我在pytorch->onnx->ncnn对mobileNetv3模型转换的过程中，遇到了：1、onnx2ncnn步骤有不支持问题，使用了onnxsim对onnx模型进行了处理后，再进行onnx2ncnn时转换OK，得到解决；2、我在构建应用，使用extractor.extract()时需要blob的name或index，当我使用ncnn2mem将文件转换成*.id.h打开查看最后的index并使用后，出现输出为28个，而我需要输出的是4个啊，奇了怪了，咋回事呢？我又使用netron可视化工具分别查看了*.param和*.param.bin两个文件，发现*.param正常最后输出4个，.param.bin不正常最后输出的是28个，整体长度对比，.param要比*.param.bin的图要长一些，貌似好像被截断了，但我使用的是*.param啊，这到底是咋回事呢？
8条答案
按热度按时间d7v8vwbk1#
模型中所有的 blob 都可以通过 name 和 index 拿出来，id.h 中的 28 个 BLOB_XXX 一定包含了 param 中的全部 blob 名字了，如果你只用 param，无需使用 ncnn2mem 工具，直接用 param 和 bin 文件即可
https://github.com/Tencent/ncnn/wiki/use-ncnn-with-alexnet.zh#%E5%8A%A0%E8%BD%BD%E6%A8%A1%E5%9E%8B
2guxujil2#
.param文件如下：
7767517
112 187
Input input.1 0 1 input.1
Convolution Conv_0 1 1 input.1 785 0=16 1=3 11=3 2=1 12=1 3=2 13=2 4=1 14=1 15=1 16=1 5=1 6=432
HardSwish Div_5 1 1 785 408 0=1.666667e-01 1=5.000000e-01
Split splitncnn_0 1 2 408 408_splitncnn_0 408_splitncnn_1
Convolution Conv_6 1 1 408_splitncnn_1 788 0=16 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=256
ReLU Relu_7 1 1 788 411
ConvolutionDepthWise Conv_8 1 1 411 791 0=16 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=144 7=16
ReLU Relu_9 1 1 791 414
Convolution Conv_10 1 1 414 794 0=16 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=256
BinaryOp Add_11 2 1 794 408_splitncnn_0 417 0=0
Convolution Conv_12 1 1 417 797 0=64 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1024
ReLU Relu_13 1 1 797 420
ConvolutionDepthWise Conv_14 1 1 420 800 0=64 1=3 11=3 2=1 12=1 3=2 13=2 4=1 14=1 15=1 16=1 5=1 6=576 7=64
ReLU Relu_15 1 1 800 423
Convolution Conv_16 1 1 423 803 0=24 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1536
Split splitncnn_1 1 2 803 803_splitncnn_0 803_splitncnn_1
Convolution Conv_17 1 1 803_splitncnn_1 806 0=72 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1728
ReLU Relu_18 1 1 806 428
ConvolutionDepthWise Conv_19 1 1 428 809 0=72 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=648 7=72
ReLU Relu_20 1 1 809 431
Convolution Conv_21 1 1 431 812 0=24 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1728
BinaryOp Add_22 2 1 812 803_splitncnn_0 434 0=0
Convolution Conv_23 1 1 434 815 0=72 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1728
ReLU Relu_24 1 1 815 437
ConvolutionDepthWise Conv_25 1 1 437 818 0=72 1=5 11=5 2=1 12=1 3=2 13=2 4=2 14=2 15=2 16=2 5=1 6=1800 7=72
ReLU Relu_26 1 1 818 440
Convolution Conv_27 1 1 440 821 0=40 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=2880
Split splitncnn_2 1 2 821 821_splitncnn_0 821_splitncnn_1
Pooling GlobalAveragePool_28 1 1 821_splitncnn_1 443 0=1 4=1
Convolution Conv_29 1 1 443 824 0=10 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=400
ReLU Relu_30 1 1 824 446
Convolution Conv_31 1 1 446 827 0=40 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=400
HardSigmoid Div_35 1 1 827 454 0=1.666667e-01 1=5.000000e-01
BinaryOp Mul_36 2 1 821_splitncnn_0 454 455 0=2
