[归档]YOLOv8l在rk3588上量化后的细节

最新推荐文章于 2024-07-04 05:24:41 发布

子正

最新推荐文章于 2024-07-04 05:24:41 发布

阅读量940

点赞数 14

文章标签： YOLO python 人工智能

本文链接：https://blog.csdn.net/twicave/article/details/139809998

版权

归档备查。这是我第一个成功进行量化的模型：

D RKNN: [17:53:26.729] Network Layer Information Table
D RKNN: [17:53:26.729] ------------------------------------------------------------------------------------------------------------------------------------------------------------------------
D RKNN: [17:53:26.729] ID OpType DataType Target InputShape OutputShape Cycles(DDR/NPU/Total) RW(KB) FullName
D RKNN: [17:53:26.729] ------------------------------------------------------------------------------------------------------------------------------------------------------------------------
D RKNN: [17:53:26.729] 0 InputOperator INT8 CPU \ (1,3,640,640) 0/0/0 0 InputOperator:images
D RKNN: [17:53:26.729] 1 ConvExSwish INT8 NPU (1,3,640,640),(64,3,3,3),(64) (1,64,320,320) 329422/1843200/1843200 1209 Conv:/model.0/conv/Conv
D RKNN: [17:53:26.729] 2 ConvExSwish INT8 NPU (1,64,320,320),(128,64,3,3),(128) (1,128,160,160) 418752/1843200/1843200 6473 Conv:/model.1/conv/Conv
D RKNN: [17:53:26.729] 3 ConvExSwish INT8 NPU (1,128,160,160),(128,128,1,1),(128) (1,128,160,160) 277797/409600/409600 3217 Conv:/model.2/cv1/conv/Conv
D RKNN: [17:53:26.729] 4 Split INT8 NPU (1,128,160,160),(2) (1,64,160,160),... 0/0/0 3200 Split:/model.2/Split
D RKNN: [17:53:26.729] 5 ConvExSwish INT8 NPU (1,64,160,160),(64,64,3,3),(64) (1,64,160,160) 140111/921600/921600 1636 Conv:/model.2/m.0/cv1/conv/Conv
D RKNN: [17:53:26.729] 6 ConvExSwish INT8 NPU (1,64,160,160),(64,64,3,3),(64) (1,64,160,160) 140111/921600/921600 1636 Conv:/model.2/m.0/cv2/conv/Conv
D RKNN: [17:53:26.729] 7 Add INT8 NPU (1,64,160,160),(1,64,160,160) (1,64,160,160) 0/0/0 3200 Add:/model.2/m.0/Add
D RKNN: [17:53:26.729] 8 ConvExSwish INT8 NPU (1,64,160,160),(64,64,3,3),(64) (1,64,160,160) 140111/921600/921600 1636 Conv:/model.2/m.1/cv1/conv/Conv
D RKNN: [17:53:26.729] 9 ConvExSwish INT8 NPU (1,64,160,160),(64,64,3,3),(64) (1,64,160,160) 140111/921600/921600 1636 Conv:/model.2/m.1/cv2/conv/Conv
D RKNN: [17:53:26.729] 10 Add INT8 NPU (1,64,160,160),(1,64,160,160) (1,64,160,160) 0/0/0 3200 Add:/model.2/m.1/Add
D RKNN: [17:53:26.729] 11 ConvExSwish INT8 NPU (1,64,160,160),(64,64,3,3),(64) (1,64,160,160) 140111/921600/921600 1636 Conv:/model.2/m.2/cv1/conv/Conv
D RKNN: [17:53:26.729] 12 ConvExSwish INT8 NPU (1,64,160,160),(64,64,3,3),(64) (1,64,160,160) 140111/921600/921600 1636 Conv:/model.2/m.2/cv2/conv/Conv
D RKNN: [17:53:26.729] 13 Add INT8 NPU (1,64,160,160),(1,64,160,160) (1,64,160,160) 0/0/0 3200 Add:/model.2/m.2/Add
D RKNN: [17:53:26.729] 14 Concat INT8 NPU (1,64,160,160),(1,64,160,160),... (1,320,160,160) 0/0/0 8000 Concat:/model.2/Concat
D RKNN: [17:53:26.729] 15 ConvExSwish INT8 NPU (1,320,160,160),(128,320,1,1),(128) (1,128,160,160) 486632/1024000/1024000 8041 Conv:/model.2/cv2/conv/Conv
D RKNN: [17:53:26.729] 16 ConvExSwish INT8 NPU (1,128,160,160),(256,128,3,3),(256) (1,256,80,80) 220351/1843200/1843200 3490 Conv:/model.3/conv/Conv
D RKNN: [17:53:26.729] 17 ConvExSwish INT8 NPU (1,256,80,80),(256,256,1,1),(256) (1,256,80,80) 141388/409600/409600 1666 Conv:/model.4/cv1/conv/Conv
D RKNN: [17:53:26.729] 18 Split INT8 NPU (1,256,80,80),(2) (1,128,80,80),... 0/0/0 1600 Split:/model.4/Split
D RKNN: [17:53:26.729] 19 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.4/m.0/cv1/conv/Conv
D RKNN: [17:53:26.729] 20 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.4/m.0/cv2/conv/Conv
D RKNN: [17:53:26.729] 21 Add INT8 NPU (1,128,80,80),(1,128,80,80) (1,128,80,80) 0/0/0 1600 Add:/model.4/m.0/Add
D RKNN: [17:53:26.729] 22 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.4/m.1/cv1/conv/Conv
D RKNN: [17:53:26.729] 23 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.4/m.1/cv2/conv/Conv
D RKNN: [17:53:26.729] 24 Add INT8 NPU (1,128,80,80),(1,128,80,80) (1,128,80,80) 0/0/0 1600 Add:/model.4/m.1/Add
D RKNN: [17:53:26.729] 25 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.4/m.2/cv1/conv/Conv
D RKNN: [17:53:26.729] 26 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.4/m.2/cv2/conv/Conv
D RKNN: [17:53:26.729] 27 Add INT8 NPU (1,128,80,80),(1,128,80,80) (1,128,80,80) 0/0/0 1600 Add:/model.4/m.2/Add
D RKNN: [17:53:26.729] 28 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.4/m.3/cv1/conv/Conv
D RKNN: [17:53:26.729] 29 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.4/m.3/cv2/conv/Conv
D RKNN: [17:53:26.729] 30 Add INT8 NPU (1,128,80,80),(1,128,80,80) (1,128,80,80) 0/0/0 1600 Add:/model.4/m.3/Add
D RKNN: [17:53:26.729] 31 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.4/m.4/cv1/conv/Conv
D RKNN: [17:53:26.729] 32 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.4/m.4/cv2/conv/Conv
D RKNN: [17:53:26.729] 33 Add INT8 NPU (1,128,80,80),(1,128,80,80) (1,128,80,80) 0/0/0 1600 Add:/model.4/m.4/Add
D RKNN: [17:53:26.729] 34 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.4/m.5/cv1/conv/Conv
D RKNN: [17:53:26.729] 35 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.4/m.5/cv2/conv/Conv
D RKNN: [17:53:26.729] 36 Add INT8 NPU (1,128,80,80),(1,128,80,80) (1,128,80,80) 0/0/0 1600 Add:/model.4/m.5/Add
D RKNN: [17:53:26.729] 37 Concat INT8 NPU (1,128,80,80),(1,128,80,80),... (1,1024,80,80) 0/0/0 6400 Concat:/model.4/Concat
D RKNN: [17:53:26.729] 38 ConvExSwish INT8 NPU (1,1024,80,80),(256,1024,1,1),(256) (1,256,80,80) 357496/1638400/1638400 6658 Conv:/model.4/cv2/conv/Conv
D RKNN: [17:53:26.729] 39 ConvExSwish INT8 NPU (1,256,80,80),(512,256,3,3),(512) (1,512,40,40) 153942/1843200/1843200 2756 Conv:/model.5/conv/Conv
D RKNN: [17:53:26.729] 40 ConvExSwish INT8 NPU (1,512,40,40),(512,512,1,1),(512) (1,512,40,40) 80521/409600/409600 1060 Conv:/model.6/cv1/conv/Conv
D RKNN: [17:53:26.729] 41 Split INT8 NPU (1,512,40,40),(2) (1,256,40,40),... 0/0/0 800 Split:/model.6/Split
D RKNN: [17:53:26.729] 42 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.6/m.0/cv1/conv/Conv
D RKNN: [17:53:26.729] 43 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.6/m.0/cv2/conv/Conv
D RKNN: [17:53:26.729] 44 Add INT8 NPU (1,256,40,40),(1,256,40,40) (1,256,40,40) 0/0/0 800 Add:/model.6/m.0/Add
D RKNN: [17:53:26.729] 45 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.6/m.1/cv1/conv/Conv
D RKNN: [17:53:26.729] 46 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.6/m.1/cv2/conv/Conv
D RKNN: [17:53:26.729] 47 Add INT8 NPU (1,256,40,40),(1,256,40,40) (1,256,40,40) 0/0/0 800 Add:/model.6/m.1/Add
D RKNN: [17:53:26.729] 48 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.6/m.2/cv1/conv/Conv
D RKNN: [17:53:26.729] 49 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.6/m.2/cv2/conv/Conv
D RKNN: [17:53:26.729] 50 Add INT8 NPU (1,256,40,40),(1,256,40,40) (1,256,40,40) 0/0/0 800 Add:/model.6/m.2/Add
D RKNN: [17:53:26.729] 51 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.6/m.3/cv1/conv/Conv
D RKNN: [17:53:26.729] 52 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.6/m.3/cv2/conv/Conv
D RKNN: [17:53:26.729] 53 Add INT8 NPU (1,256,40,40),(1,256,40,40) (1,256,40,40) 0/0/0 800 Add:/model.6/m.3/Add
D RKNN: [17:53:26.729] 54 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.6/m.4/cv1/conv/Conv
