Tencent/ncnn/pull/4173
• @MollySophia made their first contribution in https://github.com/Tencent/ncnn/pull/4187
• @Menci made their first contribution in https://github.com/Tencent/ncnn/pull/4188
• @magicse made their first contribution in https://github.com/Tencent/ncnn/pull/4193
• @tonori made their first contribution in https://github.com/Tencent/ncnn/pull/4217
• @YuzukiTsuru made their first contribution in https://github.com/Tencent/ncnn/pull/4240
• @ZhangGe6 made their first contribution in https://github.com/Tencent/ncnn/pull/4236
• @MisakaBit made their first contribution in https://github.com/Tencent/ncnn/pull/4248
• @LiuYi-Up made their first contribution in https://github.com/Tencent/ncnn/pull/4259
• @veahow made their first contribution in https://github.com/Tencent/ncnn/pull/4274
• @csukuangfj made their first contribution in https://github.com/Tencent/ncnn/pull/4283
• @Zepan made their first contribution in https://github.com/Tencent/ncnn/pull/4287
• @bestpower made their first contribution in https://github.com/Tencent/ncnn/pull/4294
• @shaoshengsong made their first contribution in https://github.com/Tencent/ncnn/pull/4328
• @junchao-loongson made their first contribution in https://github.com/Tencent/ncnn/pull/4242
• @eltociear made their first contribution in https://github.com/Tencent/ncnn/pull/4358

Full Changelog: https://github.com/Tencent/ncnn/compare/20220729...20221128

- C++
Published by github-actions[bot] over 3 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20220729 b4ba207

编译版本，默认配置，android-ndk-r24，xcode 12.4，ubuntu-18.04，ubuntu-20.04，ubuntu-22.04，vs2015，vs2017，vs2019，vs2022，emscripten-2.0.8 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x86_64 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x64 + arm + arm64 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

batchnorm avx512 优化(@LRY89757) 新增DeformableConv2d层和单元测试(@miemie2013) 修复conv3x3 winograd tensorcore权重数据错乱导致结果出错的问题 修复memorydata 4维数据转换的问题 pnnx转换torchvision.ops.DeformConv2d到ncnn pnnx自动删除无用的 mul + torch.ones 和 add + torch.zeros pnnx修复动态shape时删除无用pad可能的崩溃问题 pnnx修复动态shape时错误删除upsample的问题 添加sse优化文档(@DC-Zhou) 更加严格的编译器riscv vector支持检查，删除rvv-0.7.1编译支持 更新ci中android ndk路径，使用android-ndk-r24打包

New Contributors

• @DC-Zhou made their first contribution in https://github.com/Tencent/ncnn/pull/4053
• @miemie2013 made their first contribution in https://github.com/Tencent/ncnn/pull/4070

Full Changelog: https://github.com/Tencent/ncnn/compare/20220721...20220729

- C++
Published by github-actions[bot] over 3 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20220721 30ab31c

编译版本，默认配置，android-ndk-r23c，xcode 12.4，ubuntu-18.04，ubuntu-20.04，ubuntu-22.04，vs2015，vs2017，vs2019，vs2022，emscripten-2.0.8 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x86_64 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x64 + arm + arm64 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

armv5 convolution gemm int8优化 armv6 dsp convolution gemm int8优化 armv6 dsp convolution int8 winograd优化 mips msa/loongson mmi convolution int8 winograd优化 armv8.4 i8mm convolution gemm int8优化 探测编译器armv8.4/armv8.6的支持情况 优化innerproduct fp16s权重转换的内存消耗 统一arm eltwise不同elempack的分支 修复多线程下arm rnn/gru/lstm计算结果错误的问题 修复android-ndk-r16b编译多线程运行报错的问题 loongarch架构强制识别为mips以提升性能(@HougeLangley) 修复非常老版本的gcc编译错误 Mat创建时检查OOM 修复在android api 26编译找不到vkGetAndroidHardwareBufferPropertiesANDROID符号的问题 修复x86 fp32转fp16可能存在的内存泄漏 pnnx支持torch 1.12 pnnx识别torchscript文件格式并输出报错 pnnx转换torch.tensorsplit pnnx合并多次同轴slice为tensorsplit，修正插入位置 pnnx去除无用的一倍upsample pnnx转ncnn时合并多个BinaryOp为加权求和Eltwise pnnx合并megvii风格的shufflechannel+slice 添加pkgconfig(@djdisodo) 优化检测示例后处理nms(@jedi007) example检查加载模型返回值(@zchrissirhcz @jedi007) 添加Loongson2F toolchain(@luyanaa) 添加君正x2000 toolchain 添加ncnn svg图标(@ArchieMeng) 改善protobuf FAQ文档(@tpoisonooo) README添加ncnn-android-yolov7(@xiang-wuu) 添加yolov7示例(@cmdbug) 添加yolov7_pnnx示例(@hariag) benchmark新增fastestdet模型(@dog-qiuqiu) 新增armv8.6 ci和coverage 新增x86无sse ci 新增x86 address sanitizer ci

New Contributors

• @djdisodo made their first contribution in https://github.com/Tencent/ncnn/pull/3984
• @jedi007 made their first contribution in https://github.com/Tencent/ncnn/pull/4001
• @xiang-wuu made their first contribution in https://github.com/Tencent/ncnn/pull/4038
• @ArchieMeng made their first contribution in https://github.com/Tencent/ncnn/pull/4037
• @HougeLangley made their first contribution in https://github.com/Tencent/ncnn/pull/4044

Full Changelog: https://github.com/Tencent/ncnn/compare/20220701...20220721

- C++
Published by github-actions[bot] over 3 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20220701 0de869e

编译版本，默认配置，android-ndk-r23c，xcode 12.4，ubuntu-18.04，ubuntu-20.04，ubuntu-22.04，vs2015，vs2017，vs2019，vs2022，emscripten-2.0.8 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x8664 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x8664 + arm + arm64 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

x86/arm/mips/risc-v/vulkan 去除无用的权重内存占用 改善x86/arm/mips/risc-v winograd卷积选择策略，独立出dot函数 合并逐元素运算算子不同elempack的实现 x86 sse/avx bnll/tan优化(@jasonZhang892) x86 avx512 tanh优化(@jasonZhang892) x86 winograd 输入变换函数优化 x86 sse/avx convolution winograd23/42 pack1优化 x86 f16c innerproduct fp16s优化 arm neon tan/arcsin/arcos优化(@jasonZhang892) 改善arm sgemm卷积的选择策略 arm neon pooling bf16s优化 arm neon innerproduct汇编优化 armv7 vfpv4编译探测和运行时检测 armv7 vfpv4 cast fp16优化 armv7 vfpv4 innerproduct fp16s优化 armv5 sgemm卷积优化 mips msa cast fp16优化 mips sgemm卷积/convdw3x3优化 mips msa innerproduct fp16s优化 loongson mmi convolution gemm int8优化 risc-v vector erfc和gelu优化(@thelastlin) 优化sgemm和winograd尾尺寸寄存器布局 risc-v sgemm/winograd卷积/innerproduct/convdw3x3优化 avx512bf16/avx512fp16编译探测和运行时检测 avx512bf16/avx512fp16 cast bf16/fp16优化 armv8.2 asimdfhm，armv8.4 bf16 i8mm，armv8.6 sve sve2编译探测和运行时检测 新增einsum层实现和对应的pnnx转换 simpleomp支持libgomp abi layernorm支持一维输入和沿w做norm rnn/lstm/gru支持openmp多线程加速 mali-t760启用fp16运算 更多的binaryop arm/mips/riscv/x86特化实现 修复unaryopx86 gcc-4.4编译问题(@Yoh-Z) 修复Mat fill gcc-4.4编译问题(@Yoh-Z) 添加Power层单元测试(@proydakov) yolov5pnnx示例自动适应不同的numclass数量(@FeiGeChuanShu) 修正yolox输入shape w!=h的情况(@FeiGeChuanShu) 修复armv7中fp16转fp32发生bus error的问题(@cugxchen) 修复convdw/deconvdw的avx512代码路径(@Yoh-Z) 修复imreadwrite中total可能的溢出问题(@Z841973620) 去除scalex86中无效的死代码(@luyanaa) 去除pnnx ir中无效的死代码(@moozae) 修正testdeconvolutiondepthwise3d中printf参数错误(@Nlzy) 修复mips架构上cmake寻找thread的错误 修复在不支持cooperative matrix扩展测试崩溃的问题 改善risc-v vector vfredsum/vfredusum编译器兼容(@thelastlin) 修复某些arm编译器循环优化劣化的问题 更新glslang，修复在使用系统glslang的include路径问题 拆分arm82源码到单独文件，减小编译体积和内存占用 修复ios universal arm82编译开关启用的问题 统一winograd函数命名 修复padding arm编译警告 修复ios/tools/arm82/non-int8编译警告(@proydakov) 修复LGTM警告(@proydakov) pnnx支持转换torch bmm/min/max/einsum/arange/bitwiseand/bitwisenot/bitwiseor/bitwisexor/eq/gather/ge/gt/le/lt/ne/norm/indexselect/scatteradd/complex/imag/real/fft/fft2/fftn/hfft/hfft2/hfftn/ifft/ifft2/ifftn/ihfft/ihfft2/ihfftn/irfft/irfft2/irfftn/rfft/rfft2/rfftn，Tensor newones/newzeros/maskedfill，F.normalize一维情况 pnnx ir支持复数数据类型 pnnx支持转换Tensor select到ncnn 新增pnnx导出为onnx函数 pnnx导出ncnn fp16存储设计为一个pass pnnx添加更多hardsigmoid合并模式 pnnx合并multiheadattention的尾部unpack pnnx在静态shape输入时能有效的折叠常量 pnnx合并静态权重的卷积F.convND为nn.ConvND 修复pnnx生成slice表达式遇到动态参数崩溃的问题 pnnx支持dict作为模型输出的转换 pnnx转换ncnn模型遇到4d/5d输入nn.Linear自动添加reshape pnnx去除单输入的cat算子 pnnx在合并表达式时跳过可折叠的常量 pnnx兼容更多inplace风格的算子，改善子图匹配浮点和整数比较 pnnx导出moduleop时存出所有内部权重 pnnx添加vitb32和convnext端到端模型测试 pnnx添加swintransformer模型测试 gitignore添加python生成的文件(@triple-Mu) 添加c906和c910 v240 toolchain 迁移pnnx，loongarch和gpu的ci到自建服务器 修复loongarch ci 添加avx512 spr cpu ci 更新ci的qemu版本 cmake安装目标路径采用gnuinstalldirs 限制github action配置的权限(@nathannaveen) ci的swiftshader使用单线程 修复vs2022 ci中protobuf兼容问题 添加关于关闭android界面和设置cpu/gpu性能模式的信息 更新README中QQ群信息(@zchrissirhcz) README中的YOLOV改为YOLOv(@zhiqwang) 更新树莓派和d1的编译文档 更新添加自定义算子文档的过时信息(@LRY89757) 添加英文版faq文档(@Jianbo-Ning) 添加英文版build-for-visualstudio文档(@dankernel) 添加visiontransformer benchmark(@tpoisonooo) 更新rk3399 rk3288 gpu benchmark数据 更新qcom810 qcom855plus benchmark数据 添加Jetson AGX Orin/Jetson AGX Xavier/AX620A benchmark数据(@BUG1989) 添加loongson和sunway benchmark数据(@wzyforgit) 添加RK3588 benchmark数据(@FeiGeChuanShu) 添加amd 5700g benchmark数据(@hwdef) release添加ubuntu 22.04预编译包 release android采用ndk-r23c编译 release预编译包保护软链接