Split splitncnn_3 1 2 455 455_splitncnn_0 455_splitncnn_1
Convolution Conv_37 1 1 455_splitncnn_1 830 0=120 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=4800
ReLU Relu_38 1 1 830 458
ConvolutionDepthWise Conv_39 1 1 458 833 0=120 1=5 11=5 2=1 12=1 3=1 13=1 4=2 14=2 15=2 16=2 5=1 6=3000 7=120
ReLU Relu_40 1 1 833 461
Convolution Conv_41 1 1 461 836 0=40 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=4800
Split splitncnn_4 1 2 836 836_splitncnn_0 836_splitncnn_1
Pooling GlobalAveragePool_42 1 1 836_splitncnn_1 464 0=1 4=1
Convolution Conv_43 1 1 464 839 0=10 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=400
ReLU Relu_44 1 1 839 467
Convolution Conv_45 1 1 467 842 0=40 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=400
HardSigmoid Div_49 1 1 842 475 0=1.666667e-01 1=5.000000e-01
BinaryOp Mul_50 2 1 836_splitncnn_0 475 476 0=2
BinaryOp Add_51 2 1 476 455_splitncnn_0 477 0=0
Split splitncnn_5 1 2 477 477_splitncnn_0 477_splitncnn_1
Convolution Conv_52 1 1 477_splitncnn_1 845 0=120 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=4800
ReLU Relu_53 1 1 845 480
ConvolutionDepthWise Conv_54 1 1 480 848 0=120 1=5 11=5 2=1 12=1 3=1 13=1 4=2 14=2 15=2 16=2 5=1 6=3000 7=120
ReLU Relu_55 1 1 848 483
Convolution Conv_56 1 1 483 851 0=40 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=4800
Split splitncnn_6 1 2 851 851_splitncnn_0 851_splitncnn_1
Pooling GlobalAveragePool_57 1 1 851_splitncnn_1 486 0=1 4=1
Convolution Conv_58 1 1 486 854 0=10 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=400
ReLU Relu_59 1 1 854 489
Convolution Conv_60 1 1 489 857 0=40 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=400
HardSigmoid Div_64 1 1 857 497 0=1.666667e-01 1=5.000000e-01
BinaryOp Mul_65 2 1 851_splitncnn_0 497 498 0=2
BinaryOp Add_66 2 1 498 477_splitncnn_0 499 0=0
Convolution Conv_67 1 1 499 860 0=240 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=9600
HardSwish Div_72 1 1 860 508 0=1.666667e-01 1=5.000000e-01
ConvolutionDepthWise Conv_73 1 1 508 863 0=240 1=3 11=3 2=1 12=1 3=2 13=2 4=1 14=1 15=1 16=1 5=1 6=2160 7=240
HardSwish Div_78 1 1 863 517 0=1.666667e-01 1=5.000000e-01
Convolution Conv_79 1 1 517 866 0=80 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=19200
Split splitncnn_7 1 2 866 866_splitncnn_0 866_splitncnn_1
Convolution Conv_80 1 1 866_splitncnn_1 869 0=200 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=16000
HardSwish Div_85 1 1 869 528 0=1.666667e-01 1=5.000000e-01
ConvolutionDepthWise Conv_86 1 1 528 872 0=200 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=1800 7=200
HardSwish Div_91 1 1 872 537 0=1.666667e-01 1=5.000000e-01
Convolution Conv_92 1 1 537 875 0=80 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=16000
BinaryOp Add_93 2 1 875 866_splitncnn_0 540 0=0
Split splitncnn_8 1 2 540 540_splitncnn_0 540_splitncnn_1
Convolution Conv_94 1 1 540_splitncnn_1 878 0=184 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=14720