D RKNN: [17:53:26.729] 55 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.6/m.4/cv2/conv/Conv
D RKNN: [17:53:26.729] 56 Add INT8 NPU (1,256,40,40),(1,256,40,40) (1,256,40,40) 0/0/0 800 Add:/model.6/m.4/Add
D RKNN: [17:53:26.729] 57 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.6/m.5/cv1/conv/Conv
D RKNN: [17:53:26.729] 58 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.6/m.5/cv2/conv/Conv
D RKNN: [17:53:26.729] 59 Add INT8 NPU (1,256,40,40),(1,256,40,40) (1,256,40,40) 0/0/0 800 Add:/model.6/m.5/Add
D RKNN: [17:53:26.729] 60 Concat INT8 NPU (1,256,40,40),(1,256,40,40),... (1,2048,40,40) 0/0/0 3200 Concat:/model.6/Concat
D RKNN: [17:53:26.729] 61 ConvExSwish INT8 NPU (1,2048,40,40),(512,2048,1,1),(512) (1,512,40,40) 217667/1638400/1638400 4228 Conv:/model.6/cv2/conv/Conv
D RKNN: [17:53:26.729] 62 ConvExSwish INT8 NPU (1,512,40,40),(512,512,3,3),(512) (1,512,20,20) 143206/921600/921600 3108 Conv:/model.7/conv/Conv
D RKNN: [17:53:26.729] 63 ConvExSwish INT8 NPU (1,512,20,20),(512,512,1,1),(512) (1,512,20,20) 28572/102400/102400 460 Conv:/model.8/cv1/conv/Conv
D RKNN: [17:53:26.729] 64 Split INT8 NPU (1,512,20,20),(2) (1,256,20,20),... 0/0/0 200 Split:/model.8/Split
D RKNN: [17:53:26.729] 65 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.8/m.0/cv1/conv/Conv
D RKNN: [17:53:26.729] 66 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.8/m.0/cv2/conv/Conv
D RKNN: [17:53:26.729] 67 Add INT8 NPU (1,256,20,20),(1,256,20,20) (1,256,20,20) 0/0/0 200 Add:/model.8/m.0/Add
D RKNN: [17:53:26.729] 68 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.8/m.1/cv1/conv/Conv
D RKNN: [17:53:26.729] 69 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.8/m.1/cv2/conv/Conv
D RKNN: [17:53:26.729] 70 Add INT8 NPU (1,256,20,20),(1,256,20,20) (1,256,20,20) 0/0/0 200 Add:/model.8/m.1/Add
D RKNN: [17:53:26.729] 71 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.8/m.2/cv1/conv/Conv
D RKNN: [17:53:26.729] 72 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.8/m.2/cv2/conv/Conv
D RKNN: [17:53:26.729] 73 Add INT8 NPU (1,256,20,20),(1,256,20,20) (1,256,20,20) 0/0/0 200 Add:/model.8/m.2/Add
D RKNN: [17:53:26.729] 74 Concat INT8 NPU (1,256,20,20),(1,256,20,20),... (1,1280,20,20) 0/0/0 500 Concat:/model.8/Concat
D RKNN: [17:53:26.729] 75 ConvExSwish INT8 NPU (1,1280,20,20),(512,1280,1,1),(512) (1,512,20,20) 58183/256000/256000 1144 Conv:/model.8/cv2/conv/Conv
D RKNN: [17:53:26.729] 76 ConvExSwish INT8 NPU (1,512,20,20),(256,512,1,1),(256) (1,256,20,20) 18616/51200/51200 330 Conv:/model.9/cv1/conv/Conv
D RKNN: [17:53:26.729] 77 MaxPool INT8 NPU (1,256,20,20) (1,256,20,20) 0/0/0 100 MaxPool:/model.9/m/MaxPool
D RKNN: [17:53:26.729] 78 MaxPool INT8 NPU (1,256,20,20) (1,256,20,20) 0/0/0 100 MaxPool:/model.9/m_1/MaxPool
D RKNN: [17:53:26.729] 79 MaxPool INT8 NPU (1,256,20,20) (1,256,20,20) 0/0/0 100 MaxPool:/model.9/m_2/MaxPool
D RKNN: [17:53:26.729] 80 Concat INT8 NPU (1,256,20,20),(1,256,20,20),... (1,1024,20,20) 0/0/0 400 Concat:/model.9/Concat
D RKNN: [17:53:26.729] 81 ConvExSwish INT8 NPU (1,1024,20,20),(512,1024,1,1),(512) (1,512,20,20) 48313/204800/204800 916 Conv:/model.9/cv2/conv/Conv
D RKNN: [17:53:26.729] 82 Resize INT8 NPU (1,512,20,20),(0),(4) (1,512,40,40) 0/0/0 200 Resize:/model.10/Resize
D RKNN: [17:53:26.729] 83 Concat INT8 NPU (1,512,40,40),(1,512,40,40) (1,1024,40,40) 0/0/0 1600 Concat:/model.11/Concat
D RKNN: [17:53:26.729] 84 ConvExSwish INT8 NPU (1,1024,40,40),(512,1024,1,1),(512) (1,512,40,40) 126236/819200/819200 2116 Conv:/model.12/cv1/conv/Conv
D RKNN: [17:53:26.729] 85 Split INT8 NPU (1,512,40,40),(2) (1,256,40,40),... 0/0/0 800 Split:/model.12/Split
D RKNN: [17:53:26.729] 86 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.12/m.0/cv1/conv/Conv
D RKNN: [17:53:26.729] 87 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.12/m.0/cv2/conv/Conv
D RKNN: [17:53:26.729] 88 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.12/m.1/cv1/conv/Conv
D RKNN: [17:53:26.729] 89 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.12/m.1/cv2/conv/Conv
D RKNN: [17:53:26.729] 90 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.12/m.2/cv1/conv/Conv
D RKNN: [17:53:26.729] 91 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.12/m.2/cv2/conv/Conv
D RKNN: [17:53:26.729] 92 Concat INT8 NPU (1,256,40,40),(1,256,40,40),... (1,1280,40,40) 0/0/0 2000 Concat:/model.12/Concat
D RKNN: [17:53:26.729] 93 ConvExSwish INT8 NPU (1,1280,40,40),(512,1280,1,1),(512) (1,512,40,40) 149094/1024000/1024000 2644 Conv:/model.12/cv2/conv/Conv
D RKNN: [17:53:26.729] 94 Resize INT8 NPU (1,512,40,40),(0),(4) (1,512,80,80) 0/0/0 800 Resize:/model.13/Resize
D RKNN: [17:53:26.729] 95 Concat INT8 NPU (1,512,80,80),(1,256,80,80) (1,768,80,80) 0/0/0 4800 Concat:/model.14/Concat
D RKNN: [17:53:26.729] 96 ConvExSwish INT8 NPU (1,768,80,80),(256,768,1,1),(256) (1,256,80,80) 285460/1228800/1228800 4994 Conv:/model.15/cv1/conv/Conv
D RKNN: [17:53:26.729] 97 Split INT8 NPU (1,256,80,80),(2) (1,128,80,80),... 0/0/0 1600 Split:/model.15/Split
D RKNN: [17:53:26.729] 98 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.15/m.0/cv1/conv/Conv
D RKNN: [17:53:26.729] 99 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.15/m.0/cv2/conv/Conv
D RKNN: [17:53:26.729] 100 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.15/m.1/cv1/conv/Conv
D RKNN: [17:53:26.729] 101 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.15/m.1/cv2/conv/Conv
D RKNN: [17:53:26.729] 102 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.15/m.2/cv1/conv/Conv
D RKNN: [17:53:26.729] 103 ConvExSwish INT8 NPU (1,128,80,80),(128,128,3,3),(128) (1,128,80,80) 75543/921600/921600 945 Conv:/model.15/m.2/cv2/conv/Conv
D RKNN: [17:53:26.729] 104 Concat INT8 NPU (1,128,80,80),(1,128,80,80),... (1,640,80,80) 0/0/0 4000 Concat:/model.15/Concat
D RKNN: [17:53:26.729] 105 ConvExSwish INT8 NPU (1,640,80,80),(256,640,1,1),(256) (1,256,80,80) 249442/1024000/1024000 4162 Conv:/model.15/cv2/conv/Conv
D RKNN: [17:53:26.729] 106 ConvExSwish INT8 NPU (1,256,80,80),(256,256,3,3),(256) (1,256,40,40) 111604/921600/921600 2178 Conv:/model.16/conv/Conv
D RKNN: [17:53:26.729] 107 Concat INT8 NPU (1,256,40,40),(1,512,40,40) (1,768,40,40) 0/0/0 1200 Concat:/model.17/Concat
D RKNN: [17:53:26.729] 108 ConvExSwish INT8 NPU (1,256,80,80),(64,256,3,3),(64) (1,64,80,80) 92838/921600/921600 1744 Conv:/model.22/cv2.0/cv2.0.0/conv/Conv
D RKNN: [17:53:26.729] 109 ConvExSwish INT8 NPU (1,256,80,80),(256,256,3,3),(256) (1,256,80,80) 163553/3686400/3686400 2178 Conv:/model.22/cv3.0/cv3.0.0/conv/Conv
D RKNN: [17:53:26.729] 110 ConvExSwish INT8 NPU (1,768,40,40),(512,768,1,1),(512) (1,512,40,40) 103379/614400/614400 1588 Conv:/model.18/cv1/conv/Conv
D RKNN: [17:53:26.729] 111 Split INT8 NPU (1,512,40,40),(2) (1,256,40,40),... 0/0/0 800 Split:/model.18/Split
D RKNN: [17:53:26.729] 112 ConvExSwish INT8 NPU (1,64,80,80),(64,64,3,3),(64) (1,64,80,80) 36213/230400/230400 436 Conv:/model.22/cv2.0/cv2.0.1/conv/Conv
D RKNN: [17:53:26.729] 113 Conv INT8 NPU (1,64,80,80),(64,64,1,1),(64) (1,64,80,80) 34828/51200/51200 404 Conv:/model.22/cv2.0/cv2.0.2/Conv
D RKNN: [17:53:26.729] 114 OutputOperator INT8 CPU (1,64,80,80) \ 0/0/0 400 OutputOperator:530
D RKNN: [17:53:26.729] 115 ConvExSwish INT8 NPU (1,256,80,80),(256,256,3,3),(256) (1,256,80,80) 163553/3686400/3686400 2178 Conv:/model.22/cv3.0/cv3.0.1/conv/Conv