New Contributors

• @LRY89757 made their first contribution in https://github.com/Tencent/ncnn/pull/3741
• @nathannaveen made their first contribution in https://github.com/Tencent/ncnn/pull/3758
• @Z841973620 made their first contribution in https://github.com/Tencent/ncnn/pull/3757
• @Nlzy made their first contribution in https://github.com/Tencent/ncnn/pull/3774
• @cugxchen made their first contribution in https://github.com/Tencent/ncnn/pull/3779
• @luyanaa made their first contribution in https://github.com/Tencent/ncnn/pull/3821
• @triple-Mu made their first contribution in https://github.com/Tencent/ncnn/pull/3824
• @Jianbo-Ning made their first contribution in https://github.com/Tencent/ncnn/pull/3901
• @moozae made their first contribution in https://github.com/Tencent/ncnn/pull/3965

Full Changelog: https://github.com/Tencent/ncnn/compare/20220420...20220701

- C++
Published by github-actions[bot] over 3 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20220420 7600270

编译版本，默认配置，android-ndk-r21d，xcode 12.4，ubuntu-18.04，ubuntu-20.04，vs2015，vs2017，vs2019，vs2022，emscripten-2.0.8 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x8664 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x8664 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

conv vulkan im2col+sgemm优化 conv vulkan winograd43优化 conv vulkan implicit gemm优化 deconv vulkan sgemm+col2im优化 conv/deconv vulkan local memory优化 conv vulkan 直接卷积unroll优化 改善conv vulkan winograd23/winograd43选择策略 融合conv vulkan winograd 前后的pad/crop到transform中 innerproduct vulkan 拆分两阶段优化 补全conv 1x1 vulkan任意packing 补全conv 3x3 winograd vulkan任意packing conv/deconv vulkan pack4 nvidia tensorcore优化 x86 sse/avx 数学函数优化(@Yoh-Z) unaryop x86 优化(@Yoh-Z) floor/ceil/abs x86 sse优化(@MouriNaruto) convoluition/convoluitiondepthwise/innerproduct/padding/pooling/interp/eltwise/crop/reshape/slice/hardsigmoid/swish/binaryop/clip/relu/sigmoid/unaryop x86 avx512优化 conv sgemm avx512优化 conv3x3 winograd avx512优化 deconvolution/deconvolutiondepthwise x86直接反卷积实现 softmax x86 sse/avx/avx512优化 quantize/dequantize/requantize mips msa优化 conv int8/convdw int8/innerproduct int8 mips msa优化 multiheadattention arm neon优化(@EdVince) softmax arm neon优化 conv3x3 winograd transform部分提出为可复用函数 x86 f16c指令集检测和分发 删除没什么用的avx2-fp16相关代码 simpleomp允许最多32个microtask参数 添加loongson mmi头文件和编译支持 新增deconv1d，deconv3d和对应的pnnx转换 修正老版本gcc的avx512编译参数问题 修正sigmoid x86在很大数值输入返回nan的问题 修正gpu推理convdw发生unlocked pool allocator destoryed too early的问题 避免mips msa推理时可能发生浮点数异常 batchnorm加载参数时避免除0异常 为新算子更新modelwriter copymakeborder添加reflect类型 mali g31/g52启用fp16 修复armhf工具链编译问题 global pooling强制使用fp32累加避免nan问题 修复某些android系统无法dlsym getauxval的问题 修正新版本moltenvk tanh兼容问题 提出vulkan激活函数，glsl中实现include 修复armv7编译单元测试失败的问题(@jasonZhang892) 修正conv3x3 winograd矩阵注释(@MouriNaruto) 修正how-to-build拼写错误，更新jetson-nano编译文档(@tpoisonooo) 更新ios编译文档(@mirrorsysu) 一些注释和代码清理和修复编译警告(@tpoisonooo) 修正readme中的单词大小写(@YoungSx) 更新use-ncnn-with-own-project中的glslang的库列表 ci新增msvc arm/arm64目标 ci新增linux loongarch目标 ci更新windows matrix和vs2022目标 修复vs2019打包 新增yolov5pnnx例子 新增nanodetpluspnnx例子 减少yolov5例子中后处理耗时(@UNeedCryDear) 修复yolov5.py框位置问题(@hariag) 更新ls2k1000的benchmark数据 pnnx支持转换torch unbind/ones/oneslike/full/fulllike/randnlike/empty/emptylike/addmm pnnx支持torch 1.11.0版本 pnnx转换的ncnn模型文件使用fp16保存 pnnx在linux上链接pthread，修复windows minmax编译问题 pnnx新增静态msvc crt cmake选项 修正pnnx hardtanh 参数的ncnn转换 修复pnnx macos动态库加载路径的问题

New Contributors

• @MouriNaruto made their first contribution in https://github.com/Tencent/ncnn/pull/3591
• @YoungSx made their first contribution in https://github.com/Tencent/ncnn/pull/3655
• @hariag made their first contribution in https://github.com/Tencent/ncnn/pull/3656
• @EdVince made their first contribution in https://github.com/Tencent/ncnn/pull/3667
• @mirrorsysu made their first contribution in https://github.com/Tencent/ncnn/pull/3696
• @jasonZhang892 made their first contribution in https://github.com/Tencent/ncnn/pull/3710
• @UNeedCryDear made their first contribution in https://github.com/Tencent/ncnn/pull/3649

Full Changelog: https://github.com/Tencent/ncnn/compare/20220216...20220420

- C++
Published by github-actions[bot] almost 4 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20220216 6b2495c

编译版本，默认配置，android-ndk-r21d，xcode 12.4，ubuntu-18.04，ubuntu-20.04，vs2015，vs2017，vs2019，emscripten-2.0.8 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x8664 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x8664 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

conv sgemm pack4/pack1to4/pack4to1 x86 sse2/avx优化 conv3x3s1 winograd pack4/pack4to1 x86 sse2/avx优化 conv int8 gemm pack8to4/pack8to1/pack1to8 x86 xop/avx2/avx512-vnni/avx-vnni优化 conv3x3s1 int8 winograd pack8to4/pack8to1 x86 xop/avx2/avx512-vnni/avx-vnni优化 scale x86 avx优化(Yoh-Z) interp x86 avx优化(Yoh-Z) conv pack arm neon优化 x86 avx512基础架构 默认启用x86 avx512编译和运行时检测 解耦合x86 fma和avx2 不依赖libgcc的x86 cpu指令集探测 支持动态权重的卷积 修正可能因Mat成员函数没有内联导致的非法指令问题 修正可能因函数对象实例没有内联导致的非法指令问题 修正单元测试比较函数错误(yyuzhong) binaryop/unaryop/reduction支持4维输入 新增Tile层和torch.repeat的转换 新增MatMul层和torch.matmul的转换 armv8.2 dot编译为运行时可选 支持sw64平台(wzyforgit) 增加c-api的cmake开关 c-api增加默认mat构造函数(tpoisonooo) 简化binaryop的函数对象代码(tpoisonooo) 修正interp nearest在有非常规scalefactor参数计算错误的问题 简化c-api自定义层forwardn参数类型 删除非avx2编译时退化sse2的警告(kagurazakakotori) 在64位编译时使用mmcvtsi128si64降低内存访问(kagurazakakotori) 修正low-level op api文档错误(FeiGeChuanShu) 修正crop test缺失的doffset参数(xh-liu-tech) 修正arm convolution pack1to4 int8权重重排(cmdbug) 简化getcurrenttime平台相关宏(cmdbug) 修正armv7无neon编译时计算错误的问题 增加c906 v223工具链(zchrissirhcz) 添加第二个qq技术交流群答案(LJoson) python ci禁用tools和examples构建 ci动态库编译禁用LTO ci更新swiftshader-20220211 删除travis ci和readme相关条目(proydakov) 新增yolo-fastest模型benchmark(dog-qiuqiu) 更新来自Q-engineering树莓派/jetson-nano等benchmark数据 benchmark增加zynq-7020/z8350/n5105 pnnx支持转换torch dequantize/quantizepertensor/quantized.linearrelu/argmax/argmin/clone/normal/expand/var/amax/amin/logsumexp/prod/sum/arange/matmul/zeroslike/expandlike/deformconv2d/roialign/norm/stack/repeat/zeros/roll/remainder pnnx自动删除dropout算子 pnnx自动删除无pads的pad和noop算术表达式 pnnx常量折叠 pnnx转换4维常量数据 pnnx支持half数据类型导出的模型 pnnx转ncnn时删除尾部的reshape/permute pnnx合并conv1d-bn convtranspose1d-bn pnnx合并单一维度全select为unbind pnnx确保算子名唯一性 修正pnnx转ncnn时遇到无法展开的表达式发生崩溃的问题 pnnx转ncnn支持负数pads的F.pad pnnx转ncnn合并transpose-matmul pnnx转ncnn在pooling123d前后增加升维和降维的reshape模拟nn.MaxPool123d处理无batch维数据的行为 pnnx命令行参数的shape指定输入类型 pnnx自动寻找pytorch安装目录(Yutyrannus) pnnx ci自动拷贝dll文件(Yutyrannus) 添加pnnx命令行工具用法说明(ling0322)