HardSwish Div_99 1 1 878 549 0=1.666667e-01 1=5.000000e-01
ConvolutionDepthWise Conv_100 1 1 549 881 0=184 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=1656 7=184
HardSwish Div_105 1 1 881 558 0=1.666667e-01 1=5.000000e-01
Convolution Conv_106 1 1 558 884 0=80 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=14720
BinaryOp Add_107 2 1 884 540_splitncnn_0 561 0=0
Split splitncnn_9 1 2 561 561_splitncnn_0 561_splitncnn_1
Convolution Conv_108 1 1 561_splitncnn_1 887 0=184 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=14720
HardSwish Div_113 1 1 887 570 0=1.666667e-01 1=5.000000e-01
ConvolutionDepthWise Conv_114 1 1 570 890 0=184 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=1656 7=184
HardSwish Div_119 1 1 890 579 0=1.666667e-01 1=5.000000e-01
Convolution Conv_120 1 1 579 893 0=80 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=14720
BinaryOp Add_121 2 1 893 561_splitncnn_0 582 0=0
Split splitncnn_10 1 2 582 582_splitncnn_0 582_splitncnn_1
Convolution Conv_122 1 1 582_splitncnn_1 896 0=480 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=38400
HardSwish Div_127 1 1 896 591 0=1.666667e-01 1=5.000000e-01
ConvolutionDepthWise Conv_128 1 1 591 899 0=480 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=4320 7=480
HardSwish Div_133 1 1 899 600 0=1.666667e-01 1=5.000000e-01
Convolution Conv_134 1 1 600 902 0=112 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=53760
Split splitncnn_11 1 2 902 902_splitncnn_0 902_splitncnn_1
Pooling GlobalAveragePool_135 1 1 902_splitncnn_1 603 0=1 4=1
Convolution Conv_136 1 1 603 905 0=28 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=3136
ReLU Relu_137 1 1 905 606
Convolution Conv_138 1 1 606 908 0=112 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=3136
HardSigmoid Div_142 1 1 908 614 0=1.666667e-01 1=5.000000e-01
BinaryOp Mul_143 2 1 902_splitncnn_0 614 615 0=2
Convolution Conv_144 1 1 582_splitncnn_0 911 0=112 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=8960
BinaryOp Add_145 2 1 615 911 618 0=0
Split splitncnn_12 1 2 618 618_splitncnn_0 618_splitncnn_1
Convolution Conv_146 1 1 618_splitncnn_1 914 0=672 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=75264
HardSwish Div_151 1 1 914 627 0=1.666667e-01 1=5.000000e-01
ConvolutionDepthWise Conv_152 1 1 627 917 0=672 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=6048 7=672
HardSwish Div_157 1 1 917 636 0=1.666667e-01 1=5.000000e-01
Convolution Conv_158 1 1 636 920 0=112 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=75264
Split splitncnn_13 1 2 920 920_splitncnn_0 920_splitncnn_1
Pooling GlobalAveragePool_159 1 1 920_splitncnn_1 639 0=1 4=1
Convolution Conv_160 1 1 639 923 0=28 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=3136
ReLU Relu_161 1 1 923 642
Convolution Conv_162 1 1 642 926 0=112 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=3136
HardSigmoid Div_166 1 1 926 650 0=1.666667e-01 1=5.000000e-01
