ncnn_Android_face
face detect and segmentation by ncnn
Reference:
https://github.com/nihui/ncnn-android-scrfd
https://github.com/Tencent/ncnn
Android face detect and segmentation by ncnn
Similar Resources
Android MoveNet pose estimation by ncnn
ncnn_Android_MoveNet Android MoveNet single human pose estimation by ncnn this project is a ncnn Android demo for MoveNet, it depends on ncnn library
Dec 31, 2022
PiDiNet running in Android by ncnn
PiDiNet-NCNN 使用NCNN在安卓上实现PiDiNet这个边缘检测网络。 什么是PiDiNet？指南针：https://github.com/zhuoinoulu/pidinet 文件构成 ncnn-android-nanodet是基于nihui的nanodet项目魔改的，被我改成了运行P
Dec 13, 2022
monodepth running in Android by ncnn
monodepth-NCNN 将wavelet-monodepth的模型搬运到NCNN上，工程里面给了安卓的工程以及以及生成好的app安装包 wavelet-monodepth wavelet-monodepth：RGB图像的深度估计，wavelet顾名思义，就使用了小波变换的，官方的工程在这：ht
Aug 13, 2022
YOLOP running in Android by ncnn
YOLOP-NCNN 将YOLOP的模型搬运到NCNN上，工程里面给了windows下的VS测试以及安卓实现 YOLOP YOLOP：车辆检测+路面分割+车道线分割 三合一的网络，基于YOLO系列设计的，官方的工程在这：https://github.com/hustvl/YOLOP 工程细节 VS2
Dec 28, 2022
Android demo of LightTrack infer by ncnn
ncnn_Android_LightTrack this project is a ncnn Android demo for LightTrack, it depends on ncnn library and opencv. https://github.com/Tencent/ncnn htt
Dec 14, 2022
Android CrowdCounting demo infer by ncnn
ncnn_Android_CrowdCounting This is a sample CrowdCounting Android demo infer by ncnn, it depends on ncnn library and opencv https://github.com/Tencent
Jul 2, 2022
ncnn Android demo of PP-TinyPose
ncnn_Android_PP-TinyPose ncnn Android demo of PP-TinyPose this project is a ncnn Android demo for PP-TinyPose, it depends on ncnn library and opencv.
Nov 25, 2022
M-LSD Android demo infer by ncnn
ncnn_Android_mlsd The Android demo of M-LSD: Towards Light-weight and Real-time Line Segment Detection This is a sample ncnn android project, it depen
Jun 22, 2022
Depoly yolov5.ncnn in android.
Deploy yolov5.ncnn(v6.0) in android 测试效果 如何构建? 1. 下载 Android studio Android studio 下载地址: https://developer.android.com/studio 2. git clone 项目构建 Androi
Dec 25, 2022
Comments
-
转换后的模型大小bin和param参数内容不一致
我从 https://github.com/deepcam-cn/yolov5-face 下载的yolov5n-0.5.pt模型，转换成ncnn后，bin只有1.68m。而且param也不一样： 这个是我转换后的param
7767517 244 271 Input data 0 1 data Convolution Conv_0 1 1 data 389 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 Swish Mul_2 1 1 389 391 Split splitncnn_0 1 2 391 391_splitncnn_0 391_splitncnn_1 Convolution Conv_3 1 1 391_splitncnn_1 392 0=8 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=128 Swish Mul_5 1 1 392 394 Convolution Conv_6 1 1 394 395 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=1152 Swish Mul_8 1 1 395 397 Pooling MaxPool_9 1 1 391_splitncnn_0 398 0=0 1=2 11=2 2=2 12=2 3=0 13=0 14=0 15=0 5=0 Concat Concat_10 2 1 397 398 399 0=0 Convolution Conv_11 1 1 399 400 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=512 Swish Mul_13 1 1 400 402 Split splitncnn_1 1 2 402 402_splitncnn_0 402_splitncnn_1 ConvolutionDepthWise Conv_14 1 1 402_splitncnn_1 952 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=144 7=16 Convolution Conv_15 1 1 952 955 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=512 Swish Mul_17 1 1 955 408 Convolution Conv_18 1 1 402_splitncnn_0 958 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=512 Swish Mul_20 1 1 958 412 ConvolutionDepthWise Conv_21 1 1 412 961 0=32 1=3 11=3 2=1 12=1 3=2 13=2 4=1 14=1 15=1 16=1 5=1 6=288 7=32 Convolution Conv_22 1 1 961 964 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1024 Swish Mul_24 1 1 964 418 Concat Concat_25 2 1 408 418 419 0=0 ShuffleChannel Reshape_30 1 1 419 424 0=2 1=0 Split