New Contributors

• @wzyforgit made their first contribution in https://github.com/Tencent/ncnn/pull/3421
• @dog-qiuqiu made their first contribution in https://github.com/Tencent/ncnn/pull/3470
• @xh-liu-tech made their first contribution in https://github.com/Tencent/ncnn/pull/3475
• @ling0322 made their first contribution in https://github.com/Tencent/ncnn/pull/3487
• @kagurazakakotori made their first contribution in https://github.com/Tencent/ncnn/pull/3527
• @LJoson made their first contribution in https://github.com/Tencent/ncnn/pull/3532
• @Yoh-Z made their first contribution in https://github.com/Tencent/ncnn/pull/3540
• @yyuzhong made their first contribution in https://github.com/Tencent/ncnn/pull/3556

Full Changelog: https://github.com/Tencent/ncnn/compare/20211208...20220216

- C++
Published by github-actions[bot] about 4 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20211208 8916d1e

编译版本，默认配置，android-ndk-r21d，xcode 12.4，ubuntu-18.04，ubuntu-20.04，vs2015，vs2017，vs2019，emscripten-2.0.8 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x8664 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x8664 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

Mat数据结构支持4维 新增Convolution3D, Pooling3D和对应的pnnx算子转换 这些算子支持4维输入输出(Cast, Packing, ReLU, BatchNorm, Reshape, Flatten, Permute, Crop)和对应的pnnx算子转换 C api增加4维mat Convolution1D常规的simd优化(sse/avx/neon/rvv/msa) 降低gpu推理时的cpu占用 降低单元测试cpu占用 改进pnnx转ncnn的batch轴识别 更新operators文档 修复开启simpleocv时仍然寻找系统opencv的问题(zchrissirhcz) 修正p2pnet例子绘图bug(FeiGeChuanShu) 支持c906 v2.2.2新工具链 更可靠的ci任务取消机制 ci新增avx512和nvidia t4 修复python wheel发布脚本 更新ci lavapipe版本(ljtjerry) 更新ci webassembly支持nodejs v16 更新FAQ(zhaqu, Bright476, Rinfair-CSP-A016) 修正拼写错误(cmdbug)

New Contributors

• @zhaqu made their first contribution in https://github.com/Tencent/ncnn/pull/3374
• @ljtjerry made their first contribution in https://github.com/Tencent/ncnn/pull/3387
• @Rinfair-CSP-A016 made their first contribution in https://github.com/Tencent/ncnn/pull/3399

Full Changelog: https://github.com/Tencent/ncnn/compare/20211122...20211208

- C++
Published by github-actions[bot] about 4 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20211122 e4c821a

编译版本，默认配置，android-ndk-r21d，xcode 12.4，ubuntu-18.04，ubuntu-20.04，vs2015，vs2017，vs2019，emscripten-2.0.8 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x8664 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x8664 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

PNNX(PyTorch Neural Network Exchange)是PyTorch模型部署的新方式，可以避开ONNX中间商，导出比较干净的高层OP risc-v v binaryop, hardswish, hardsigmoid, prelu, selu, dropout, gru, softmax优化(thelastlin) risc-v v conv1x1 fc优化 arm neon requantize leakyrelu优化 arm neon innerproduct gemm int8优化 针对c906 sgemm pack优化(yaobyPerfxlab, xianyi) x86 avx 卷积激活优化(zhiliu6) x86 sse convolution, convolutiondepthwise, pooling优化(Timen) 修正layernorm affine计算错误 修正pooling adaptive计算错误 修正deconvolution output padding在有bias时的计算错误 interp支持cubic aligncorner插值 interp支持对2维数据w方向拉伸 新增convolutiondepthwise1d和pnnx转换 rnn/lstm/gru支持不相等的输入输出个数 修正squeeze和expanddims层axes的处理 使用整数计算pooling adaptive参数上下界(Yutyrannus) 修复armv7 neon round模式差异 修复x86 sse/avx round模式差异 修复int8输入单元测试可能的越界读 修复在某些android平台无法获得auxv变量的问题 修正apple a11 a12检测armv8.2 dot扩展指令错误的问题 内存引用加载模型时不再拷贝到内存 修复pyncnn numpy转Mat时非对齐拷贝出错的问题 正确检测和支持apple a15和m1(zchrissirhcz) 修复AVX-only代码和用户提供opt时的单元测试逻辑(Timen) hardswish激活合并入convolution和innerproduct(zhiliu6) 自动解耦extract的Mat数据与Net实例的内存池 Net的customlayertoindex移到public(Timen) 删除代码中的无用变量(Sinky-Yan) cmake检测esp32的xtensa架构 cmake install安装ncnn工具(jinmingyi1998) 修正hardswish test beta参数(zhiliu6) 修复ncnnoptimize无法生成合理int8权重的问题 ncnnoptimize支持embd层 修正onnx2ncnn concat算子负数axis转换的问题 修复onnx2ncnn合并expand算子(grimoire) 修复某些arm kernel越界读数据的问题 修复NCNNSTDIO=OFF的编译问题 新增YOLOX例子, 更新预处理逻辑(FateScript) 新增RobustVideoMatting例子(FeiGeChuanShu) 新增scrfd croudhuman例子(MarsTechHAN) 新增YOLOv5 v6.0例子(zhiliu6) 新增CrowdCounting-P2PNet例子(FeiGeChuanShu) readme添加yolox(Sinky-Yan) 更新readme文档(fzyzcjy) 修复msvc编译器警告(TianZerL) 一些拼写错误修正(cmdbug, huoshuai-dot) 更新faq文档(ncnnnnn, luqiang-guo, zhiqwang, cmdbug, CharlesHuan, Shiro-Nana, zmq175) 更新operators算子文档(soragotosann) 更新d1和ls2k编译文档 新增termux编译文档(Sinky-Yan) 更新msvc编译文档(ncnnnnn) 更新编译文档(dankernel, mlbo, xiguadong) 更新macos openmp安装方法(zhiqwang) 更新量化文档中的链接(ShiquanYu) 修正python编译文档路径错误(nixondutt) benchmark新增m1数据(zhiqwang) benchmark新增mbp数据(AnnYellow) benchmark新增khadas vim3 amlogic a311d数据(elejke, FeiGeChuanShu) benchmark新增Phytium FT-2000+/64数据 benchmark新增RK3568数据(BowShotDS) benchmark新增RK3328数据(Liuyufanlyf) benchmark新增Ingenic X2000和T40数据(MarsTechHAN) ci更新swiftshader ci新增基于lavapipe的gpu测试 ci删除travis arm32(Richuanwu) ci更新xcode版本

New Contributors

• @SinKy-Yan made their first contribution in https://github.com/Tencent/ncnn/pull/3124
• @FateScript made their first contribution in https://github.com/Tencent/ncnn/pull/3110
• @BowShotDS made their first contribution in https://github.com/Tencent/ncnn/pull/3145
• @Liuyufanlyf made their first contribution in https://github.com/Tencent/ncnn/pull/3164
• @yaobyPerfxlab made their first contribution in https://github.com/Tencent/ncnn/pull/3159
• @TianZerL made their first contribution in https://github.com/Tencent/ncnn/pull/3188
• @grimoire made their first contribution in https://github.com/Tencent/ncnn/pull/3189
• @dankernel made their first contribution in https://github.com/Tencent/ncnn/pull/3248
• @Richuanwu made their first contribution in https://github.com/Tencent/ncnn/pull/3279
• @ShiquanYu made their first contribution in https://github.com/Tencent/ncnn/pull/3283
• @nixondutt made their first contribution in https://github.com/Tencent/ncnn/pull/3293
• @mlbo made their first contribution in https://github.com/Tencent/ncnn/pull/3314
• @luqiang-guo made their first contribution in https://github.com/Tencent/ncnn/pull/3332
• @Yutyrannus made their first contribution in https://github.com/Tencent/ncnn/pull/3333
• @xiguadong made their first contribution in https://github.com/Tencent/ncnn/pull/3344
• @soragotosann made their first contribution in https://github.com/Tencent/ncnn/pull/3345
• @huoshuai-dot made their first contribution in https://github.com/Tencent/ncnn/pull/3348
• @fzyzcjy made their first contribution in https://github.com/Tencent/ncnn/pull/3358
• @CharlesHuan made their first contribution in https://github.com/Tencent/ncnn/pull/3361
• @Shiro-Nana made their first contribution in https://github.com/Tencent/ncnn/pull/3368
• @zmq175 made their first contribution in https://github.com/Tencent/ncnn/pull/3369
• @AnnYellow made their first contribution in https://github.com/Tencent/ncnn/pull/3373