D RKNN: [17:53:26.729] 116 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.18/m.0/cv1/conv/Conv
D RKNN: [17:53:26.729] 117 ConvSigmoid INT8 NPU (1,256,80,80),(80,256,1,1),(80) (1,80,80,80) 96138/153600/153600 1620 Conv:/model.22/cv3.0/cv3.0.2/Conv
D RKNN: [17:53:26.729] 118 OutputOperator INT8 CPU (1,80,80,80) \ 0/0/0 600 OutputOperator:onnx::ReduceSum_538
D RKNN: [17:53:26.729] 119 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.18/m.0/cv2/conv/Conv
D RKNN: [17:53:26.729] 120 ConvClip INT8 NPU (1,80,80,80),(1,80,1,1),(1) (1,1,80,80) 34642/25600/34642 600 Conv:/model.22/ReduceSum_2conv
D RKNN: [17:53:26.729] 121 OutputOperator INT8 CPU (1,1,80,80) \ 0/0/0 200 OutputOperator:543
D RKNN: [17:53:26.729] 122 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.18/m.1/cv1/conv/Conv
D RKNN: [17:53:26.729] 123 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.18/m.1/cv2/conv/Conv
D RKNN: [17:53:26.729] 124 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.18/m.2/cv1/conv/Conv
D RKNN: [17:53:26.729] 125 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.18/m.2/cv2/conv/Conv
D RKNN: [17:53:26.729] 126 Concat INT8 NPU (1,256,40,40),(1,256,40,40),... (1,1280,40,40) 0/0/0 2000 Concat:/model.18/Concat
D RKNN: [17:53:26.729] 127 ConvExSwish INT8 NPU (1,1280,40,40),(512,1280,1,1),(512) (1,512,40,40) 149094/1024000/1024000 2644 Conv:/model.18/cv2/conv/Conv
D RKNN: [17:53:26.729] 128 ConvExSwish INT8 NPU (1,512,40,40),(512,512,3,3),(512) (1,512,20,20) 143206/921600/921600 3108 Conv:/model.19/conv/Conv
D RKNN: [17:53:26.729] 129 Concat INT8 NPU (1,512,20,20),(1,512,20,20) (1,1024,20,20) 0/0/0 400 Concat:/model.20/Concat
D RKNN: [17:53:26.729] 130 ConvExSwish INT8 NPU (1,512,40,40),(64,512,3,3),(64) (1,64,40,40) 51452/460800/460800 1088 Conv:/model.22/cv2.1/cv2.1.0/conv/Conv
D RKNN: [17:53:26.729] 131 ConvExSwish INT8 NPU (1,512,40,40),(256,512,3,3),(256) (1,256,40,40) 101907/1843200/1843200 1954 Conv:/model.22/cv3.1/cv3.1.0/conv/Conv
D RKNN: [17:53:26.729] 132 ConvExSwish INT8 NPU (1,1024,20,20),(512,1024,1,1),(512) (1,512,20,20) 48313/204800/204800 916 Conv:/model.21/cv1/conv/Conv
D RKNN: [17:53:26.729] 133 Split INT8 NPU (1,512,20,20),(2) (1,256,20,20),... 0/0/0 200 Split:/model.21/Split
D RKNN: [17:53:26.729] 134 ConvExSwish INT8 NPU (1,64,40,40),(64,64,3,3),(64) (1,64,40,40) 10239/57600/57600 136 Conv:/model.22/cv2.1/cv2.1.1/conv/Conv
D RKNN: [17:53:26.729] 135 Conv INT8 NPU (1,64,40,40),(64,64,1,1),(64) (1,64,40,40) 8853/12800/12800 104 Conv:/model.22/cv2.1/cv2.1.2/Conv
D RKNN: [17:53:26.729] 136 OutputOperator INT8 CPU (1,64,40,40) \ 0/0/0 100 OutputOperator:550
D RKNN: [17:53:26.729] 137 ConvExSwish INT8 NPU (1,256,40,40),(256,256,3,3),(256) (1,256,40,40) 59655/921600/921600 978 Conv:/model.22/cv3.1/cv3.1.1/conv/Conv
D RKNN: [17:53:26.729] 138 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.21/m.0/cv1/conv/Conv
D RKNN: [17:53:26.729] 139 ConvSigmoid INT8 NPU (1,256,40,40),(80,256,1,1),(80) (1,80,40,40) 24709/38400/38400 420 Conv:/model.22/cv3.1/cv3.1.2/Conv
D RKNN: [17:53:26.729] 140 OutputOperator INT8 CPU (1,80,40,40) \ 0/0/0 150 OutputOperator:onnx::ReduceSum_558
D RKNN: [17:53:26.729] 141 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.21/m.0/cv2/conv/Conv
D RKNN: [17:53:26.729] 142 ConvClip INT8 NPU (1,80,40,40),(1,80,1,1),(1) (1,1,40,40) 8667/6400/8667 150 Conv:/model.22/ReduceSum_1_2conv
D RKNN: [17:53:26.729] 143 OutputOperator INT8 CPU (1,1,40,40) \ 0/0/0 50 OutputOperator:562
D RKNN: [17:53:26.729] 144 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.21/m.1/cv1/conv/Conv
D RKNN: [17:53:26.729] 145 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.21/m.1/cv2/conv/Conv
D RKNN: [17:53:26.729] 146 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.21/m.2/cv1/conv/Conv
D RKNN: [17:53:26.729] 147 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.21/m.2/cv2/conv/Conv
D RKNN: [17:53:26.729] 148 Concat INT8 NPU (1,256,20,20),(1,256,20,20),... (1,1280,20,20) 0/0/0 500 Concat:/model.21/Concat
D RKNN: [17:53:26.729] 149 ConvExSwish INT8 NPU (1,1280,20,20),(512,1280,1,1),(512) (1,512,20,20) 58183/256000/256000 1144 Conv:/model.21/cv2/conv/Conv
D RKNN: [17:53:26.729] 150 ConvExSwish INT8 NPU (1,512,20,20),(64,512,3,3),(64) (1,64,20,20) 22230/115200/115200 488 Conv:/model.22/cv2.2/cv2.2.0/conv/Conv
D RKNN: [17:53:26.729] 151 ConvExSwish INT8 NPU (1,512,20,20),(256,512,3,3),(256) (1,256,20,20) 62945/460800/460800 1354 Conv:/model.22/cv3.2/cv3.2.0/conv/Conv
D RKNN: [17:53:26.729] 152 ConvExSwish INT8 NPU (1,64,20,20),(64,64,3,3),(64) (1,64,20,20) 3745/14400/14400 61 Conv:/model.22/cv2.2/cv2.2.1/conv/Conv
D RKNN: [17:53:26.729] 153 Conv INT8 NPU (1,64,20,20),(64,64,1,1),(64) (1,64,20,20) 2360/3200/3200 29 Conv:/model.22/cv2.2/cv2.2.2/Conv
D RKNN: [17:53:26.729] 154 OutputOperator INT8 CPU (1,64,20,20) \ 0/0/0 25 OutputOperator:569
D RKNN: [17:53:26.729] 155 ConvExSwish INT8 NPU (1,256,20,20),(256,256,3,3),(256) (1,256,20,20) 33681/230400/230400 678 Conv:/model.22/cv3.2/cv3.2.1/conv/Conv
D RKNN: [17:53:26.729] 156 ConvSigmoid INT8 NPU (1,256,20,20),(80,256,1,1),(80) (1,80,20,20) 6851/9600/9600 120 Conv:/model.22/cv3.2/cv3.2.2/Conv
D RKNN: [17:53:26.729] 157 OutputOperator INT8 CPU (1,80,20,20) \ 0/0/0 37 OutputOperator:onnx::ReduceSum_577
D RKNN: [17:53:26.729] 158 ConvClip INT8 NPU (1,80,20,20),(1,80,1,1),(1) (1,1,20,20) 2174/1600/2174 37 Conv:/model.22/ReduceSum_2_2conv
D RKNN: [17:53:26.729] 159 OutputOperator INT8 CPU (1,1,20,20) \ 0/0/0 12 OutputOperator:581
D RKNN: [17:53:26.729] ------------------------------------------------------------------------------------------------------------------------------------------------------------------------
D RKNN: [17:53:26.730] <<<<<<<< end: rknn::RKNNModelRegCmdbuildPass
D RKNN: [17:53:26.730] >>>>>> start: rknn::RKNNModelExportPass
D RKNN: [17:53:26.731] Export RKNN model to /tmp/tmp3ryw8zjh/check.rknn
D RKNN: [17:53:26.793] <<<<<<<< end: rknn::RKNNModelExportPass
D RKNN: [17:53:26.793] >>>>>> start: rknn::RKNNMemStatisticsPass
D RKNN: [17:53:26.794] ---------------------------------------------------------------------------------------------------------------------------------------------------------
D RKNN: [17:53:26.794] Feature Tensor Information Table
D RKNN: [17:53:26.794] -----------------------------------------------------------------------------------------------------------------------+---------------------------------
D RKNN: [17:53:26.794] ID User Tensor DataType DataFormat OrigShape NativeShape | [Start End) Size
D RKNN: [17:53:26.794] -----------------------------------------------------------------------------------------------------------------------+---------------------------------
D RKNN: [17:53:26.794] 1 ConvExSwish images INT8 NC1HWC2 (1,3,640,640) (1,1,640,640,3) | 0x00000000 0x0012c000 0x0012c000
D RKNN: [17:53:26.794] 2 ConvExSwish /model.0/act/Mul_output_0 INT8 NC1HWC2 (1,64,320,320) (1,4,320,320,16) | 0x0012c000 0x0076c000 0x00640000
D RKNN: [17:53:26.794] 3 ConvExSwish /model.1/act/Mul_output_0 INT8 NC1HWC2 (1,128,160,160) (1,8,160,160,16) | 0x0076c000 0x00a8c000 0x00320000
D RKNN: [17:53:26.794] 4 Split /model.2/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,128,160,160) (1,8,160,160,16) | 0x00000000 0x00320000 0x00320000