splitncnn_2 1 2 424 424_splitncnn_0 424_splitncnn_1 Crop Slice_41 1 1 424_splitncnn_1 435 -23309=1,0 -23310=1,32 -23311=1,0 Crop Slice_44 1 1 424_splitncnn_0 438 -23309=1,32 -23310=1,64 -23311=1,0 Convolution Conv_45 1 1 438 967 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1024 Swish Mul_47 1 1 967 442 ConvolutionDepthWise Conv_48 1 1 442 970 0=32 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=288 7=32 Convolution Conv_49 1 1 970 973 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1024 Swish Mul_51 1 1 973 448 Concat Concat_52 2 1 435 448 449 0=0 ShuffleChannel Reshape_57 1 1 449 454 0=2 1=0 Split splitncnn_3 1 2 454 454_splitncnn_0 454_splitncnn_1 Crop Slice_68 1 1 454_splitncnn_1 465 -23309=1,0 -23310=1,32 -23311=1,0 Crop Slice_71 1 1 454_splitncnn_0 468 -23309=1,32 -23310=1,64 -23311=1,0 Convolution Conv_72 1 1 468 976 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1024 Swish Mul_74 1 1 976 472 ConvolutionDepthWise Conv_75 1 1 472 979 0=32 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=288 7=32 Convolution Conv_76 1 1 979 982 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1024 Swish Mul_78 1 1 982 478 Concat Concat_79 2 1 465 478 479 0=0 ShuffleChannel Reshape_84 1 1 479 484 0=2 1=0 Split splitncnn_4 1 2 484 484_splitncnn_0 484_splitncnn_1 Crop Slice_95 1 1 484_splitncnn_1 495 -23309=1,0 -23310=1,32 -23311=1,0 Crop Slice_98 1 1 484_splitncnn_0 498 -23309=1,32 -23310=1,64 -23311=1,0 Convolution Conv_99 1 1 498 985 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1024 Swish Mul_101 1 1 985 502 ConvolutionDepthWise Conv_102 1 1 502 988 0=32 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=288 7=32 Convolution Conv_103 1 1 988 991 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1024 Swish Mul_105 1 1 991 508 Concat Concat_106 2 1 495 508 509 0=0 ShuffleChannel Reshape_111 1 1 509 514 0=2 1=0 Split splitncnn_5 1 3 514 514_splitncnn_0 514_splitncnn_1 514_splitncnn_2 ConvolutionDepthWise Conv_112 1 1 514_splitncnn_2 994 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 Convolution Conv_113 1 1 994 997 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=4096 Swish Mul_115 1 1 997 520 Convolution Conv_116 1 1 514_splitncnn_1 1000 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=4096 Swish Mul_118 1 1 1000 524 ConvolutionDepthWise Conv_119 1 1 524 1003 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 Convolution Conv_120 1 1 1003 1006 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=4096 Swish Mul_122 1 1 1006 530 Concat Concat_123 2 1 520 530 531 0=0 ShuffleChannel Reshape_128 1 1 531 536 0=2 1=0 Split splitncnn_6 1 2 536 536_splitncnn_0 536_splitncnn_1 Crop Slice_139 1 1 536_splitncnn_1 547 -23309=1,0 -23310=1,64 -23311=1,0 Crop Slice_142 1 1 536_splitncnn_0 550 -23309=1,64 -23310=1,128 -23311=1,0 Convolution Conv_143 1 1 550 1009 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=4096 Swish Mul_145 1 1 1009 554 ConvolutionDepthWise Conv_146 1 1 554 1012 0=64 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=576 7=64 Convolution Conv_147 1 1 1012 1015 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=4096 Swish Mul_149 1 1 1015 560 Concat Concat_150 2 1 547 560 561 0=0 ShuffleChannel Reshape_155 1 1 561 566 0=2 1=0 Split splitncnn_7 1 2 566 566_splitncnn_0 566_splitncnn_1 Crop Slice_166 1 1 566_splitncnn_1 577 -23309=1,0 -23310=1,64 -23311=1,0 Crop Slice_169 1 1 566_splitncnn_0 580 -23309=1,64 -23310=1,128 -23311=1,0 Convolution Conv_170 1 1 580 1018 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=4096 Swish Mul_172 1 1 