Full Changelog: https://github.com/Tencent/ncnn/compare/20210720...20211122

- C++
Published by github-actions[bot] over 4 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20210720 2c4ae09

编译版本，默认配置，android-ndk-r21d，xcode 12.2，ubuntu-16.04，ubuntu-18.04，ubuntu-20.04，vs2015, vs2017，vs2019, emscripten-2.0.8 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x8664 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x8664 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

risc-v架构cpu的vector 0.7.1和1.0扩展的算子优化，包括fp32/fp16，支持可变vlen，运行时检测vector和半精度扩展与函数分发(absval, cast, clip, concat, convolution, convolutiondepthwise, crop, deconvolution, deconvolutiondepthwise, flatten, innerproduct, interp, mish, packing, padding, pooling, relu, sigmoid, swish, tanh, unaryop) mips架构cpu的msa扩展的算子优化，运行时检测msa扩展与函数分发(absval, bias, binaryop, clip, concat, convolution, convolutiondepthwise, crop, deconvolution, deconvolutiondepthwise, dropout, eltwise, flatten, hardsigmoid, hardswish, innerproduct, interp, mish, packing, padding, pooling, prelu, relu, sigmoid, slice, softmax, swish, tanh, unaryop) 运行时检测avx，优化avx-only平台的性能(Timen) 支持loongarch64架构编译(tsuibin) 在apple设备上总是启用armv8.2 dot 可以不依赖opencv用simpleocv编译example示例 改善visual studio配合clang编译(Timen) 新增cmake选项NCNNBF16，可禁止所有bf16相关代码减小库体积 大幅更新operators算子文档 arm neon数学函数fma优化 arm neon tanh优化(deepage) AbsVal/ReLU的risc-v vector优化(thelastlin) 修正x86 requantize pack4to1计算错误 修正innerproduct gemm in8计算错误(lsdustc) 修正warpaffinebilinearyuv420sp uv变换矩阵错误(DaydreamCoding) 修正yuv420sp2rgb在armv7平台越界读数据问题(zchrissirhcz) 修正vulkan pushconstant编码时的内存泄漏(chenxiemin) darknet2ncnn支持sam层和letterbox检测(zhiliu6) 修复darknet2ncnn pad=0转换错误(zhiliu6) 修正ncnn2table工具解析命令行长数字错误 优化ncnn2table多线程效率 ncnn2table支持动态输入(jinmingyi1998) 修正ncnn2table easyquant方法文件索引错误(lsdustc) 修正ncnnoptimize丢失interp参数问题(jinmingyi1998) 修复ncnnoptimize在替换conv为fc算子后可能的段错误 修复ncnnoptimize在遇到孤立节点时可能的段错误 修复macos ci swiftshader编译 修正testextractor.py的TypeError断言(zhiqwang) 修复macos的编译警告(proydakov) risc-v ci升级qemu 6.0.0并支持rvv扩展 ci现在过滤更改文件，减少触发 新增c906工具链 更新visual studio编译中文文档(zchrissirhcz) 修正examples yolov4视频加载错误(uniartisan) readme添加pocky群号(JuYanYan) readme添加scrfd(ncnnnnn) 增加issue模板(tpoisonooo) 一些拼写错误修正(hwdef) benchmark新增nanodet_m模型(BUG1989) benchmark新增v1605b数据(kalcohol) benchmark新增loongson 2k1000数据 benchmark更新jetson agx数据(zineos) 新增代码格式化ci，禁用restyled

New Contributors

• @JuYanYan made their first contribution in https://github.com/Tencent/ncnn/pull/2956
• @uniartisan made their first contribution in https://github.com/Tencent/ncnn/pull/3005
• @hwdef made their first contribution in https://github.com/Tencent/ncnn/pull/3045
• @DaydreamCoding made their first contribution in https://github.com/Tencent/ncnn/pull/3048
• @sdli1995 made their first contribution in https://github.com/Tencent/ncnn/pull/3081
• @chenxiemin made their first contribution in https://github.com/Tencent/ncnn/pull/3088
• @tsuibin made their first contribution in https://github.com/Tencent/ncnn/pull/3094

Full Changelog: https://github.com/Tencent/ncnn/compare/20210525...20210720

- C++
Published by github-actions[bot] over 4 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20210525 f6c4952

编译版本，默认配置，android-ndk-r21d，xcode 12.2，ubuntu-16.04，ubuntu-18.04，ubuntu-20.04，vs2015, vs2017，vs2019, emscripten-2.0.8 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x8664 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x8664 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

绘图api，画框，画圆，画线，画字 simpleocv添加stbimage读写图片文件 运行时检测armv8.2 dotprod 未找到opencv时依然能编译量化工具 允许超过gpu硬件队列数限制并行提交任务 ncnnoptimize自动生成随机bin文件 修复convolutiondepthwise int8经过ncnnoptimize后权重错位问题 extract int8数据自动转换为fp32 添加获取模型输入输出blob接口(caishanli) 发布python预编译包(caishanli) 更新imx7d benchmark risc-v v 优化数学函数 运行时检测 risc-v vlen mlir2ncnn合并swish benchmark添加efficientnetv2b0 修正jetson cmake工具链错误定义android宏的问题 修正macos/ios glslang framework打包问题 webassembly预编译包启用simpleocv 添加scrfd人脸检测例子 添加scrfd人脸检测截图(ZHEQIUSHUI) 更新FAQ(deepage) 修正拼写错误(FusionBolt) 添加下载数badge

New Contributors

• @FusionBolt made their first contribution in https://github.com/Tencent/ncnn/pull/2922
• @ZHEQIUSHUI made their first contribution in https://github.com/Tencent/ncnn/pull/2925

Full Changelog: https://github.com/Tencent/ncnn/compare/20210507...20210525

- C++
Published by github-actions[bot] almost 5 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20210507 ae14ca9

编译版本，默认配置，android-ndk-r21d，xcode 12.2，ubuntu-16.04，ubuntu-18.04，ubuntu-20.04，vs2015, vs2017，vs2019, emscripten-2.0.8 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，with and w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，with and w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x8664 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x8664 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |

int8 packing重构，自动转换packing，大幅优化int8 arm neon卷积实现，支持armv8.2 dot指令加速 重写ncnn量化工具，支持kl/aciq/easyquant三种量化策略，提升多线程效率 ncnn2int8 离线融合quantize-激活-dequantize为requantize，实现端到端int8 去除用于在线融合requantize功能的cmake NCNNREQUANT编译选项 conv/fc int8支持全部激活组合 conv3x3s1 pack8 直接卷积x86 avx优化 conv3x3 conv1x1 pack8 x86优化(zhiliu6) instancenorm arm neon优化 pixelshuffle arm neon优化 运行时检测risc-v cpu v扩展和函数分发 log/exp/sin/cos/tanh数学函数的risc-v v优化 packing/sigmoid/mish/tanh/swish/unaryop/cast risc-v v优化 动态库导出vkcommand和vkcompute api binaryop新增三种broadcast类型 新增cmake编译选项NCNNINT8，可禁用全部int8推理相关代码 为findblobindexbyname错误附加更有用的提示信息 新增检测cpu支持risc-v v扩展和fp16扩展的查询接口 新增c906编译支持 删除caffe2ncnn中早期遗留的fp16和int8量化功能 修正conv1x1s1 sgemm pack8to4 fp16sa有bias时arm neon计算错误的问题 修正lrn vulkan因fp16精度不足导致计算错误的问题 修正ncnn2int8解析过长行时出错 修正使用gpu时候，无法input extract同个blob的问题 修正macos使用集成显卡时初始化错误 修正tanh neon计算错误 修复启用NCNNARM82编译时在树莓派运行发生非法指令错误 修正caffe2ncnn input层1维2维的参数转换 修正onnx clip没有max导致转换出错的问题 mxnet2ncnn 支持channel pad 改善mxnet2ncnn有同名blob模型的兼容性 排序ncnnaddlayertest(ncnnnnn) 为hardsigmoid/hardswish默认参数添加注释(songqun) python打包去掉ppc64le(caishanli) 修复老版本gcc编译问题 修复NCNN_STRING=OFF时的编译问题(zhiliu6) 添加Apple M1 benchmark(DaChengTechnology) 修正文档拼写错误(cmdbug, proydakov) 更新ncnn量化推理文档 更新operation-param-weight-table(cmdbug) 添加新的faq文档(wwdok, zchrissirhcz, runrunrun1994, wblksheep, DaChengTechnology, ncnnnnn, 791136190, mmiirroo, cmdbug) 删除构建文档中有关cctools的部分 restyled机器人不触发ci 更新codecov版本 更新risc-v ci工具链，支持最新rvv-1.0 添加risc-v的代码覆盖率 更新qcom855+的benchmark数据

New Contributors

• @wwdok made their first contribution in https://github.com/Tencent/ncnn/pull/2829
• @runrunrun1994 made their first contribution in https://github.com/Tencent/ncnn/pull/2831
• @wblksheep made their first contribution in https://github.com/Tencent/ncnn/pull/2835
• @mmiirroo made their first contribution in https://github.com/Tencent/ncnn/pull/2851
• @xianyi made their first contribution in https://github.com/Tencent/ncnn/pull/2868