BinaryOp Mul_167 2 1 920_splitncnn_0 650 651 0=2
BinaryOp Add_168 2 1 651 618_splitncnn_0 652 0=0
Split splitncnn_14 1 2 652 652_splitncnn_0 652_splitncnn_1
Convolution Conv_169 1 1 652_splitncnn_1 929 0=672 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=75264
HardSwish Div_174 1 1 929 661 0=1.666667e-01 1=5.000000e-01
ConvolutionDepthWise Conv_175 1 1 661 932 0=672 1=5 11=5 2=1 12=1 3=1 13=1 4=2 14=2 15=2 16=2 5=1 6=16800 7=672
HardSwish Div_180 1 1 932 670 0=1.666667e-01 1=5.000000e-01
Convolution Conv_181 1 1 670 935 0=160 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=107520
Split splitncnn_15 1 2 935 935_splitncnn_0 935_splitncnn_1
Pooling GlobalAveragePool_182 1 1 935_splitncnn_1 673 0=1 4=1
Convolution Conv_183 1 1 673 938 0=40 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=6400
ReLU Relu_184 1 1 938 676
Convolution Conv_185 1 1 676 941 0=160 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=6400
HardSigmoid Div_189 1 1 941 684 0=1.666667e-01 1=5.000000e-01
BinaryOp Mul_190 2 1 935_splitncnn_0 684 685 0=2
Convolution Conv_191 1 1 652_splitncnn_0 944 0=160 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=17920
BinaryOp Add_192 2 1 685 944 688 0=0
Convolution Conv_193 1 1 688 947 0=672 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=107520
HardSwish Div_198 1 1 947 697 0=1.666667e-01 1=5.000000e-01
ConvolutionDepthWise Conv_199 1 1 697 950 0=672 1=5 11=5 2=1 12=1 3=2 13=2 4=2 14=2 15=2 16=2 5=1 6=16800 7=672
HardSwish Div_204 1 1 950 706 0=1.666667e-01 1=5.000000e-01
Convolution Conv_205 1 1 706 953 0=160 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=107520
Split splitncnn_16 1 2 953 953_splitncnn_0 953_splitncnn_1
Pooling GlobalAveragePool_206 1 1 953_splitncnn_1 709 0=1 4=1
Convolution Conv_207 1 1 709 956 0=40 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=6400
ReLU Relu_208 1 1 956 712
Convolution Conv_209 1 1 712 959 0=160 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=6400
HardSigmoid Div_213 1 1 959 720 0=1.666667e-01 1=5.000000e-01
BinaryOp Mul_214 2 1 953_splitncnn_0 720 721 0=2
Split splitncnn_17 1 2 721 721_splitncnn_0 721_splitncnn_1
Convolution Conv_215 1 1 721_splitncnn_1 962 0=960 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=153600
HardSwish Div_220 1 1 962 730 0=1.666667e-01 1=5.000000e-01
ConvolutionDepthWise Conv_221 1 1 730 965 0=960 1=5 11=5 2=1 12=1 3=1 13=1 4=2 14=2 15=2 16=2 5=1 6=24000 7=960
HardSwish Div_226 1 1 965 739 0=1.666667e-01 1=5.000000e-01
Convolution Conv_227 1 1 739 968 0=160 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=153600
Split splitncnn_18 1 2 968 968_splitncnn_0 968_splitncnn_1
Pooling GlobalAveragePool_228 1 1 968_splitncnn_1 742 0=1 4=1
Convolution Conv_229 1 1 742 971 0=40 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=6400
ReLU Relu_230 1 1 971 745
Convolution Conv_231 1 1 745 974 0=160 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=6400