1018 584 ConvolutionDepthWise Conv_173 1 1 584 1021 0=64 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=576 7=64 Convolution Conv_174 1 1 1021 1024 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=4096 Swish Mul_176 1 1 1024 590 Concat Concat_177 2 1 577 590 591 0=0 ShuffleChannel Reshape_182 1 1 591 596 0=2 1=0 Split splitncnn_8 1 2 596 596_splitncnn_0 596_splitncnn_1 Crop Slice_193 1 1 596_splitncnn_1 607 -23309=1,0 -23310=1,64 -23311=1,0 Crop Slice_196 1 1 596_splitncnn_0 610 -23309=1,64 -23310=1,128 -23311=1,0 Convolution Conv_197 1 1 610 1027 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=4096 Swish Mul_199 1 1 1027 614 ConvolutionDepthWise Conv_200 1 1 614 1030 0=64 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=576 7=64 Convolution Conv_201 1 1 1030 1033 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=4096 Swish Mul_203 1 1 1033 620 Concat Concat_204 2 1 607 620 621 0=0 ShuffleChannel Reshape_209 1 1 621 626 0=2 1=0 Split splitncnn_9 1 2 626 626_splitncnn_0 626_splitncnn_1 Crop Slice_220 1 1 626_splitncnn_1 637 -23309=1,0 -23310=1,64 -23311=1,0 Crop Slice_223 1 1 626_splitncnn_0 640 -23309=1,64 -23310=1,128 -23311=1,0 Convolution Conv_224 1 1 640 1036 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=4096 Swish Mul_226 1 1 1036 644 ConvolutionDepthWise Conv_227 1 1 644 1039 0=64 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=576 7=64 Convolution Conv_228 1 1 1039 1042 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=4096 Swish Mul_230 1 1 1042 650 Concat Concat_231 2 1 637 650 651 0=0 ShuffleChannel Reshape_236 1 1 651 656 0=2 1=0 Split splitncnn_10 1 2 656 656_splitncnn_0 656_splitncnn_1 Crop Slice_247 1 1 656_splitncnn_1 667 -23309=1,0 -23310=1,64 -23311=1,0 Crop Slice_250 1 1 656_splitncnn_0 670 -23309=1,64 -23310=1,128 -23311=1,0 Convolution Conv_251 1 1 670 1045 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=4096 Swish Mul_253 1 1 1045 674 ConvolutionDepthWise Conv_254 1 1 674 1048 0=64 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=576 7=64 Convolution Conv_255 1 1 1048 1051 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=4096 Swish Mul_257 1 1 1051 680 Concat Concat_258 2 1 667 680 681 0=0 ShuffleChannel Reshape_263 1 1 681 686 0=2 1=0 Split splitncnn_11 1 2 686 686_splitncnn_0 686_splitncnn_1 Crop Slice_274 1 1 686_splitncnn_1 697 -23309=1,0 -23310=1,64 -23311=1,0 Crop Slice_277 1 1 686_splitncnn_0 700 -23309=1,64 -23310=1,128 -23311=1,0 Convolution Conv_278 1 1 700 1054 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=4096 Swish Mul_280 1 1 1054 704 ConvolutionDepthWise Conv_281 1 1 704 1057 0=64 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=576 7=64 Convolution Conv_282 1 1 1057 1060 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=4096 Swish Mul_284 1 1 1060 710 Concat Concat_285 2 1 697 710 711 0=0 ShuffleChannel Reshape_290 1 1 711 716 0=2 1=0 Split splitncnn_12 1 2 716 716_splitncnn_0 716_splitncnn_1 Crop Slice_301 1 1 716_splitncnn_1 727 -23309=1,0 -23310=1,64 -23311=1,0 Crop Slice_304 1 1 716_splitncnn_0 730 -23309=1,64 -23310=1,128 -23311=1,0 Convolution Conv_305 1 1 730 1063 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=4096 Swish Mul_307 1 1 1063 734 ConvolutionDepthWise Conv_308 1 1 734 1066 0=64 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=576 7=64 Convolution Conv_309 1 1 1066 1069 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=4096 Swish Mul_311 1 1 1069 740 Concat Concat_312 2 1 727 740 741 0=0 ShuffleChannel Reshape_317 1 1 741 746 0=2 1=0 Split splitncnn_13 1 3 746 