D RKNN: [17:53:26.794] 5 ConvExSwish /model.2/Split_output_1 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x004b0000 0x00640000 0x00190000
D RKNN: [17:53:26.794] 6 ConvExSwish /model.2/m.0/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [17:53:26.794] 7 Add /model.2/Split_output_1 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x004b0000 0x00640000 0x00190000
D RKNN: [17:53:26.794] 7 Add /model.2/m.0/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00190000 0x00320000 0x00190000
D RKNN: [17:53:26.794] 8 ConvExSwish /model.2/m.0/Add_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [17:53:26.794] 9 ConvExSwish /model.2/m.1/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00190000 0x00320000 0x00190000
D RKNN: [17:53:26.794] 10 Add /model.2/m.0/Add_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [17:53:26.794] 10 Add /model.2/m.1/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00640000 0x007d0000 0x00190000
D RKNN: [17:53:26.794] 11 ConvExSwish /model.2/m.1/Add_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00190000 0x00320000 0x00190000
D RKNN: [17:53:26.794] 12 ConvExSwish /model.2/m.2/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00640000 0x007d0000 0x00190000
D RKNN: [17:53:26.794] 13 Add /model.2/m.1/Add_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00190000 0x00320000 0x00190000
D RKNN: [17:53:26.794] 13 Add /model.2/m.2/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x007d0000 0x00960000 0x00190000
D RKNN: [17:53:26.794] 14 Concat /model.2/Split_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00320000 0x004b0000 0x00190000
D RKNN: [17:53:26.794] 14 Concat /model.2/Split_output_1 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x004b0000 0x00640000 0x00190000
D RKNN: [17:53:26.794] 14 Concat /model.2/m.0/Add_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [17:53:26.794] 14 Concat /model.2/m.1/Add_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00190000 0x00320000 0x00190000
D RKNN: [17:53:26.794] 14 Concat /model.2/m.2/Add_output_0 INT8 NC1HWC2 (1,64,160,160) (1,4,160,160,16) | 0x00640000 0x007d0000 0x00190000
D RKNN: [17:53:26.794] 15 ConvExSwish /model.2/Concat_output_0 INT8 NC1HWC2 (1,320,160,160) (1,20,160,160,16) | 0x007d0000*0x00fa0000 0x007d0000
D RKNN: [17:53:26.794] 16 ConvExSwish /model.2/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,128,160,160) (1,8,160,160,16) | 0x00000000 0x00320000 0x00320000
D RKNN: [17:53:26.794] 17 ConvExSwish /model.3/act/Mul_output_0 INT8 NC1HWC2 (1,256,80,80) (1,16,80,80,16) | 0x00320000 0x004b0000 0x00190000
D RKNN: [17:53:26.794] 18 Split /model.4/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,80,80) (1,16,80,80,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [17:53:26.794] 19 ConvExSwish /model.4/Split_output_1 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [17:53:26.794] 20 ConvExSwish /model.4/m.0/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [17:53:26.794] 21 Add /model.4/Split_output_1 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [17:53:26.794] 21 Add /model.4/m.0/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x000c8000 0x00190000 0x000c8000
D RKNN: [17:53:26.794] 22 ConvExSwish /model.4/m.0/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [17:53:26.794] 23 ConvExSwish /model.4/m.1/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x000c8000 0x00190000 0x000c8000
D RKNN: [17:53:26.794] 24 Add /model.4/m.0/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [17:53:26.794] 24 Add /model.4/m.1/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00320000 0x003e8000 0x000c8000
D RKNN: [17:53:26.794] 25 ConvExSwish /model.4/m.1/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x000c8000 0x00190000 0x000c8000
D RKNN: [17:53:26.794] 26 ConvExSwish /model.4/m.2/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00320000 0x003e8000 0x000c8000
D RKNN: [17:53:26.794] 27 Add /model.4/m.1/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x000c8000 0x00190000 0x000c8000
D RKNN: [17:53:26.794] 27 Add /model.4/m.2/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x003e8000 0x004b0000 0x000c8000
D RKNN: [17:53:26.794] 28 ConvExSwish /model.4/m.2/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00320000 0x003e8000 0x000c8000
D RKNN: [17:53:26.794] 29 ConvExSwish /model.4/m.3/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x003e8000 0x004b0000 0x000c8000
D RKNN: [17:53:26.794] 30 Add /model.4/m.2/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00320000 0x003e8000 0x000c8000
D RKNN: [17:53:26.794] 30 Add /model.4/m.3/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x004b0000 0x00578000 0x000c8000
D RKNN: [17:53:26.794] 31 ConvExSwish /model.4/m.3/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x003e8000 0x004b0000 0x000c8000
D RKNN: [17:53:26.794] 32 ConvExSwish /model.4/m.4/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x004b0000 0x00578000 0x000c8000
D RKNN: [17:53:26.794] 33 Add /model.4/m.3/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x003e8000 0x004b0000 0x000c8000
D RKNN: [17:53:26.794] 33 Add /model.4/m.4/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00578000 0x00640000 0x000c8000
D RKNN: [17:53:26.794] 34 ConvExSwish /model.4/m.4/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x004b0000 0x00578000 0x000c8000
D RKNN: [17:53:26.794] 35 ConvExSwish /model.4/m.5/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00578000 0x00640000 0x000c8000
D RKNN: [17:53:26.794] 36 Add /model.4/m.4/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x004b0000 0x00578000 0x000c8000
D RKNN: [17:53:26.794] 36 Add /model.4/m.5/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00640000 0x00708000 0x000c8000
D RKNN: [17:53:26.794] 37 Concat /model.4/Split_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00258000 0x00320000 0x000c8000
D RKNN: [17:53:26.794] 37 Concat /model.4/Split_output_1 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [17:53:26.794] 37 Concat /model.4/m.0/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [17:53:26.794] 37 Concat /model.4/m.1/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x000c8000 0x00190000 0x000c8000
D RKNN: [17:53:26.794] 37 Concat /model.4/m.2/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00320000 0x003e8000 0x000c8000
D RKNN: [17:53:26.794] 37 Concat /model.4/m.3/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x003e8000 0x004b0000 0x000c8000
D RKNN: [17:53:26.794] 37 Concat /model.4/m.4/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x004b0000 0x00578000 0x000c8000
D RKNN: [17:53:26.794] 37 Concat /model.4/m.5/Add_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00578000 0x00640000 0x000c8000
D RKNN: [17:53:26.794] 38 ConvExSwish /model.4/Concat_output_0 INT8 NC1HWC2 (1,1024,80,80) (1,64,80,80,16) | 0x00640000 0x00c80000 0x00640000
D RKNN: [17:53:26.794] 39 ConvExSwish /model.4/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,80,80) (1,16,80,80,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [17:53:26.794] 40 ConvExSwish /model.5/act/Mul_output_0 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [17:53:26.794] 41 Split /model.6/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x00258000 0x00320000 0x000c8000