Full Changelog: https://github.com/Tencent/ncnn/compare/20210322...20210507

- C++
Published by github-actions[bot] almost 5 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20210322 e86799e

编译版本，默认配置，android-ndk-r21d，xcode 12.2，ubuntu-16.04，ubuntu-18.04，ubuntu-20.04，vs2017，vs2019 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x8664 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x8664 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads |

warpaffine函数arm neon优化 新增multiheadattention和pytorch的转换 新增gelu(RBelogorodtsevFBase) 新增flush denormal选项并默认启用(leeys888) 新增adaptivepooling vulkan实现(zylo117) 默认使用net局部的内存池 默认使用大核心的cpu作为线程数 在较新的adreno/mali gpu上启用fp16s/int8s 修正int8 armv7 conv1x1s1 requant无neon计算错误 conv3x3s1 winograd42 arm neon优化 通用convolution im2col sgemm的arm neon优化 常规的AVX2 convolution优化(zhiliu6) 优化ssd detectionoutput候选框计算(WeiChungChang) 在旧版adreno驱动时使用桥接的image上传下载 修复inplace forward(gdh1995) 消除NCNNBENCHMARK启用时不必要的数据复制(yx9527) 改善megvii风格的shufflechannel转换 onnx2ncnn自动拓扑排序 改善onnx2ncnn layernorm转换 ncnnoptimize可以切分模型(chentyjpm) mlir2ncnn设置自定义llvm/mlr路径(daquexian) 修复多输入模型使用gpu推理可能导致的数据错误 修复gpu image分配失败的回退cpu的问题 修复gpu buffer2host的问题 修复某些pipeline编译失败的问题(zchrissirhcz) 修复macos编译问题(leeys888) 修复onnx2ncnn转换某些memorydata shape错误 修复python model zoo下载(caishanli) 修复ncnnoptimize遇到多个自定义层崩溃问题 cmake寻找和链接thread库 更新glslang版本(proydakov) int8量化工具支持adaptive pool(GuoxiaWang) 上传wheel到pypi(caishanli) 修复python net extractor销毁顺序的问题(caishanli) 新增python vulkan test(caishanli) 修正python setup.py缺失的import(zylo117) 更新convertmodel.com链接(daquexian) 更新mlir tf2 dialect 修正一些拼写错误(zchrissirhcz, caishanli, zhiqwang) ios最低版本要求9.0(DaChengTechnology) 关于在自己项目使用ncnn的文档(zchrissirhcz) readme新增nanodet(RangiLyu) 补充android cmake ninja编译方法(ncnnnnn) readme更新各个算法链接(linser233) 修正how-to-build文档中benchncnn输出格式(ncnnnnn) 新增build-mlir2ncnn文档(zchrissirhcz) 修复nanodet示例代码的变量重名(RangiLyu) 修复yolact示例代码的越界问题(cmdbug) 新增nanodet python demo(caishanli) 新增有关nvidia gpu无法开启vulkan问题的文档(PENGUINLIONG)

- C++
Published by github-actions[bot] almost 5 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20210124 5e4ea0b

编译版本，默认配置，android-ndk-r21d，xcode 12.2，ubuntu-16.04，ubuntu-18.04，ubuntu-20.04，vs2017，vs2019 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x8664 | |ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x8664 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads |

添加python绑定，默认不编译(caishanli) 新增cmake选项NCNNSHAREDLIB编译动态库，pimpl实现模式 新增cmake选项NCNNPLATFORMAPI控制是否调用平台相关的api 大幅更新 C api，增加底层 op 接口 Blob类的consumer成员改为单个 重构forwardlayer逻辑为更加简短 warpaffine整数实现和 arm neon 优化 新增pooling的adaptive参数，支持pytorch AdaptiveAvgPool2d/AdaptiveMaxPool2d转换(GuoxiaWang) 新增gru和rnn，以及对应的 arm neon 优化 lstm arm neon 优化 innerproduct aarch64 int8 gemm优化(tpoisonooo) padding支持1-3维，补充单元测试用例 packing pack8 arm neon 优化 重构onnx2ncnn和mlir2ncnn构图和优化逻辑，修复opsetversion=12模型转换错误 改善onnx lsrm/gru/rnn的转换和算子融合 interp vulkan 支持 aligncorner=True innerproduct现支持2维gemm计算 简化innerproduct x86 arm的pack分类和优化代码 自定义层注册添加customlayerdestroyer参数(caishanli) Reorg/PixelShuffle层支持nhwc模式，onnx DepthToSpace mode DCR转换 减少不必要的unpack/pack(maxfy1992) packing pack4 x86 sse 优化 conv1x1s1 pack4 x86 sse 优化 改善macos的arm64支持 修正 memorydata vulkan 没有packing的问题 单元测试检查layer的支持属性 onnx2ncnn跨batch的Transpose转换 mlir2ncnn使用更短的blob名字 ncnnoptimize中的aborted提示改为skipped 修复blob数量超出实际数量时ncnnoptimize崩溃的问题 android 平台自动链接 jnigraphics 当开启vulkan校验时会启用VKLAYERKHRONOSvalidation扩展 更换pyncnn model zoo地址(mosheliv) 检查NCNNMAXPARAM_COUNT越界(zchrissirhcz) simplepose例子添加提示(zchrissirhcz) 修复一些编译器警告(zchrissirhcz, ncnnnnn, proydakov) 修正一些代码的拼写错误(zchrissirhcz, ncnnnnn) 修复mingw-x64 simd编译错误(zchrissirhcz) operators文档添加convolutiondepthwise/crop/sigmoid/tanh(cavalleria) operators文档添加pooling(Sanster) 更新支持的平台矩阵(monkeyking) 新增github pull request文档(tpoisonooo) 增加 pytest option/allocator/net/extractor V831工具链(sunnycase) ci添加vs2015 ci添加python编译(caishanli) release的windows预编译包包含32位库以及vs2015版本 release添加linux/windows/android动态库预编译包

- C++
Published by github-actions[bot] about 5 years ago

ncnn - android ios macos linux windows webassembly 预编译库 20201218 5650b77

编译版本，默认配置，android-ndk-r21d，xcode 12.2，ubuntu-16.04，ubuntu-18.04，ubuntu-20.04，vs2017，vs2019 | file | content | arch | |---|---|---| |ncnn-full-source.zip |包含全部 submodule 代码的完整源码 | | |ncnn-android.zip | android 静态库 | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-android-vulkan.zip | android 静态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x8664 | |ncnn-ios.zip | ios 静态库，w/o bitcode | armv7 + arm64 + arm64e + i386 + x8664 | |ncnn-ios-vulkan.zip | ios 静态库，支持 GPU，w/o bitcode | arm64 + arm64e + x8664 | |ncnn-macos.zip | macos 静态库 | x8664 + arm64 | |ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x8664 + arm64 | |ncnn-ubuntu.zip | ubuntu linux 静态库，支持 GPU，模型转换工具 | x8664 | |ncnn-windows.zip | windows 静态库，支持 GPU，模型转换工具 | x8664 | |ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads |

ncnnoptimize和ncnn2mem自动处理自定义op 新增获取ncnn版本的API：const char* ncnn_version(); Eltwise层支持一维和二维输入 开启更多vulkan扩展，根据gpu厂商设定较可靠的subgroup size 修正macos/ios arm64 simpleomp崩溃 onnx2ncnn 转换gemm保留输入数据 采用github action编译openmp和预编译包，发布新版本 增加ios arm64e架构编译 修正gcc-4.4/gcc-4.8编译错误 修正一些编译警告(ncnnnnn, zchrissirhcz, proydakov) 修正 build.sh macos 编译参数(cavalleria) 更新 macos vulkan sdk(monkeyking) benchmark新增3970X和RTX8000数据(BUG1989) operators文档新增cast(xingxingRealzyx)

- C++
Published by github-actions[bot] about 5 years ago

ncnn - android ios 预编译库 20201208 0508315

编译版本，默认配置，android-ndk-r21d，cctools-port 895 + ld64-274.2 + ios 10.2 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664) ncnn-android-vulkan-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664，包含vulkan支持) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) ncnn-vulkan.framework.zip 是 ios 的静态库(arm64 + x8664，包含vulkan支持，MoltenVK-1.1.82.0) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664) glslang.framework.zip 是 ios ncnn glslang 运行时静态库(arm64 + x8664)