746_splitncnn_0 746_splitncnn_1 746_splitncnn_2 ConvolutionDepthWise Conv_318 1 1 746_splitncnn_2 1072 0=128 1=3 11=3 2=1 12=1 3=2 13=2 4=1 14=1 15=1 16=1 5=1 6=1152 7=128 Convolution Conv_319 1 1 1072 1075 0=128 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=16384 Swish Mul_321 1 1 1075 752 Convolution Conv_322 1 1 746_splitncnn_1 1078 0=128 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=16384 Swish Mul_324 1 1 1078 756 ConvolutionDepthWise Conv_325 1 1 756 1081 0=128 1=3 11=3 2=1 12=1 3=2 13=2 4=1 14=1 15=1 16=1 5=1 6=1152 7=128 Convolution Conv_326 1 1 1081 1084 0=128 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=16384 Swish Mul_328 1 1 1084 762 Concat Concat_329 2 1 752 762 763 0=0 ShuffleChannel Reshape_334 1 1 763 768 0=2 1=0 Split splitncnn_14 1 2 768 768_splitncnn_0 768_splitncnn_1 Crop Slice_345 1 1 768_splitncnn_1 779 -23309=1,0 -23310=1,128 -23311=1,0 Crop Slice_348 1 1 768_splitncnn_0 782 -23309=1,128 -23310=1,256 -23311=1,0 Convolution Conv_349 1 1 782 1087 0=128 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=16384 Swish Mul_351 1 1 1087 786 ConvolutionDepthWise Conv_352 1 1 786 1090 0=128 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=1152 7=128 Convolution Conv_353 1 1 1090 1093 0=128 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=16384 Swish Mul_355 1 1 1093 792 Concat Concat_356 2 1 779 792 793 0=0 ShuffleChannel Reshape_361 1 1 793 798 0=2 1=0 Split splitncnn_15 1 2 798 798_splitncnn_0 798_splitncnn_1 Crop Slice_372 1 1 798_splitncnn_1 809 -23309=1,0 -23310=1,128 -23311=1,0 Crop Slice_375 1 1 798_splitncnn_0 812 -23309=1,128 -23310=1,256 -23311=1,0 Convolution Conv_376 1 1 812 1096 0=128 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=16384 Swish Mul_378 1 1 1096 816 ConvolutionDepthWise Conv_379 1 1 816 1099 0=128 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=1152 7=128 Convolution Conv_380 1 1 1099 1102 0=128 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=16384 Swish Mul_382 1 1 1102 822 Concat Concat_383 2 1 809 822 823 0=0 ShuffleChannel Reshape_388 1 1 823 828 0=2 1=0 Split splitncnn_16 1 2 828 828_splitncnn_0 828_splitncnn_1 Crop Slice_399 1 1 828_splitncnn_1 839 -23309=1,0 -23310=1,128 -23311=1,0 Crop Slice_402 1 1 828_splitncnn_0 842 -23309=1,128 -23310=1,256 -23311=1,0 Convolution Conv_403 1 1 842 1105 0=128 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=16384 Swish Mul_405 1 1 1105 846 ConvolutionDepthWise Conv_406 1 1 846 1108 0=128 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=1152 7=128 Convolution Conv_407 1 1 1108 1111 0=128 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=16384 Swish Mul_409 1 1 1111 852 Concat Concat_410 2 1 839 852 853 0=0 ShuffleChannel Reshape_415 1 1 853 858 0=2 1=0 Convolution Conv_416 1 1 858 859 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=16384 Swish Mul_418 1 1 859 861 Split splitncnn_17 1 2 861 861_splitncnn_0 861_splitncnn_1 Interp Resize_420 1 1 861_splitncnn_1 866 0=1 1=2.000000e+00 2=2.000000e+00 3=0 4=0 6=0 Concat Concat_421 2 1 866 746_splitncnn_0 867 0=0 Split splitncnn_18 1 2 867 867_splitncnn_0 867_splitncnn_1 Convolution Conv_422 1 1 867_splitncnn_1 868 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=6144 Swish Mul_424 1 1 868 870 Convolution Conv_425 1 1 870 871 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1024 Swish Mul_427 1 1 871 873 Convolution Conv_428 1 1 873 874 0=32 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=9216 Swish Mul_430 1 1 874 876 Convolution Conv_431 1 1 867_splitncnn_0 877 