HardSigmoid Div_235 1 1 974 753 0=1.666667e-01 1=5.000000e-01
BinaryOp Mul_236 2 1 968_splitncnn_0 753 754 0=2
BinaryOp Add_237 2 1 754 721_splitncnn_0 755 0=0
Convolution Conv_238 1 1 755 977 0=960 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=153600
HardSwish Div_243 1 1 977 764 0=1.666667e-01 1=5.000000e-01
Pooling AveragePool_245 1 1 764 766 0=1 1=7 11=7 2=7 12=7 3=0 13=0 14=0 15=0 5=1 6=0
Reshape Reshape_251 1 1 766 774 0=-1
InnerProduct Gemm_252 1 1 774 775 0=1280 1=1 2=1228800
BatchNorm BatchNormalization_253 1 1 775 776 0=1280
HardSwish Div_258 1 1 776 783 0=1.666667e-01 1=5.000000e-01
InnerProduct Gemm_259 1 1 783 784 0=4 1=1 2=5120
经过ncnn2mem之后生成的.id.h如下：
#ifndef NCNN_INCLUDE_GUARD_onnx_MobileNetV3_Large_weather_id_h
#define NCNN_INCLUDE_GUARD_onnx_MobileNetV3_Large_weather_id_h
namespace onnx_MobileNetV3_Large_weather_param_id {
const int LAYER_input_1 = 0;
const int BLOB_input_1 = 0;
const int LAYER_Conv_0 = 1;
const int BLOB_785 = 1;
const int LAYER_Div_5 = 2;
const int BLOB_408 = 2;
const int LAYER_splitncnn_0 = 3;
const int BLOB_408_splitncnn_0 = 3;
const int BLOB_408_splitncnn_1 = 4;
const int LAYER_Conv_6 = 4;
const int BLOB_788 = 5;
const int LAYER_Relu_7 = 5;
const int BLOB_411 = 6;
const int LAYER_Conv_8 = 6;
const int BLOB_791 = 7;
const int LAYER_Relu_9 = 7;
const int BLOB_414 = 8;
const int LAYER_Conv_10 = 8;
const int BLOB_794 = 9;
const int LAYER_Add_11 = 9;
const int BLOB_417 = 10;
const int LAYER_Conv_12 = 10;
const int BLOB_797 = 11;
const int LAYER_Relu_13 = 11;
const int BLOB_420 = 12;
const int LAYER_Conv_14 = 12;
const int BLOB_800 = 13;
const int LAYER_Relu_15 = 13;
const int BLOB_423 = 14;
const int LAYER_Conv_16 = 14;
const int BLOB_803 = 15;
const int LAYER_splitncnn_1 = 15;
const int BLOB_803_splitncnn_0 = 16;
const int BLOB_803_splitncnn_1 = 17;
const int LAYER_Conv_17 = 16;
const int BLOB_806 = 18;
const int LAYER_Relu_18 = 17;
const int BLOB_428 = 19;
const int LAYER_Conv_19 = 18;
const int BLOB_809 = 20;
const int LAYER_Relu_20 = 19;
const int BLOB_431 = 21;
const int LAYER_Conv_21 = 20;
const int BLOB_812 = 22;
const int LAYER_Add_22 = 21;
const int BLOB_434 = 23;
const int LAYER_Conv_23 = 22;
const int BLOB_815 = 24;
const int LAYER_Relu_24 = 23;
const int BLOB_437 = 25;
const int LAYER_Conv_25 = 24;
const int BLOB_818 = 26;
const int LAYER_Relu_26 = 25;
const int BLOB_440 = 27;
const int LAYER_Conv_27 = 26;
const int BLOB_821 = 28;
const int LAYER_splitncnn_2 = 27;
const int BLOB_821_splitncnn_0 = 29;
const int BLOB_821_splitncnn_1 = 30;
const int LAYER_GlobalAveragePool_28 = 28;
const int BLOB_443 = 31;
const int LAYER_Conv_29 = 29;
const int BLOB_824 = 32;
const int LAYER_Relu_30 = 30;
const int BLOB_446 = 33;
const int LAYER_Conv_31 = 31;
const int BLOB_827 = 34;
const int LAYER_Div_35 = 32;
const int BLOB_454 = 35;
const int LAYER_Mul_36 = 33;
const int BLOB_455 = 36;
const int LAYER_splitncnn_3 = 34;
const int BLOB_455_splitncnn_0 = 37;
const int BLOB_455_splitncnn_1 = 38;