新增Mat pixel affine任意角度旋转平移缩放函数 新增两组点计算warpaffine矩阵和逆变换函数 x86 SSE2的pack4架构更新和一些优化，包括BatchNorm/Bias/BinaryOp/Clip/Concat/Convolution/ConvolutionDepthWise/Dropout/Eltwise/Flatten/HardSigmoid/HardSwish/Innerproduct/Mish/Padding/Pooling/PReLU/ReLU/Scale/Sigmoid/Swish/TanH(PENGUINLIONG) 在支持vulkan 1.1驱动上自动检测subgroup信息 新增跨平台类thread-local-storage 新增simpleomp，实现最少的llvm openmp abi运行函数 新增获取cpu大小核信息的getlittlecpucount()和getbigcpucount()(zchrissirhcz) 新增softplus层实现和onnx转换(ncnnnnn) 支持Apple M1芯片 支持Open Harmony OS(zchrissirhcz) Concat/Slice/Softmax支持axis负数的参数(Ca0L) 新增NCNNSSE2编译选项，可完全禁用x86和webassembly的SIMD优化 一些通用的x86 Convolution AVX2性能优化(zhiliu6) vulkan支持Crop和Padding一维和二维blob 新增keras2ncnn模型转换工具(MarsTechHAN) Interp支持aligncorner=True并支持onnx Resize转换(maxfy1992) 新增yolov5例子(Zhengtq) 新增nanodet例子 vulkan image storage shader统一使用image3d存储类型 禁用NCNNTHREADS时的NCNNXADD实现 老旧adreno驱动不再启用image类型，修复gpu推理错误 去除ncnnoptimize过时的aarch64自动调优和相关文档 ncnnoptimize合并Reduction为Global Pooling ncnnoptimize替换单系数PReLU为Leaky ReLU ncnnoptimize清理broadcasting BinaryOp前的冗余Expand ncnnoptimize在shape推断后输出MAC和预计的内存足迹 有关opencv-mat转换和旋转文档的错误修正(ncnnnnn) 修正arm82 fp16s crop一维和二维错误的问题 Extractor::extract 支持第三个flag参数避免layout和存储类型转换(MarsTechHAN) abs()替换为fabs()(zchrissirhcz) 大量的编译器警告修复(proydakov, ncnnnnn, zchrissirhcz, pH5) ncnn可在c++03标准下编译 修复c++14标准的编译问题(nullptr-leo) 修复NCNNPIXEL关闭时的编译(tpoisonooo, nullptr-leo) 修复protobuf旧版本编译错误(deepage) cmake开关NCNNOPENCV更名为NCNN_SIMPLEOCV 修正yolact例子的颜色越界(zchrissirhcz) onnx2ncnn支持Max Min Pow与常数的转换 onnx2ncnn支持Pad channel参数 onnx2ncnn MatMul转换支持其中一个为MemoryData输入 修正onnx2ncnn Slice参数转换溢出的问题 修正onnx2ncnn和ncnnoptimize的groupnorm转换 mlir2ncnn适配新mlir api mlir2ncnn合并keras风格的batchnorm和instancenorm FAQ新增windows dll卸载崩溃的解决方案(qiqikit) 新增最小化编译ncnn二进制包的中文英文文档(songqun) 新增openmp最佳实践文档(youzainn) 改善编译步骤文档(baryluk) 一些文档和代码注释的拼写错误修正(HollowMan6, Zhengtq) 算子文档更新(xingxingRealzyx, LosReturn, Ca0L) 新增有关convertmodel.com的信息(daquexian) ci新增webassembly-nosimd和webassembly-simpleomp编译 ci新增android ndk-r16b编译 ci新增vs2017 cpu gpu编译 ci新增macos arm64编译 ci新增codeql分析

- C++
Published by nihui about 5 years ago

ncnn - android ios 预编译库 20200916 b766c8c

编译版本，默认配置，android-ndk-r21d，cctools-port 895 + ld64-274.2 + ios 10.2 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664) ncnn-android-vulkan-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664，包含vulkan支持) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) ncnn-vulkan.framework.zip 是 ios 的静态库(arm64 + x8664，包含vulkan支持，MoltenVK-1.1.82.0) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664) glslang.framework.zip 是 ios ncnn glslang 运行时静态库(arm64 + x8664)

armv8.2 fp16s/fp16sa优化，包括batchnorm/binaryop/clip/convolution/convolutiondepthwise/deconvolution/deconvolutiondepthwise/eltwise/flatten/hardsigmoid/hardswish/innerproduct/interp/mish/packing/padding/pooling/prelu/relu/reshape/shufflechannel/sigmoid/slice/swish/tanh/unaryop以及对应的pack8优化实现 默认启用fp16计算功能 Mat frompixels/frompixelsresize接受ROI参数实现crop+resize 更精细的cpu绑定接口 新增gemm 新增groupnorm，支持pytorch groupnorm转换 新增layernorm 无affine的instancenorm/groupnorm ncnnoptimize最后的flag设1表示转fp16模型(by zchrissirhcz) simplestl新增list实现，完全去除libstdc++依赖(by nullptr-leo) 开放glsl编译spirv接口 interp允许接受第二个blob作为参考size packing 遵守线程数设置 windows上寻找vulkan-sdk时给出提示信息(by zchrissirhcz) yolov3detectionoutput层avx优化(by zhiliu6) mxnet reduction 参数兼容数组和单个数字 ncnnoptimize自动合并binaryop-with-scalar 修正opencv 2.x/4 编译问题(by zchrissirhcz) 修复resizebilinearc4可能的crash 修正开启bf16s时extract可能没有转回fp32的问题 修正老编译器UINT64MAX编译错误(by ncnnnnn) 修正vulkan conv1x1s1 pack1计算错误 修正onnx2ncnn在转换resize时可能的crash loadparammem的参数必须以\0结尾 更新mlir tf2 dialect mlir2ncnn转换tf.Maximum/tf.Minimum/tf.ResizeBilinear mlir2ncnn合并instancenorm mlir2ncnn合并keras风格的Conv2d/Dense 修正yolov4例子bgr2rgb(by MarsTechHAN and qaz734913414) 修正darknet maxpool padding size转换(by ruru5697) ncnn cmake target自动依赖glslang(by youzainn) 修正powerpc64编译问题，绕过interp altivec优化bug 修正armv7带stride参数from_pixels bus error 单元测试新增mat pixel resize 默认不编译ncnn单元测试(by caishanli) ci最低编译环境为ubuntu-16.04，c++03 添加telegram群聊(by zchrissirhcz)

- C++
Published by nihui over 5 years ago

ncnn - android ios 预编译库 20200727 bedf00a

编译版本，默认配置，android-ndk-r21d，cctools-port 895 + ld64-274.2 + ios 10.2 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664) ncnn-android-vulkan-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664，包含vulkan支持) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) ncnn-vulkan.framework.zip 是 ios 的静态库(arm64 + x8664，包含vulkan支持，MoltenVK-1.1.82.0) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664) glslang.framework.zip 是 ios ncnn glslang 运行时静态库(armv7 + arm64 + i386 + x8664)

x86 avx优化，包括batchnorm/bias/binaryop/cast/clip/concat/convolution/convolutiondepthwise/crop/dropout/eltwise/flatten/hardsigmoid/hardswish/innerproduct/lrn/lstm/mish/packing/padding/pooling/prelu/relu/reshape/scale/sigmoid/slice/swish/tanh以及对应的pack8优化实现(by Timen) arm lstm neon优化(by Timen) 附带中间状态输入输出的lstm(by Timen) 使用在线pipeline缓存大幅优化gpu推理的模型加载效率，默认启用 使用gpu推理时自动创建instance 全局开启armv8.2和avx编译，运行时判断cpu特性使用不同的优化代码 C api 上层封装和squeezenetcapi例子 降低摄像头循环调用ncnn时openmp线程的cpu负载 新增darknet2ncnn教程，yolov4-tiny(by zhiliu6) mlir2ncnn模型转换工具，可以转换常用分类模型/pix2pi2 修正usepackinglayout/usebf16storage选项打开时，int8推理错误 修正当输出层支持bf16s时，没有转换为fp32的错误 修正gpu out of allocator错误 onnx shufflechannel兼容megvii写法 改善onnx slice转换兼容性 改善onnx resize转换兼容性 改善onnx simplified后的normalize转换兼容性 改善reshape nhwc的兼容性 修正deconvolution output shape和padding的处理 修复conv3x3s1 pack1to4 bf16s计算错误 修正tanh mips计算错误 修正输入一维数据和mish激活时convolution计算错误 修正interp nearest计算错误 绕过nvidia显卡上normalize/softmax计算错误 绕过nvidia显卡上padding reflect计算错误 去掉priorbox fp16s的绕过手段 绕过qcom adreno老驱动winograd计算错误的问题 ios打包glslang ci增加squeezenet/matpixelsrotate ci新增riscv32/riscv64/mips32/mips64，包括riscv-v扩展和mips-msa扩展 新增yolov4例子(by zhiliu6) FAQ新增jpg解码和resize章节(by zchrissirhcz) benchmark新增jstson agx(by zineos)

- C++
Published by nihui over 5 years ago

ncnn - android ios 预编译库 20200616 622879a

编译版本，默认配置，android-ndk-r21d，cctools-port 895 + ld64-274.2 + ios 10.2 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664) ncnn-android-vulkan-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664，包含vulkan支持) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664，bitcode) ncnn-vulkan.framework.zip 是 ios 的静态库(arm64 + x8664，bitcode，包含vulkan支持，MoltenVK-1.1.82.0) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x86_64，bitcode)

adreno gpu image存储+fp16p/fp16s/fp16pa/fp16sa优化，在qcom855之前的高通芯片上默认启用，包括全部gpu shader 新增darknet转换器，支持yolov4和efficientnetb0-yolov3(by zhiliu6) 新增simplestl，可替代std::string/std::vector，默认不启用(by scarsty) 新增NCNNLOGE宏，android自动在adb logcat输出信息(by maxint) 运行时生成spirv，大幅减小gpu库体积 新增python绑定链接 新增查询当前可用gpu显存接口 gpu fp16/fp32转换，buffer/image转换，全部融合入packing层 gpu device级别复用packing/unpacking管线 3d padding，新增blazeface benchmark(by Timen) 新增yuv420sp2rgbhalf快速实现(by tpoisonooo) interp pack4 bf16s bf16s-pack4 neon优化 改善fbnetv2 hardsigmoid hardswish识别转换 修复ncnn作为sub project编译问题(by MarisaKirisame) 修复int8 pooling(by yx9527) 修复innerproduct arm sigmoid缺失的问题 修复mxnet slice None转换crop错误(by ddddwee1) 新增mish层(by zhiliu6) 新增swish层(by zhiliu6) 改善roialign detectron2转换兼容性(by wkcn) 新增语音相关的statisticspooling层(by Wang-Charles) 新增deepcopy工具层 改善mxnet gluon导出list类型参数的转换(by papercatnku) 改善onnx swish识别转换 更稳定的arm tanhps优化实现 cast bfloat16/float32转换的avx优化(by Timen) ncnnoptimize合并scalar binaryop，包括sub/div ncnnoptimize合并weighted sum ncnnoptimize合并convolution + mish(by zhiliu6) 修正binaryop gpu special type 2/4的传播条件 修正ncnn2mem输出param.bin文件路径(by GuoxiaWang) 修复设置cpu affinity mask时可能的越界错误 修复老旧adreno/mali驱动image存储crash的问题 修复多国语系中param加载错误的问题 修复gpu convolution winograd在有shape hint时crop错误的问题 检查copycutborder参数(by tpoisonooo) 修正quantize文档的小错误(mengfu188) 树莓派4b benchmark(by elejke) qcom865开启fp16计算功能 mali-t880/g51/g52/g71/g72开启fp16计算功能 更新qcom810/qcom660/qcom835/qcom855+/kirin970 benchmark数据 统一code style 单元测试新增全部op的image存储变种 github自动识别comp为GLSL 修复旧版vulkan-sdk编译(by xfan1024) ios编译bitcode和native两种版本