D RKNN: [17:53:26.794] 42 ConvExSwish /model.6/Split_output_1 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00190000 0x001f4000 0x00064000
D RKNN: [17:53:26.794] 43 ConvExSwish /model.6/m.0/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00258000 0x002bc000 0x00064000
D RKNN: [17:53:26.794] 44 Add /model.6/Split_output_1 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00190000 0x001f4000 0x00064000
D RKNN: [17:53:26.794] 44 Add /model.6/m.0/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x002bc000 0x00320000 0x00064000
D RKNN: [17:53:26.794] 45 ConvExSwish /model.6/m.0/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00258000 0x002bc000 0x00064000
D RKNN: [17:53:26.794] 46 ConvExSwish /model.6/m.1/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x002bc000 0x00320000 0x00064000
D RKNN: [17:53:26.794] 47 Add /model.6/m.0/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00258000 0x002bc000 0x00064000
D RKNN: [17:53:26.794] 47 Add /model.6/m.1/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00320000 0x00384000 0x00064000
D RKNN: [17:53:26.794] 48 ConvExSwish /model.6/m.1/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x002bc000 0x00320000 0x00064000
D RKNN: [17:53:26.794] 49 ConvExSwish /model.6/m.2/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00320000 0x00384000 0x00064000
D RKNN: [17:53:26.794] 50 Add /model.6/m.1/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x002bc000 0x00320000 0x00064000
D RKNN: [17:53:26.794] 50 Add /model.6/m.2/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00384000 0x003e8000 0x00064000
D RKNN: [17:53:26.794] 51 ConvExSwish /model.6/m.2/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00320000 0x00384000 0x00064000
D RKNN: [17:53:26.794] 52 ConvExSwish /model.6/m.3/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00384000 0x003e8000 0x00064000
D RKNN: [17:53:26.794] 53 Add /model.6/m.2/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00320000 0x00384000 0x00064000
D RKNN: [17:53:26.794] 53 Add /model.6/m.3/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x003e8000 0x0044c000 0x00064000
D RKNN: [17:53:26.794] 54 ConvExSwish /model.6/m.3/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00384000 0x003e8000 0x00064000
D RKNN: [17:53:26.794] 55 ConvExSwish /model.6/m.4/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x003e8000 0x0044c000 0x00064000
D RKNN: [17:53:26.794] 56 Add /model.6/m.3/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00384000 0x003e8000 0x00064000
D RKNN: [17:53:26.794] 56 Add /model.6/m.4/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x0044c000 0x004b0000 0x00064000
D RKNN: [17:53:26.794] 57 ConvExSwish /model.6/m.4/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x003e8000 0x0044c000 0x00064000
D RKNN: [17:53:26.794] 58 ConvExSwish /model.6/m.5/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x0044c000 0x004b0000 0x00064000
D RKNN: [17:53:26.794] 59 Add /model.6/m.4/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x003e8000 0x0044c000 0x00064000
D RKNN: [17:53:26.794] 59 Add /model.6/m.5/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x004b0000 0x00514000 0x00064000
D RKNN: [17:53:26.794] 60 Concat /model.6/Split_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x001f4000 0x00258000 0x00064000
D RKNN: [17:53:26.794] 60 Concat /model.6/Split_output_1 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00190000 0x001f4000 0x00064000
D RKNN: [17:53:26.794] 60 Concat /model.6/m.0/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00258000 0x002bc000 0x00064000
D RKNN: [17:53:26.794] 60 Concat /model.6/m.1/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x002bc000 0x00320000 0x00064000
D RKNN: [17:53:26.794] 60 Concat /model.6/m.2/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00320000 0x00384000 0x00064000
D RKNN: [17:53:26.794] 60 Concat /model.6/m.3/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00384000 0x003e8000 0x00064000
D RKNN: [17:53:26.794] 60 Concat /model.6/m.4/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x003e8000 0x0044c000 0x00064000
D RKNN: [17:53:26.794] 60 Concat /model.6/m.5/Add_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x0044c000 0x004b0000 0x00064000
D RKNN: [17:53:26.794] 61 ConvExSwish /model.6/Concat_output_0 INT8 NC1HWC2 (1,2048,40,40) (1,128,40,40,16) | 0x004b0000 0x007d0000 0x00320000
D RKNN: [17:53:26.794] 62 ConvExSwish /model.6/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [17:53:26.794] 63 ConvExSwish /model.7/act/Mul_output_0 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x00258000 0x0028a000 0x00032000
D RKNN: [17:53:26.794] 64 Split /model.8/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x0028a000 0x002bc000 0x00032000
D RKNN: [17:53:26.794] 65 ConvExSwish /model.8/Split_output_1 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00271000 0x0028a000 0x00019000
D RKNN: [17:53:26.794] 66 ConvExSwish /model.8/m.0/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0028a000 0x002a3000 0x00019000
D RKNN: [17:53:26.794] 67 Add /model.8/Split_output_1 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00271000 0x0028a000 0x00019000
D RKNN: [17:53:26.794] 67 Add /model.8/m.0/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002a3000 0x002bc000 0x00019000
D RKNN: [17:53:26.794] 68 ConvExSwish /model.8/m.0/Add_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0028a000 0x002a3000 0x00019000
D RKNN: [17:53:26.794] 69 ConvExSwish /model.8/m.1/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002a3000 0x002bc000 0x00019000
D RKNN: [17:53:26.794] 70 Add /model.8/m.0/Add_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0028a000 0x002a3000 0x00019000
D RKNN: [17:53:26.794] 70 Add /model.8/m.1/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002bc000 0x002d5000 0x00019000
D RKNN: [17:53:26.794] 71 ConvExSwish /model.8/m.1/Add_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002a3000 0x002bc000 0x00019000
D RKNN: [17:53:26.794] 72 ConvExSwish /model.8/m.2/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002bc000 0x002d5000 0x00019000
D RKNN: [17:53:26.794] 73 Add /model.8/m.1/Add_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002a3000 0x002bc000 0x00019000
D RKNN: [17:53:26.794] 73 Add /model.8/m.2/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002d5000 0x002ee000 0x00019000
D RKNN: [17:53:26.794] 74 Concat /model.8/Split_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00258000 0x00271000 0x00019000
D RKNN: [17:53:26.794] 74 Concat /model.8/Split_output_1 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00271000 0x0028a000 0x00019000
D RKNN: [17:53:26.794] 74 Concat /model.8/m.0/Add_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0028a000 0x002a3000 0x00019000
D RKNN: [17:53:26.794] 74 Concat /model.8/m.1/Add_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002a3000 0x002bc000 0x00019000
D RKNN: [17:53:26.794] 74 Concat /model.8/m.2/Add_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002bc000 0x002d5000 0x00019000
D RKNN: [17:53:26.794] 75 ConvExSwish /model.8/Concat_output_0 INT8 NC1HWC2 (1,1280,20,20) (1,80,20,20,16) | 0x002d5000 0x00352000 0x0007d000
D RKNN: [17:53:26.794] 76 ConvExSwish /model.8/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x00258000 0x0028a000 0x00032000