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=6144 Swish Mul_433 1 1 877 879 Concat Concat_434 2 1 876 879 880 0=0 Convolution Conv_435 1 1 880 881 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=4096 Swish Mul_437 1 1 881 883 Convolution Conv_438 1 1 883 884 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=4096 Swish Mul_440 1 1 884 886 Split splitncnn_19 1 2 886 886_splitncnn_0 886_splitncnn_1 Interp Resize_442 1 1 886_splitncnn_1 891 0=1 1=2.000000e+00 2=2.000000e+00 3=0 4=0 6=0 Concat Concat_443 2 1 891 514_splitncnn_0 892 0=0 Split splitncnn_20 1 2 892 892_splitncnn_0 892_splitncnn_1 Convolution Conv_444 1 1 892_splitncnn_1 893 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=4096 Swish Mul_446 1 1 893 895 Convolution Conv_447 1 1 895 896 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1024 Swish Mul_449 1 1 896 898 Convolution Conv_450 1 1 898 899 0=32 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=9216 Swish Mul_452 1 1 899 901 Convolution Conv_453 1 1 892_splitncnn_0 902 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=4096 Swish Mul_455 1 1 902 904 Concat Concat_456 2 1 901 904 905 0=0 Convolution Conv_457 1 1 905 906 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=4096 Swish Mul_459 1 1 906 908 Split splitncnn_21 1 2 908 908_splitncnn_0 908_splitncnn_1 Convolution Conv_460 1 1 908_splitncnn_1 909 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=36864 Swish Mul_462 1 1 909 911 Concat Concat_463 2 1 911 886_splitncnn_0 912 0=0 Split splitncnn_22 1 2 912 912_splitncnn_0 912_splitncnn_1 Convolution Conv_464 1 1 912_splitncnn_1 913 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=4096 Swish Mul_466 1 1 913 915 Convolution Conv_467 1 1 915 916 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1024 Swish Mul_469 1 1 916 918 Convolution Conv_470 1 1 918 919 0=32 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=9216 Swish Mul_472 1 1 919 921 Convolution Conv_473 1 1 912_splitncnn_0 922 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=4096 Swish Mul_475 1 1 922 924 Concat Concat_476 2 1 921 924 925 0=0 Convolution Conv_477 1 1 925 926 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=4096 Swish Mul_479 1 1 926 928 Split splitncnn_23 1 2 928 928_splitncnn_0 928_splitncnn_1 Convolution Conv_480 1 1 928_splitncnn_1 929 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=36864 Swish Mul_482 1 1 929 931 Concat Concat_483 2 1 931 861_splitncnn_0 932 0=0 Split splitncnn_24 1 2 932 932_splitncnn_0 932_splitncnn_1 Convolution Conv_484 1 1 932_splitncnn_1 933 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=4096 Swish Mul_486 1 1 933 935 Convolution Conv_487 1 1 935 936 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=1024 Swish Mul_489 1 1 936 938 Convolution Conv_490 1 1 938 939 0=32 1=3 11=3 2=1 12=1 3=1 13=1 4=1 14=1 15=1 16=1 5=1 6=9216 Swish Mul_492 1 1 939 941 Convolution Conv_493 1 1 932_splitncnn_0 942 0=32 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=4096 Swish Mul_495 1 1 942 944 Concat Concat_496 2 1 941 944 945 0=0 Convolution Conv_497 1 1 945 946 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=4096 Swish Mul_499 1 1 946 948 Convolution Conv_500 1 1 908_splitncnn_0 stride_8 0=48 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=3072 Convolution Conv_501 1 1 928_splitncnn_0 stride_16 0=48 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=3072 Convolution Conv_502 1 1 948 stride_32 0=48 1=1 11=1 2=1 12=1 3=1 13=1 4=0 14=0 15=0 16=0 5=1 6=3072 === 请问可以分享一下您的原pt模型和转换脚本吗？我对比分析一下差异，谢谢 -
Mean values are skipped in yolov7?