- C++
Published by nihui over 5 years ago

ncnn - android ios 预编译库 20200413 5580da4

编译版本，默认配置，android-ndk-r19c，cctools-port 895 + ld64-274.2 + ios 10.2 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664) ncnn-android-vulkan-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664，包含vulkan支持) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664，bitcode) ncnn-vulkan.framework.zip 是 ios 的静态库(arm64 + x8664，bitcode，包含vulkan支持，MoltenVK-1.1.82.0) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x86_64，bitcode)

bfloat16数据类型存储和算子优化实现，默认不启用，主要算子armv7/aarch64特化优化，packing布局的armv7/aarch64特化优化（包括BinaryOp/Cast/Clip/Concat/Convolution/ConvolutionDepthWise/Crop/Eltwise/Flatten/HardSigmoid/HardSwish/Innerproduct/Packing/Padding/Pooling/ReLU/ShuffleChannel/Sigmoid/Slice/TanH） 默认启用cpu packinglayout加速 Mat topixels/topixelsresize arm neon优化 mips算子优化absval/bias/clip/sigmoid/softmax/tanh(by nullptr-leo) gpu shader按下标创建并自动获得specialization和pushconstant数量 android hardwarebuffer导入VkMat接口重构 为避免对齐问题，去除全部VkMat局部引用构造函数 VkMat和Command接口重构，去除staging成员，简化上传下载API 可指定cpu id的线程精准绑定接口 Mat PixelType 新增 BGRA 和相关转换类型 BinaryOp广播规则新增左值attention type 3/4 LSTM单向双向算子和onnx转换(支持chineseocrlite) 新增工具层DeepCopy float32与bfloat16转换函数 命名enum类型(by caishanli) benchncnn新增冷却时间开关(by kalcohol) RK3288和RK3399 gpu开启fp16计算功能 visual studio 源码分组(by kalcohol) 修复innerproduct requant计算问题(by yx9527) 修复flatten gpu fp16p pack1to4/pack1to8某些shape运算错误 修复gpu非coherent显存不一致问题 改善onnx新版Pad/Resize/Clip/Slice转换兼容性 改善onnx hardsigmoid/hardswish识别转换 修复onnx模型某些BinaryOp输入丢失问题 docs文件夹自动同步wiki 单元测试增加到40个(by xieydd monkeyking) 单元测试增加gpu fp16p，gpu pack8和cpu bf16s变种 Travis CI新增arm32编译+单元测试+覆盖率 codecov代码覆盖率整合 ios编译开启bitcode windows android库编译脚本(by kalcohol) 修复windows上的mingw编译(by qaz734913414) cv::Mat与ncnn::Mat转换文档 高效roi/resize/rotate文档 protobuf安装问题FAQ(by tpoisonooo) 新增yolact实例分割例子

- C++
Published by nihui almost 6 years ago

ncnn - android ios 预编译库 20200226 57bedd5

编译版本，默认配置，android-ndk-r19c，cctools-port 895 + ld64-274.2 + ios 10.2 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664) ncnn-android-vulkan-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664，包含vulkan支持) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) ncnn-vulkan.framework.zip 是 ios 的静态库(arm64 + x8664，包含vulkan支持，MoltenVK-1.1.82.0) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x86_64)

实现全部pack8 shader，默认不启用 shader存取宏改为function-style 所有gpu算子加载时会尝试读取shape hint并调整localsize 单元测试增加到30个 ncnnoptimize离线shape推断 实现pixelshuffle的cpu/gpu推理 onnx pixelshuffle转换 im2col将遵循sgemm_convolution选项开关 改善qcom adreno老驱动兼容性 qcom855/855plus开启gpu fp16a功能 chgemm和int-requant计算错误修复(by tpoisonooo) cmake生成VS工程分组(by kalcohol) 量化工具默认加入编译(by kalcohol) fp32/fp16 avx2优化(by zhiliu6) avx2卷积计算错误修正(by zhiliu6) 很多很多算子的bug修复

- C++
Published by nihui about 6 years ago

ncnn - android ios 预编译库 20200106 6f2ef19

编译版本，默认配置，android-ndk-r19c，cctools-port 895 + ld64-274.2 + ios 10.2 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664) ncnn-android-vulkan-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664，包含vulkan支持) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) ncnn-vulkan.framework.zip 是 ios 的静态库(arm64 + x8664，包含vulkan支持，MoltenVK-1.1.82.0) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x86_64)

pixel rotate api，8种90度角度旋转镜像翻转优化，支持stride参数和ROI ncnn example model zoo提供下载 Mat frompixels(resize)/topixels(resize)支持stride参数和ROI android 8.0支持android hardware buffer转换vkmat 修复旧arm mali驱动兼容性问题 改善onnx prelu/flatten转换兼容性 pytorch normalize转换 normalize支持inplace normalize vulkan slice pack4优化 slice vulkan per-channel padding ncnnoptimizer删除无用的pooling 1x1s1 ncnnoptimizer删除无用的memorydata 修复deconvolution vulkan计算错误 修复pooling vulkan SAME pad, avgpoolcountinclude_pad 修复可能的 staging buffer data race 修正prelu gpu计算错误 优化yolov3 output性能 vulkan spatial attention broadcasting 修正fasterrcnn gpu fp16p计算错误 修正conv1x1s1 gpu fp16p计算错误 改善pytorch shufflenetv2模型转换 ci新增webassembly

- C++
Published by nihui about 6 years ago

ncnn - android ios 预编译库 20191113 9593783

编译版本，默认配置，android-ndk-r19c，cctools-port 895 + ld64-274.2 + ios 10.2 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664) ncnn-android-vulkan-lib 是 android 的静态库(armeabi-v7a + arm64-v8a + x86 + x8664，包含vulkan支持) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) ncnn-vulkan.framework.zip 是 ios 的静态库(arm64 + x8664，包含vulkan支持，MoltenVK-1.1.82.0) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x86_64)

pack内存布局推断neon优化(armv7+aarch64)：conv1x1s1 conv1x1s2 conv3x3s1 conv3x3s1-winograd conv3x3s2 conv5x5s1 conv5x5s2 conv7x7s2 convdw3x3s1 convdw3x3s2 convdw5x5s1 convdw5x5s2 group-convolution/deconvolution pooling3x3s2-max pooling2x2s2-max padding relu hardsigmoid hardswish innerproduct reshape flatten shufflechannel 移除接口中的Option默认参数，预处理函数只使用1线程 mat输出新增颜色转换rgb2rgba/bgr2rgba/gray2rgba 新增android Bitmap与Mat直接转换函数 新增android Asset加载模型函数 新增NNIE ImageWatch插件 改善deconvolution pad/adj参数兼容性 新增Noop 新增convolution padvalue参数 unaryop vulkan实现tanh 修正radv驱动instancenorm crash mxnet hardsigmoid/hardswish融合转换 onnx 1维batchnorm融合转换 onnx split转换 Reduction新增PROD/L1/L2/LogSum/LogSumExp以及keepdims参数 onnx ReduceMax/ReduceMin/ReduceMean/ReduceProd/ReduceSum/ReduceSumSquare/ReduceL1/ReduceL2/ReduceLogSum/ReduceLogSumExp转换 改善mxnet和onnx slice转换兼容性 onnx Unsqueeze/Squeeze转换 onnx Pooling ceilmode转换 新增DataReader接口，方便从加密数据加载 修复某些手机无法识别大小核的问题 ncnnoptimize融合工具保留参数中的浮点精度 修复arm平台某些参数下im2col+gemm实现错误的问题 修复gpu推断使用fp16存储上传权重时可能的越界写问题 修复hisim100编译错误 int8 convolution winograd43精度提升 ncnn2table工具兼容性改善 ci新增windows-vs2017-gpu cmake选项NCNNDISABLEPIC禁用PIC 新增retinaface人脸检测例子 新增mobilenetv3-ssd通用物体检测例子 benchmark新增shufflenetv2 benchmark开启pack内存布局推断功能 新增android x86/x8664预编译库

- C++
Published by nihui over 6 years ago

ncnn - android ios 预编译库 20190908 91ef4ee

编译版本，默认配置，android-ndk-r19c，cctools-port 895 + ld64-274.2 + ios 10.2 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn-android-vulkan-lib 是 android 的静态库(armeabi-v7a + arm64-v8a，包含vulkan支持) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) ncnn-vulkan.framework.zip 是 ios 的静态库(arm64 + x8664，包含vulkan支持，MoltenVK-1.1.82.0) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x86_64)