D RKNN: [17:53:26.794] 77 MaxPool /model.9/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0028a000 0x002a3000 0x00019000
D RKNN: [17:53:26.794] 78 MaxPool /model.9/m/MaxPool_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00258000 0x00271000 0x00019000
D RKNN: [17:53:26.794] 79 MaxPool /model.9/m_1/MaxPool_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00271000 0x0028a000 0x00019000
D RKNN: [17:53:26.794] 80 Concat /model.9/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0028a000 0x002a3000 0x00019000
D RKNN: [17:53:26.794] 80 Concat /model.9/m/MaxPool_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00258000 0x00271000 0x00019000
D RKNN: [17:53:26.794] 80 Concat /model.9/m_1/MaxPool_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00271000 0x0028a000 0x00019000
D RKNN: [17:53:26.794] 80 Concat /model.9/m_2/MaxPool_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002a3000 0x002bc000 0x00019000
D RKNN: [17:53:26.794] 81 ConvExSwish /model.9/Concat_output_0 INT8 NC1HWC2 (1,1024,20,20) (1,64,20,20,16) | 0x002bc000 0x00320000 0x00064000
D RKNN: [17:53:26.794] 82 Resize /model.9/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x00258000 0x0028a000 0x00032000
D RKNN: [17:53:26.794] 83 Concat /model.10/Resize_output_0 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x0028a040 0x00352040 0x000c8000
D RKNN: [17:53:26.794] 83 Concat /model.6/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [17:53:26.794] 84 ConvExSwish /model.11/Concat_output_0 INT8 NC1HWC2 (1,1024,40,40) (1,64,40,40,16) | 0x00352040 0x004e2040 0x00190000
D RKNN: [17:53:26.794] 85 Split /model.12/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [17:53:26.794] 86 ConvExSwish /model.12/Split_output_1 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x002ee000 0x00352000 0x00064000
D RKNN: [17:53:26.794] 87 ConvExSwish /model.12/m.0/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00190000 0x001f4000 0x00064000
D RKNN: [17:53:26.794] 88 ConvExSwish /model.12/m.0/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x001f4000 0x00258000 0x00064000
D RKNN: [17:53:26.794] 89 ConvExSwish /model.12/m.1/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00190000 0x001f4000 0x00064000
D RKNN: [17:53:26.794] 90 ConvExSwish /model.12/m.1/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00352000 0x003b6000 0x00064000
D RKNN: [17:53:26.794] 91 ConvExSwish /model.12/m.2/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00190000 0x001f4000 0x00064000
D RKNN: [17:53:26.794] 92 Concat /model.12/Split_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x0028a000 0x002ee000 0x00064000
D RKNN: [17:53:26.794] 92 Concat /model.12/Split_output_1 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x002ee000 0x00352000 0x00064000
D RKNN: [17:53:26.794] 92 Concat /model.12/m.0/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x001f4000 0x00258000 0x00064000
D RKNN: [17:53:26.794] 92 Concat /model.12/m.1/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00352000 0x003b6000 0x00064000
D RKNN: [17:53:26.794] 92 Concat /model.12/m.2/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x003b6000 0x0041a000 0x00064000
D RKNN: [17:53:26.794] 93 ConvExSwish /model.12/Concat_output_0 INT8 NC1HWC2 (1,1280,40,40) (1,80,40,40,16) | 0x0041a000 0x0060e000 0x001f4000
D RKNN: [17:53:26.794] 94 Resize /model.12/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [17:53:26.794] 95 Concat /model.13/Resize_output_0 INT8 NC1HWC2 (1,512,80,80) (1,32,80,80,16) | 0x0028a040 0x005aa040 0x00320000
D RKNN: [17:53:26.794] 95 Concat /model.4/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,80,80) (1,16,80,80,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [17:53:26.794] 96 ConvExSwish /model.14/Concat_output_0 INT8 NC1HWC2 (1,768,80,80) (1,48,80,80,16) | 0x005aa040 0x00a5a040 0x004b0000
D RKNN: [17:53:26.794] 97 Split /model.15/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,80,80) (1,16,80,80,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [17:53:26.794] 98 ConvExSwish /model.15/Split_output_1 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00352000 0x0041a000 0x000c8000
D RKNN: [17:53:26.794] 99 ConvExSwish /model.15/m.0/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [17:53:26.794] 100 ConvExSwish /model.15/m.0/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x000c8000 0x00190000 0x000c8000
D RKNN: [17:53:26.794] 101 ConvExSwish /model.15/m.1/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [17:53:26.794] 102 ConvExSwish /model.15/m.1/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x0041a000 0x004e2000 0x000c8000
D RKNN: [17:53:26.794] 103 ConvExSwish /model.15/m.2/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [17:53:26.794] 104 Concat /model.15/Split_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x0028a000 0x00352000 0x000c8000
D RKNN: [17:53:26.794] 104 Concat /model.15/Split_output_1 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x00352000 0x0041a000 0x000c8000
D RKNN: [17:53:26.794] 104 Concat /model.15/m.0/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x000c8000 0x00190000 0x000c8000
D RKNN: [17:53:26.794] 104 Concat /model.15/m.1/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x0041a000 0x004e2000 0x000c8000
D RKNN: [17:53:26.794] 104 Concat /model.15/m.2/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,128,80,80) (1,8,80,80,16) | 0x004e2000 0x005aa000 0x000c8000
D RKNN: [17:53:26.794] 105 ConvExSwish /model.15/Concat_output_0 INT8 NC1HWC2 (1,640,80,80) (1,40,80,80,16) | 0x005aa000 0x00992000 0x003e8000
D RKNN: [17:53:26.794] 106 ConvExSwish /model.15/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,80,80) (1,16,80,80,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [17:53:26.794] 107 Concat /model.16/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x0028a000 0x002ee000 0x00064000
D RKNN: [17:53:26.794] 107 Concat /model.12/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x00190000 0x00258000 0x000c8000
D RKNN: [17:53:26.794] 108 ConvExSwish /model.15/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,80,80) (1,16,80,80,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [17:53:26.794] 109 ConvExSwish /model.15/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,80,80) (1,16,80,80,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [17:53:26.794] 110 ConvExSwish /model.17/Concat_output_0 INT8 NC1HWC2 (1,768,40,40) (1,48,40,40,16) | 0x002ee000 0x0041a000 0x0012c000
D RKNN: [17:53:26.794] 111 Split /model.18/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x00000000 0x000c8000 0x000c8000
D RKNN: [17:53:26.794] 112 ConvExSwish /model.22/cv2.0/cv2.0.0/act/Mul_output_0 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x0028a000 0x002ee000 0x00064000
D RKNN: [17:53:26.794] 113 Conv /model.22/cv2.0/cv2.0.1/act/Mul_output_0 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x003b6000 0x0041a000 0x00064000
D RKNN: [17:53:26.794] 114 OutputOperator 530 INT8 NC1HWC2 (1,64,80,80) (1,4,80,80,16) | 0x0028a000 0x002ee000 0x00064000
D RKNN: [17:53:26.794] 115 ConvExSwish /model.22/cv3.0/cv3.0.0/act/Mul_output_0 INT8 NC1HWC2 (1,256,80,80) (1,16,80,80,16) | 0x0041a000 0x005aa000 0x00190000
D RKNN: [17:53:26.794] 116 ConvExSwish /model.18/Split_output_1 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00352000 0x003b6000 0x00064000