Hello, here passing 0 for mean values lead to skipping of mean subtraction step. However before that in code pass mean values equal to 127.5f.
So which is correct?
-
interesting work
Hello, Great work with this! We're a team of Computer vision developers and work with TNN, Ncnn + MNN - and I'd like to have your email for some further discussion if it's fine with you? my email - kris AT tap.pm
-
Unable to run the Android App
I have downloaded the repo and set up the opencv and ncnn.
opencv: SET(OpenCV_VERSION 4.5.1)
nccn version: ncnn-20210322-android-vulkan
NDK Version: 22.1.7171670
The build compilation is successful but when I try to deploy this code onto my Android device this is the error I face:
Build command failed. Error while executing process /Users/harish/Library/Android/sdk/cmake/3.10.2.4988404/bin/ninja with arguments {-C /Users/harish/Coding/ncnn-android-scrfd/app/.cxx/cmake/debug/x86 scrfdncnn} ninja: Entering directory/Users/harish/Coding/ncnn-android-scrfd/app/.cxx/cmake/debug/x86' [1/1] Linking CXX shared library /Users/harish/Coding/ncnn-android-scrfd/app/build/intermediates/cmake/debug/obj/x86/libscrfdncnn.so FAILED: /Users/harish/Coding/ncnn-android-scrfd/app/build/intermediates/cmake/debug/obj/x86/libscrfdncnn.so : && /Users/harish/Library/Android/sdk/ndk/22.1.7171670/toolchains/llvm/prebuilt/darwin-x86_64/bin/clang++ --target=i686-none-linux-android24 --gcc-toolchain=/Users/harish/Library/Android/sdk/ndk/22.1.7171670/toolchains/llvm/prebuilt/darwin-x86_64 --sysroot=/Users/harish/Library/Android/sdk/ndk/22.1.7171670/toolchains/llvm/prebuilt/darwin-x86_64/sysroot -fPIC -g -DANDROID -fdata-sections -ffunction-sections -funwind-tables -fstack-protector-strong -no-canonical-prefixes -D_FORTIFY_SOURCE=2 -Wformat -Werror=format-security -O0 -fno-limit-debug-info -Wl,--exclude-libs,libgcc.a -Wl,--exclude-libs,libgcc_real.a -Wl,--exclude-libs,libatomic.a -static-libstdc++ -Wl,--build-id=sha1 -Wl,--no-rosegment -Wl,--fatal-warnings -Wl,--no-undefined -Qunused-arguments -shared -Wl,-soname,libscrfdncnn.so -o /Users/harish/Coding/ncnn-android-scrfd/app/build/intermediates/cmake/debug/obj/x86/libscrfdncnn.so CMakeFiles/scrfdncnn.dir/scrfdncnn.cpp.o CMakeFiles/scrfdncnn.dir/scrfd.cpp.o CMakeFiles/scrfdncnn.dir/ndkcamera.cpp.o /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/ncnn-20210322-android-vulkan/x86/lib/libncnn.a /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/opencv-mobile-4.5.1-android/sdk/native/staticlibs/x86/libopencv_core.a /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/opencv-mobile-4.5.1-android/sdk/native/staticlibs/x86/libopencv_imgproc.a -lcamera2ndk -lmediandk -fopenmp -static-openmp /Users/harish/Library/Android/sdk/ndk/22.1.7171670/toolchains/llvm/prebuilt/darwin-x86_64/sysroot/usr/lib/i686-linux-android/24/libvulkan.so /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/ncnn-20210322-android-vulkan/x86/lib/libglslang.a /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/ncnn-20210322-android-vulkan/x86/lib/libSPIRV.a /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/ncnn-20210322-android-vulkan/x86/lib/libMachineIndependent.a /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/ncnn-20210322-android-vulkan/x86/lib/libOGLCompiler.a /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/ncnn-20210322-android-vulkan/x86/lib/libOSDependent.a -pthread /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/ncnn-20210322-android-vulkan/x86/lib/libGenericCodeGen.a -landroid -ljnigraphics /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/opencv-mobile-4.5.1-android/sdk/native/staticlibs/x86/libopencv_core.a -ldl -lm -llog -latomic -lm && : ld: error: undefined symbol: gzopenreferenced by persistence.cpp persistence.cpp.o:(cv::FileStorage::Impl::open(char const*, int, char const*)) in archive /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/opencv-mobile-4.5.1-android/sdk/native/staticlibs/x86/libopencv_core.a