搬运了很多很多wiki文档 新增实验性pack内存布局推断：absval batchnorm clip relu sigmoid packing convolution convolutiondepthwise innerproduct pooling flatten prelu scale dropout softmax binaryop deconvolution deconvolutiondepthwise concat eltwise cast split 新选项usepackinglayout控制是否cpu使用pack内存布局推理 conv1x1s1 pack4 sgemm arm neon优化 conv3x3s1 pack4 winograd arm neon优化 tanh arm neon优化 新增模型无finetune量化工具ncnn2table和readme(默认不编译) ncnn2table新增swapRB参数 ncnnoptimize在armlinux自动卷积调优 ncnnoptimize自动删除binaryop前无用的reshape 新增hardsigmoid 新增selu，onnx 支持转换 新增hardswish padding支持reflect模式 pooling avg新参数countincludepad，mxnet/onnx支持转换 convolution deconvolution支持四个方向不等长padding onnx autopad SAMELOWER转换 deconvolution新参数outputadj和outputshape onnx resize转换 onnx Div转换 mxnet BilinearResize2D转换 修正 mxnet onnx slice转换 pytorch onnx channelshuffle转换 pytorch onnx hardsigmoid hardswish转换 修正gpu多线程显存池共享问题 concat vulkan实现pack1to4 pack4to1to4 binaryop vulkan实现broadcast instancenorm vulkan实现 crop vulkan实现pack1to4 pack4to1 可移植的thread/condition-variable类 添加hisiv600 hi3559V100工具链文件 cmake编译系统更新，头文件安装到include/ncnn 更新mobilenetv2yolov3 benchmark 新增mobilenet_v3 benchmark ncnn模型可在netron中可视化 新增人体关键点定位例子simplepose 更新android squeezencnn工程

- C++
Published by nihui over 6 years ago

ncnn - android ios 预编译库 20190611 bade132

编译版本，默认配置，android-ndk-r19c，cctools-port 895 + ld64-274.2 + ios 10.2 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn-android-vulkan-lib 是 android 的静态库(armeabi-v7a + arm64-v8a，包含vulkan支持) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) ncnn-vulkan.framework.zip 是 ios 的静态库(arm64 + x8664，包含vulkan支持，MoltenVK-1.1.82.0) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x86_64)

新增算子融合工具 ncnnoptimize (bn + scale / conv + bn / deconv + bn / innerproduct + bn / conv + relu 等) armv7/arm64 conv1x1s2 armv7/arm64 其他卷积的 sgemm 优化 int8 requantize 层融合实现全int8存储 修复旧版本 cmake openmp 兼容性 option api 变动，移除全局option frompixelsresize 越界读修正 x86 convolution avx2 优化 x86 convolution sse2 优化 interp resize bicubic 插值 gpu convolution/padding 支持 SAME pad gpu conv1x1s1 优化 gpu conv3x3s1 winograd-f23 优化 gpu fp16 packed 优化，支持全部gpu gpu fp16 storage 优化，支持绝大多数桌面gpu gpu fp16 arithmetic 优化，默认关闭 允许创建自定义 vulkan compute pipeline 并嵌入推断过程 gpu 各层耗时统计 vulkan layer 架构调整 gpu fp16p fp16s fp16a int8s in8a 控制开关 更简单的多卡 gpu 设置 api 新的分割例子 pelee ssd segmentation benchmark fp32 算子融合

- C++
Published by nihui over 6 years ago

ncnn - android ios 预编译库 20190320 dbf2052

编译版本，默认配置，android-ndk-r18b，cctools-port 895 + ld64-274.2 + ios 10.2 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn-android-vulkan-lib 是 android 的静态库(armeabi-v7a + arm64-v8a，包含vulkan支持) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) ncnn-vulkan.framework.zip 是 ios 的静态库(arm64 + x8664，包含vulkan支持，MoltenVK-1.1.82.0) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x86_64)

新增实验性gpu推断：AbsVal, BatchNorm, BinaryOp(no broadcasting), Clip, Concat, Convolution(pad -233 not supported), ConvolutionDepthWise(pad -233 not supported), Crop, Deconvolution, DeconvolutionDepthWise, Dropout, Eltwise, Flatten, InnerProduct, Interp, LRN, Packing, Padding, Permute, Pooling(pad SAME not supported), PReLU, PriorBox, ReLU, Reorg, Reshape, Scale, ShuffleChannel, Sigmoid, Softmax, TanH, UnaryOp 支持gpu/cpu混合推断 无溢出的int8卷积计算 精度更好的int8量化方法 element packing数据存储 conv3x3s1 int8 aarch64优化 conv3x3s2 int8 armv7/aarch64优化 conv1x1s1 int8 aarch64优化 convdw3x3s1 int8 aarch64优化 convdw3x3s2 int8 aarch64优化 修正armv7-without-neon编译 example例子全部支持gpu运算 兼容onnx/mxnet的upsample和slice转换 squeezencnn增加gpu识别按钮 benchmark新增gpu推断 benchmark新增resnet50以及int8模型 ios openmp 更新为 7.0.1

- C++
Published by nihui almost 7 years ago

ncnn - android ios 预编译库 20181228 0991893

编译版本，默认配置，android-ndk-r17b，cctools-port 886 + ld64 264.3.102 + ios 9.3 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664)

clip armv7/aarch64优化 convdw5x5 armv7/aarch64优化 conv3x3s1 aarch64优化 convdw3x3 int8 armv7 优化 conv1x1/conv3x3 int8 aarch64 优化 新增从内存加载明文param接口 Net::loadparammem() 修正permute/dequantize/lstm/innerproduct int8 新增psroipooling/roialign 新增VS ImageWatch插件 修复新版本cmake的openmp编译 支持树莓派3编译 支持ARM-linux和hisi平台编译 更新cmake-ios工具链 修正yolov2多尺度检测 支持yolov3和yolov3例子 darknet2ncnn转换器 支持R-FCN和R-FCN例子 支持mxnet-ssd模型转换 新增shufflenetv2例子 兼容onnx opset7/8模型转换，增加更多op转换 修正mxnet batchnorm fix_gamma参数转换 新增yuv420sp转RGB和缩放函数 benchmark新增mnasnet/proxylessnasnet/mobilenet-yolov2/mobilenet-yolov3

- C++
Published by nihui about 7 years ago

ncnn - android ios 预编译库 20180830 ef36d79

编译版本，默认配置，android-ndk-r15c，cctools-port 886 + ld64 264.3.102 + ios 9.3 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664)

blob/workspace内存池接口 winograd/sgemm/int8推断运行时开关 更精细的多线程控制 caffe模型转换加载int8量化表 int8推断(experimental) windows高精度时间戳 conv3x3s2优化 depthwiseconv3x3s1 arm64优化 conv1x1和conv3x3 int8 armv7优化 修正dilated+stride conv快速运算 mxnet-shufflenet模型转换 新增mobilenetv2ssdlite例子

- C++
Published by nihui over 7 years ago

ncnn - android ios 预编译库 20180704 d0cad77

编译版本，默认配置，android-ndk-r15c，cctools-port 886 + ld64 264.3.102 + ios 9.3 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664)

- C++
Published by nihui over 7 years ago

ncnn - android ios 预编译库 20180427 b560252

编译版本，默认配置，android-ndk-r15c，cctools-port 886 + ld64 264.3.102 + ios 9.3 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664)

- C++
Published by nihui almost 8 years ago

ncnn - android ios 预编译库 20180314 656de48

编译版本，默认配置，android-ndk-r15c，cctools-port 886 + ld64 264.3.102 + ios 9.3 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664)

- C++
Published by nihui almost 8 years ago

ncnn - android ios 预编译库 20180129 f133729

编译版本，默认配置，android-ndk-r15c，cctools-port 886 + ld64 264.3.102 + ios 9.3 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664)

- C++
Published by nihui about 8 years ago

ncnn - android ios 预编译库 20171225 1f5c646

编译版本，默认配置，android-ndk-r15c，cctools-port 886 + ld64 264.3.102 + ios 9.3 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664)

- C++
Published by nihui about 8 years ago

ncnn - android ios 预编译库 20171017 d8193dd

编译版本，默认配置，android-ndk-r15c，cctools-port 886 + ld64 264.3.102 + ios 9.3 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664)

- C++
Published by nihui over 8 years ago

ncnn - android ios 预编译库 20170919 c641db8

编译版本，默认配置，android-ndk-r15c，cctools-port 886 + ld64 264.3.102 + ios 9.3 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664)

- C++
Published by nihui over 8 years ago

ncnn - android ios 预编译库 20170809 0b50826

编译版本，默认配置，android-ndk-r15c，cctools-port 886 + ld64 264.3.102 + ios 9.3 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664)

- C++
Published by nihui over 8 years ago

ncnn - android ios 预编译库 20170724 402cbee

编译版本，默认配置，android-ndk-r13b，cctools-port 886 + ld64 264.3.102 + ios 9.3 sdk libc++ ncnn-android-lib 是 android 的静态库(armeabi-v7a + arm64-v8a) ncnn.framework.zip 是 ios 的静态库(armv7 + arm64 + i386 + x8664) openmp.framework.zip 是 ios ncnn openmp 运行时静态库(armv7 + arm64 + i386 + x8664)

ncnn-android-lib.zip ncnn.framework.zip openmp.framework.zip

- C++
Published by nihui over 8 years ago