const int LAYER_Conv_37 = 35;
const int BLOB_830 = 39;
const int LAYER_Relu_38 = 36;
const int BLOB_458 = 40;
const int LAYER_Conv_39 = 37;
const int BLOB_833 = 41;
const int LAYER_Relu_40 = 38;
const int BLOB_461 = 42;
const int LAYER_Conv_41 = 39;
const int BLOB_836 = 43;
const int LAYER_splitncnn_4 = 40;
const int BLOB_836_splitncnn_0 = 44;
const int BLOB_836_splitncnn_1 = 45;
const int LAYER_GlobalAveragePool_42 = 41;
const int BLOB_464 = 46;
const int LAYER_Conv_43 = 42;
const int BLOB_839 = 47;
const int LAYER_Relu_44 = 43;
const int BLOB_467 = 48;
const int LAYER_Conv_45 = 44;
const int BLOB_842 = 49;
const int LAYER_Div_49 = 45;
const int BLOB_475 = 50;
const int LAYER_Mul_50 = 46;
const int BLOB_476 = 51;
const int LAYER_Add_51 = 47;
const int BLOB_477 = 52;
const int LAYER_splitncnn_5 = 48;
const int BLOB_477_splitncnn_0 = 53;
const int BLOB_477_splitncnn_1 = 54;
const int LAYER_Conv_52 = 49;
const int BLOB_845 = 55;
const int LAYER_Relu_53 = 50;
const int BLOB_480 = 56;
const int LAYER_Conv_54 = 51;
const int BLOB_848 = 57;
const int LAYER_Relu_55 = 52;
const int BLOB_483 = 58;
const int LAYER_Conv_56 = 53;
const int BLOB_851 = 59;
const int LAYER_splitncnn_6 = 54;
const int BLOB_851_splitncnn_0 = 60;
const int BLOB_851_splitncnn_1 = 61;
const int LAYER_GlobalAveragePool_57 = 55;
const int BLOB_486 = 62;
const int LAYER_Conv_58 = 56;
const int BLOB_854 = 63;
const int LAYER_Relu_59 = 57;
const int BLOB_489 = 64;
const int LAYER_Conv_60 = 58;
const int BLOB_857 = 65;
const int LAYER_Div_64 = 59;
const int BLOB_497 = 66;
const int LAYER_Mul_65 = 60;
const int BLOB_498 = 67;
const int LAYER_Add_66 = 61;
const int BLOB_499 = 68;
const int LAYER_Conv_67 = 62;
const int BLOB_860 = 69;
const int LAYER_Div_72 = 63;
const int BLOB_508 = 70;
const int LAYER_Conv_73 = 64;
const int BLOB_863 = 71;
const int LAYER_Div_78 = 65;
const int BLOB_517 = 72;
const int LAYER_Conv_79 = 66;
const int BLOB_866 = 73;
const int LAYER_splitncnn_7 = 67;
const int BLOB_866_splitncnn_0 = 74;
const int BLOB_866_splitncnn_1 = 75;
const int LAYER_Conv_80 = 68;
const int BLOB_869 = 76;
const int LAYER_Div_85 = 69;
const int BLOB_528 = 77;
const int LAYER_Conv_86 = 70;
const int BLOB_872 = 78;
const int LAYER_Div_91 = 71;
const int BLOB_537 = 79;
const int LAYER_Conv_92 = 72;
const int BLOB_875 = 80;
const int LAYER_Add_93 = 73;
const int BLOB_540 = 81;
const int LAYER_splitncnn_8 = 74;
const int BLOB_540_splitncnn_0 = 82;
const int BLOB_540_splitncnn_1 = 83;
const int LAYER_Conv_94 = 75;
const int BLOB_878 = 84;
const int LAYER_Div_99 = 76;
const int BLOB_549 = 85;
const int LAYER_Conv_100 = 77;
const int BLOB_881 = 86;
const int LAYER_Div_105 = 78;
const int BLOB_558 = 87;
const int LAYER_Conv_106 = 79;
const int BLOB_884 = 88;
const int LAYER_Add_107 = 80;
const int BLOB_561 = 89;
const int LAYER_splitncnn_9 = 81;
const int BLOB_561_splitncnn_0 = 90;
const int BLOB_561_splitncnn_1 = 91;