D RKNN: [17:53:26.794] 117 ConvSigmoid /model.22/cv3.0/cv3.0.1/act/Mul_output_0 INT8 NC1HWC2 (1,256,80,80) (1,16,80,80,16) | 0x00000000 0x00190000 0x00190000
D RKNN: [17:53:26.794] 118 OutputOperator onnx::ReduceSum_538 INT8 NC1HWC2 (1,80,80,80) (1,6,80,80,16) | 0x003b6000 0x0044c000 0x00096000
D RKNN: [17:53:26.794] 119 ConvExSwish /model.18/m.0/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00190000 0x001f4000 0x00064000
D RKNN: [17:53:26.794] 120 ConvClip onnx::ReduceSum_538 INT8 NC1HWC2 (1,80,80,80) (1,6,80,80,16) | 0x003b6000 0x0044c000 0x00096000
D RKNN: [17:53:26.794] 121 OutputOperator 543 INT8 NC1HWC2 (1,1,80,80) (1,2,80,80,16) | 0x00000000 0x00032000 0x00032000
D RKNN: [17:53:26.794] 122 ConvExSwish /model.18/m.0/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x001f4000 0x00258000 0x00064000
D RKNN: [17:53:26.794] 123 ConvExSwish /model.18/m.1/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00032000 0x00096000 0x00064000
D RKNN: [17:53:26.794] 124 ConvExSwish /model.18/m.1/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00096000 0x000fa000 0x00064000
D RKNN: [17:53:26.794] 125 ConvExSwish /model.18/m.2/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00032000 0x00096000 0x00064000
D RKNN: [17:53:26.794] 126 Concat /model.18/Split_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x002ee000 0x00352000 0x00064000
D RKNN: [17:53:26.794] 126 Concat /model.18/Split_output_1 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00352000 0x003b6000 0x00064000
D RKNN: [17:53:26.794] 126 Concat /model.18/m.0/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x001f4000 0x00258000 0x00064000
D RKNN: [17:53:26.794] 126 Concat /model.18/m.1/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x00096000 0x000fa000 0x00064000
D RKNN: [17:53:26.794] 126 Concat /model.18/m.2/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x000fa000 0x0015e000 0x00064000
D RKNN: [17:53:26.794] 127 ConvExSwish /model.18/Concat_output_0 INT8 NC1HWC2 (1,1280,40,40) (1,80,40,40,16) | 0x0044c000 0x00640000 0x001f4000
D RKNN: [17:53:26.794] 128 ConvExSwish /model.18/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x002ee000 0x003b6000 0x000c8000
D RKNN: [17:53:26.794] 129 Concat /model.19/act/Mul_output_0 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x00032000 0x00064000 0x00032000
D RKNN: [17:53:26.794] 129 Concat /model.9/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x00258000 0x0028a000 0x00032000
D RKNN: [17:53:26.794] 130 ConvExSwish /model.18/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x002ee000 0x003b6000 0x000c8000
D RKNN: [17:53:26.794] 131 ConvExSwish /model.18/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,512,40,40) (1,32,40,40,16) | 0x002ee000 0x003b6000 0x000c8000
D RKNN: [17:53:26.794] 132 ConvExSwish /model.20/Concat_output_0 INT8 NC1HWC2 (1,1024,20,20) (1,64,20,20,16) | 0x00064000 0x000c8000 0x00064000
D RKNN: [17:53:26.794] 133 Split /model.21/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x002ee000 0x00320000 0x00032000
D RKNN: [17:53:26.794] 134 ConvExSwish /model.22/cv2.1/cv2.1.0/act/Mul_output_0 INT8 NC1HWC2 (1,64,40,40) (1,4,40,40,16) | 0x00032000 0x0004b000 0x00019000
D RKNN: [17:53:26.794] 135 Conv /model.22/cv2.1/cv2.1.1/act/Mul_output_0 INT8 NC1HWC2 (1,64,40,40) (1,4,40,40,16) | 0x0007d000 0x00096000 0x00019000
D RKNN: [17:53:26.794] 136 OutputOperator 550 INT8 NC1HWC2 (1,64,40,40) (1,4,40,40,16) | 0x00032000 0x0004b000 0x00019000
D RKNN: [17:53:26.794] 137 ConvExSwish /model.22/cv3.1/cv3.1.0/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x000c8000 0x0012c000 0x00064000
D RKNN: [17:53:26.794] 138 ConvExSwish /model.21/Split_output_1 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00064000 0x0007d000 0x00019000
D RKNN: [17:53:26.794] 139 ConvSigmoid /model.22/cv3.1/cv3.1.1/act/Mul_output_0 INT8 NC1HWC2 (1,256,40,40) (1,16,40,40,16) | 0x002ee000 0x00352000 0x00064000
D RKNN: [17:53:26.794] 140 OutputOperator onnx::ReduceSum_558 INT8 NC1HWC2 (1,80,40,40) (1,6,40,40,16) | 0x0036b000 0x00390800 0x00025800
D RKNN: [17:53:26.794] 141 ConvExSwish /model.21/m.0/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00352000 0x0036b000 0x00019000
D RKNN: [17:53:26.794] 142 ConvClip onnx::ReduceSum_558 INT8 NC1HWC2 (1,80,40,40) (1,6,40,40,16) | 0x0036b000 0x00390800 0x00025800
D RKNN: [17:53:26.794] 143 OutputOperator 562 INT8 NC1HWC2 (1,1,40,40) (1,2,40,40,16) | 0x003a9800 0x003b6000 0x0000c800
D RKNN: [17:53:26.794] 144 ConvExSwish /model.21/m.0/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00390800 0x003a9800 0x00019000
D RKNN: [17:53:26.794] 145 ConvExSwish /model.21/m.1/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002ee000 0x00307000 0x00019000
D RKNN: [17:53:26.794] 146 ConvExSwish /model.21/m.1/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00307000 0x00320000 0x00019000
D RKNN: [17:53:26.794] 147 ConvExSwish /model.21/m.2/cv1/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002ee000 0x00307000 0x00019000
D RKNN: [17:53:26.794] 148 Concat /model.21/Split_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x0004b000 0x00064000 0x00019000
D RKNN: [17:53:26.794] 148 Concat /model.21/Split_output_1 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00064000 0x0007d000 0x00019000
D RKNN: [17:53:26.794] 148 Concat /model.21/m.0/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00390800 0x003a9800 0x00019000
D RKNN: [17:53:26.794] 148 Concat /model.21/m.1/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00307000 0x00320000 0x00019000
D RKNN: [17:53:26.794] 148 Concat /model.21/m.2/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00320000 0x00339000 0x00019000
D RKNN: [17:53:26.794] 149 ConvExSwish /model.21/Concat_output_0 INT8 NC1HWC2 (1,1280,20,20) (1,80,20,20,16) | 0x0007d000 0x000fa000 0x0007d000
D RKNN: [17:53:26.794] 150 ConvExSwish /model.21/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x0004b000 0x0007d000 0x00032000
D RKNN: [17:53:26.794] 151 ConvExSwish /model.21/cv2/act/Mul_output_0 INT8 NC1HWC2 (1,512,20,20) (1,32,20,20,16) | 0x0004b000 0x0007d000 0x00032000
D RKNN: [17:53:26.794] 152 ConvExSwish /model.22/cv2.2/cv2.2.0/act/Mul_output_0 INT8 NC1HWC2 (1,64,20,20) (1,4,20,20,16) | 0x00390800 0x00396c00 0x00006400
D RKNN: [17:53:26.794] 153 Conv /model.22/cv2.2/cv2.2.1/act/Mul_output_0 INT8 NC1HWC2 (1,64,20,20) (1,4,20,20,16) | 0x00396c00 0x0039d000 0x00006400
D RKNN: [17:53:26.794] 154 OutputOperator 569 INT8 NC1HWC2 (1,64,20,20) (1,4,20,20,16) | 0x00390800 0x00396c00 0x00006400
D RKNN: [17:53:26.794] 155 ConvExSwish /model.22/cv3.2/cv3.2.0/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x002ee000 0x00307000 0x00019000
D RKNN: [17:53:26.794] 156 ConvSigmoid /model.22/cv3.2/cv3.2.1/act/Mul_output_0 INT8 NC1HWC2 (1,256,20,20) (1,16,20,20,16) | 0x00307000 0x00320000 0x00019000
D RKNN: [17:53:26.794] 157 OutputOperator onnx::ReduceSum_577 INT8 NC1HWC2 (1,80,20,20) (1,6,20,20,16) | 0x00396c00 0x003a0200 0x00009600
D RKNN: [17:53:26.794] 158 ConvClip onnx::ReduceSum_577 INT8 NC1HWC2 (1,80,20,20) (1,6,20,20,16) | 0x00396c00 0x003a0200 0x00009600
D RKNN: [17:53:26.794] 159 OutputOperator 581 INT8 NC1HWC2 (1,1,20,20) (1,2,20,20,16) | 0x003a0200 0x003a3400 0x00003200
D RKNN: [17:53:26.794] -----------------------------------------------------------------------------------------------------------------------+---------------------------------