ld: error: undefined symbol: gzgets
referenced by persistence.cpp persistence.cpp.o:(cv::FileStorage::Impl::getsFromFile(char*, int)) in archive /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/opencv-mobile-4.5.1-android/sdk/native/staticlibs/x86/libopencv_core.a
ld: error: undefined symbol: gzputs
referenced by persistence.cpp persistence.cpp.o:(cv::FileStorage::Impl::puts(char const*)) in archive /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/opencv-mobile-4.5.1-android/sdk/native/staticlibs/x86/libopencv_core.a
ld: error: undefined symbol: gzeof
referenced by persistence.cpp persistence.cpp.o:(cv::FileStorage::Impl::eof()) in archive /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/opencv-mobile-4.5.1-android/sdk/native/staticlibs/x86/libopencv_core.a
ld: error: undefined symbol: gzclose
referenced by persistence.cpp persistence.cpp.o:(cv::FileStorage::Impl::closeFile()) in archive /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/opencv-mobile-4.5.1-android/sdk/native/staticlibs/x86/libopencv_core.a
ld: error: undefined symbol: gzrewind
referenced by persistence.cpp persistence.cpp.o:(cv::FileStorage::Impl::rewind()) in archive /Users/harish/Coding/ncnn-android-scrfd/app/src/main/jni/opencv-mobile-4.5.1-android/sdk/native/staticlibs/x86/libopencv_core.a clang++: error: linker command failed with exit code 1 (use -v to see invocation) ninja: build stopped: subcommand failed.
`
Related tags
RealSR-NCNN-Android is a simple Android application that based on Realsr-NCNN & Real-ESRGAN.
RealSR-NCNN-Android Real-ESRGAN is a Practical Algorithms for General Image Restoration. RealSR-NCNN-Android is a simple Android application that base
Jan 3, 2023
Android hand detect and pose estimation by ncnn
ncnn_nanodet_hand 1.hand detect:用nanode-m训练了个hand detect模型, 2.hand pose:用CMU的数据集训练了个ghostnet作为backbone模仿pfld的handpose模型 3.推理:handpose.cpp单独检测pose，nano
Jan 3, 2023
Android hair/human segmentation demo by ncnn
ncnn_Android_human Android hair/human segmentation demo by ncnn PS:performance maybe poor.it's just a demo:) Reference: 1.https://github.com/Tencent/n
May 23, 2022
Android human segmentation by ncnn
ncnn_Android_human_segmentation this project is a ncnn Android demo for RobustVideoMatting, it depends on ncnn library and opencv. https://github.com/
Nov 30, 2022
Android yolox hand detect by ncnn
The yolox hand detection This is a sample ncnn android project, it depends on ncnn library and opencv https://github.com/Tencent/ncnn https://github.c
Sep 7, 2022
Swapping face using Face Mesh with TensorFlow Lite
demo.mp4 Aiine Transform (アイン変換) Swapping face using FaceMesh. (could be used to unveil masked faces) Tested Environment Computer Windows 10 (x64) + V
Apr 26, 2022
This is a sample ncnn android project, it depends on ncnn library and opencv
This is a sample ncnn android project, it depends on ncnn library and opencv
Jan 6, 2023
The SCRFD face detection, depends on ncnn library and opencv
The SCRFD face detection, depends on ncnn library and opencv
Jan 5, 2023
Deploy SCRFD, an efficient high accuracy face detection approach, in your web browser with ncnn and webassembly
ncnn-webassembly-scrfd open https://nihui.github.io/ncnn-webassembly-scrfd and enjoy build and deploy Install emscripten
Nov 16, 2022
Portrait segmentation in your web browser with ncnn and webassembly
ncnn-webassembly-portrait-segmentation open https://nihui.github.io/ncnn-webassembly-portrait-segmentation and enjoy build and deploy Install emscript
Dec 5, 2022