const int LAYER_Conv_108 = 82;
const int BLOB_887 = 92;
const int LAYER_Div_113 = 83;
const int BLOB_570 = 93;
const int LAYER_Conv_114 = 84;
const int BLOB_890 = 94;
const int LAYER_Div_119 = 85;
const int BLOB_579 = 95;
const int LAYER_Conv_120 = 86;
const int BLOB_893 = 96;
const int LAYER_Add_121 = 87;
const int BLOB_582 = 97;
const int LAYER_splitncnn_10 = 88;
const int BLOB_582_splitncnn_0 = 98;
const int BLOB_582_splitncnn_1 = 99;
const int LAYER_Conv_122 = 89;
const int BLOB_896 = 100;
const int LAYER_Div_127 = 90;
const int BLOB_591 = 101;
const int LAYER_Conv_128 = 91;
const int BLOB_899 = 102;
const int LAYER_Div_133 = 92;
const int BLOB_600 = 103;
const int LAYER_Conv_134 = 93;
const int BLOB_902 = 104;
const int LAYER_splitncnn_11 = 94;
const int BLOB_902_splitncnn_0 = 105;
const int BLOB_902_splitncnn_1 = 106;
const int LAYER_GlobalAveragePool_135 = 95;
const int BLOB_603 = 107;
const int LAYER_Conv_136 = 96;
const int BLOB_905 = 108;
const int LAYER_Relu_137 = 97;
const int BLOB_606 = 109;
const int LAYER_Conv_138 = 98;
const int BLOB_908 = 110;
const int LAYER_Div_142 = 99;
const int BLOB_614 = 111;
const int LAYER_Mul_143 = 100;
const int BLOB_615 = 112;
const int LAYER_Conv_144 = 101;
const int BLOB_911 = 113;
const int LAYER_Add_145 = 102;
const int BLOB_618 = 114;
const int LAYER_splitncnn_12 = 103;
const int BLOB_618_splitncnn_0 = 115;
const int BLOB_618_splitncnn_1 = 116;
const int LAYER_Conv_146 = 104;
const int BLOB_914 = 117;
const int LAYER_Div_151 = 105;
const int BLOB_627 = 118;
const int LAYER_Conv_152 = 106;
const int BLOB_917 = 119;
const int LAYER_Div_157 = 107;
const int BLOB_636 = 120;
const int LAYER_Conv_158 = 108;
const int BLOB_920 = 121;
const int LAYER_splitncnn_13 = 109;
const int BLOB_920_splitncnn_0 = 122;
const int BLOB_920_splitncnn_1 = 123;
const int LAYER_GlobalAveragePool_159 = 110;
const int BLOB_639 = 124;
const int LAYER_Conv_160 = 111;
const int BLOB_923 = 125;
} // namespace onnx_MobileNetV3_Large_weather_param_id
#endif // NCNN_INCLUDE_GUARD_onnx_MobileNetV3_Large_weather_id_h
我需要拿最后的*.param中的Gemm_259，但是id.h中没有对应的；另外，我直接使用的是 param 和 bin 文件，但是在extract()中输入Gemm_259出现find_blob_index_by_name Gemm_259 failed的错误；（我是在windows中转换的）
r1zhe5dt3#
Gemm_259 是 layer name，不是 blob name，Gemm_259 的输出 blob name 是 784
推荐用netron打开，点击Gemm_259这个op，右边也会显示 blob name
yqkkidmi4#
使用的是 param 和 bin 文件，extractor.extract("784", output); 依旧出现find_blob_index_by_name 784 failed的错误
gcmastyq5#
mobilenet_v3.zip 附上文件
vfwfrxfs6#
使用的是 param 和 bin 文件，extractor.extract("784", output); 依旧出现find_blob_index_by_name 784 failed的错误
确认 load_param load_model 文件是否正确
fd3cxomn7#
ncnn::Net mobileNet_v3;
mobileNet_v3.load_param("MobileNetV3_Larger.param");
mobileNet_v3.load_model("MobileNetV3_Large.bin");
ncnn::Extractor extractor = mobileNet_v3.create_extractor();
extractor.input(0, in);
ncnn::Mat output;
extractor.extract("784", output);
加载方式确认无误，前面上传附件，您可以验证分析一下
oiopk7p58#
我也和你一样，遇到了同一个问题了，请问您解决了没？？？