D RKNN: [17:53:26.794] -----------------------------------------------------------------------------------------------------------------
D RKNN: [17:53:26.794] Const Tensor Information Table
D RKNN: [17:53:26.794] -------------------------------------------------------------------------------+---------------------------------
D RKNN: [17:53:26.794] ID User Tensor DataType OrigShape | [Start End) Size
D RKNN: [17:53:26.794] -------------------------------------------------------------------------------+---------------------------------
D RKNN: [17:53:26.794] 1 ConvExSwish model.0.conv.weight INT8 (64,3,3,3) | 0x00000000 0x00002400 0x00002400
D RKNN: [17:53:26.794] 1 ConvExSwish model.0.conv.bias INT32 (64) | 0x00002400 0x00002600 0x00000200
D RKNN: [17:53:26.794] 2 ConvExSwish model.1.conv.weight INT8 (128,64,3,3) | 0x00002600 0x00014600 0x00012000
D RKNN: [17:53:26.794] 2 ConvExSwish model.1.conv.bias INT32 (128) | 0x00014600 0x00014a00 0x00000400
D RKNN: [17:53:26.794] 3 ConvExSwish model.2.cv1.conv.weight INT8 (128,128,1,1) | 0x00014a00 0x00018a00 0x00004000
D RKNN: [17:53:26.794] 3 ConvExSwish model.2.cv1.conv.bias INT32 (128) | 0x00018a00 0x00018e00 0x00000400
D RKNN: [17:53:26.794] 4 Split /model.2/Split_split INT64 (2) | 0x029cf900 0x029cf910 0x00000010
D RKNN: [17:53:26.794] 5 ConvExSwish model.2.m.0.cv1.conv.weight INT8 (64,64,3,3) | 0x00023200 0x0002c200 0x00009000
D RKNN: [17:53:26.794] 5 ConvExSwish model.2.m.0.cv1.conv.bias INT32 (64) | 0x0002c200 0x0002c400 0x00000200
D RKNN: [17:53:26.794] 6 ConvExSwish model.2.m.0.cv2.conv.weight INT8 (64,64,3,3) | 0x0002c400 0x00035400 0x00009000
D RKNN: [17:53:26.794] 6 ConvExSwish model.2.m.0.cv2.conv.bias INT32 (64) | 0x00035400 0x00035600 0x00000200
D RKNN: [17:53:26.794] 8 ConvExSwish model.2.m.1.cv1.conv.weight INT8 (64,64,3,3) | 0x00035600 0x0003e600 0x00009000
D RKNN: [17:53:26.794] 8 ConvExSwish model.2.m.1.cv1.conv.bias INT32 (64) | 0x0003e600 0x0003e800 0x00000200
D RKNN: [17:53:26.794] 9 ConvExSwish model.2.m.1.cv2.conv.weight INT8 (64,64,3,3) | 0x0003e800 0x00047800 0x00009000
D RKNN: [17:53:26.794] 9 ConvExSwish model.2.m.1.cv2.conv.bias INT32 (64) | 0x00047800 0x00047a00 0x00000200
D RKNN: [17:53:26.794] 11 ConvExSwish model.2.m.2.cv1.conv.weight INT8 (64,64,3,3) | 0x00047a00 0x00050a00 0x00009000
D RKNN: [17:53:26.794] 11 ConvExSwish model.2.m.2.cv1.conv.bias INT32 (64) | 0x00050a00 0x00050c00 0x00000200
D RKNN: [17:53:26.794] 12 ConvExSwish model.2.m.2.cv2.conv.weight INT8 (64,64,3,3) | 0x00050c00 0x00059c00 0x00009000
D RKNN: [17:53:26.794] 12 ConvExSwish model.2.m.2.cv2.conv.bias INT32 (64) | 0x00059c00 0x00059e00 0x00000200
D RKNN: [17:53:26.794] 15 ConvExSwish model.2.cv2.conv.weight INT8 (128,320,1,1) | 0x00018e00 0x00022e00 0x0000a000
D RKNN: [17:53:26.794] 15 ConvExSwish model.2.cv2.conv.bias INT32 (128) | 0x00022e00 0x00023200 0x00000400
D RKNN: [17:53:26.794] 16 ConvExSwish model.3.conv.weight INT8 (256,128,3,3) | 0x00059e00 0x000a1e00 0x00048000
D RKNN: [17:53:26.794] 16 ConvExSwish model.3.conv.bias INT32 (256) | 0x000a1e00 0x000a2600 0x00000800
D RKNN: [17:53:26.794] 17 ConvExSwish model.4.cv1.conv.weight INT8 (256,256,1,1) | 0x000a2600 0x000b2600 0x00010000
D RKNN: [17:53:26.794] 17 ConvExSwish model.4.cv1.conv.bias INT32 (256) | 0x000b2600 0x000b2e00 0x00000800
D RKNN: [17:53:26.794] 18 Split /model.4/Split_split INT64 (2) | 0x029cf940 0x029cf950 0x00000010
D RKNN: [17:53:26.794] 19 ConvExSwish model.4.m.0.cv1.conv.weight INT8 (128,128,3,3) | 0x000f3600 0x00117600 0x00024000
D RKNN: [17:53:26.794] 19 ConvExSwish model.4.m.0.cv1.conv.bias INT32 (128) | 0x00117600 0x00117a00 0x00000400
D RKNN: [17:53:26.794] 20 ConvExSwish model.4.m.0.cv2.conv.weight INT8 (128,128,3,3) | 0x00117a00 0x0013ba00 0x00024000
D RKNN: [17:53:26.794] 20 ConvExSwish model.4.m.0.cv2.conv.bias INT32 (128) | 0x0013ba00 0x0013be00 0x00000400
D RKNN: [17:53:26.794] 22 ConvExSwish model.4.m.1.cv1.conv.weight INT8 (128,128,3,3) | 0x0013be00 0x0015fe00 0x00024000
D RKNN: [17:53:26.794] 22 ConvExSwish model.4.m.1.cv1.conv.bias INT32 (128) | 0x0015fe00 0x00160200 0x00000400
D RKNN: [17:53:26.794] 23 ConvExSwish model.4.m.1.cv2.conv.weight INT8 (128,128,3,3) | 0x00160200 0x00184200 0x00024000
D RKNN: [17:53:26.794] 23 ConvExSwish model.4.m.1.cv2.conv.bias INT32 (128) | 0x00184200 0x00184600 0x00000400
D RKNN: [17:53:26.794] 25 ConvExSwish model.4.m.2.cv1.conv.weight INT8 (128,128,3,3) | 0x00184600 0x001a8600 0x00024000
D RKNN: [17:53:26.794] 25 ConvExSwish model.4.m.2.cv1.conv.bias INT32 (128) | 0x001a8600 0x001a8a00 0x00000400
D RKNN: [17:53:26.794] 26 ConvExSwish model.4.m.2.cv2.conv.weight INT8 (128,128,3,3) | 0x001a8a00 0x001cca00 0x00024000
D RKNN: [17:53:26.794] 26 ConvExSwish model.4.m.2.cv2.conv.bias INT32 (128) | 0x001cca00 0x001cce00 0x00000400
D RKNN: [17:53:26.794] 28 ConvExSwish model.4.m.3.cv1.conv.weight INT8 (128,128,3,3) | 0x001cce00 0x001f0e00 0x00024000
D RKNN: [17:53:26.794] 28 ConvExSwish model.4.m.3.cv1.conv.bias INT32 (128) | 0x001f0e00 0x001f1200 0x00000400
D RKNN: [17:53:26.794] 29 ConvExSwish model.4.m.3.cv2.conv.weight INT8 (128,128,3,3) | 0x001f1200 0x00215200 0x00024000
D RKNN: [17:53:26.794] 29 ConvExSwish model.4.m.3.cv2.conv.bias INT32 (128) | 0x00215200 0x00215600 0x00000400
D RKNN: [17:53:26.794] 31 ConvExSwish model.4.m.4.cv1.conv.weight INT8 (128,128,3,3) | 0x00215600 0x00239600 0x00024000
D RKNN: [17:53:26.794] 31 ConvExSwish model.4.m.4.cv1.conv.bias INT32 (128) | 0x00239600 0x00239a00 0x00000400
D RKNN: [17:53:26.794] 32 ConvExSwish model.4.m.4.cv2.conv.weight INT8 (128,128,3,3) | 0x00239a00 0x0025da00 0x00024000
D RKNN: [17:53:26.794] 32 ConvExSwish model.4.m.4.cv2.conv.bias INT32 (128) | 0x0025da00 0x0025de00 0x00000400
D RKNN: [17:53:26.794] 34 ConvExSwish model.4.m.5.cv1.conv.weight INT8 (128,128,3,3) | 0x0025de00 0x00281e00 0x00024000
D RKNN: [17:53:26.794] 34 ConvExSwish model.4.m.5.cv1.conv.bias INT32 (128) | 0x00281e00 0x00282200 0x00000400
D RKNN: [17:53:26.794] 35 ConvExSwish model.4.m.5.cv2.conv.weight INT8 (128,128,3,3) | 0x00282200 0x002a6200 0x00024000
D RKNN: [17:53:26.794] 35 ConvExSwish model.4.m.5.cv2.conv.bias INT32 (128) | 0x002a6200 0x002a6600 0x00000400
D RKNN: [17:53:26.794] 38 ConvExSwish model.4.cv2.conv.weight INT8 (256,1024,1,1) | 0x000b2e00 0x000f2e00 0x00040000
D RKNN: [17:53:26.794] 38 ConvExSwish model.4.cv2.conv.bias INT32 (256) | 0x000f2e00 0x000f3600 0x00000800
D RKNN: [17:53:26.794] 39 ConvExSwish model.5.conv.weight INT8 (512,256,3,3) | 0x002a6600 0x003c6600 0x00120000
D RKNN: [17:53:26.794] 39 ConvExSwish model.5.conv.bias INT32 (512) | 0x003c6600 0x003c7600 0x00001000
D RKNN: [17:53:26.794] 40 ConvExSwish model.6.cv1.conv.weight INT8 (512,512,1,1) | 0x003c7600 0x00407600 0x00040000
D RKNN: [17:53:26.794] 40 ConvExSwish model.6.cv1.conv.bias INT32 (512) | 0x00407600 0x00408600 0x00001000
D RKNN: [17:53:26.794] 41 Split /model.6/Split_split INT64 (2) | 0x029cf980 0x029cf990 0x00000010
D RKNN: [17:53:26.794] 42 ConvExSwish model.6.m.0.cv1.conv.weight INT8 (256,256,3,3) | 0x00509600 0x00599600 0x00090000
D RKNN: [17:53:26.794] 42 ConvExSwish model.6.m.0.cv1.conv.bias INT32 (256) | 0x00599600 0x00599e00 0x00000800
D RKNN: [17:53:26.794] 43 ConvExSwish model.6.m.0.cv2.conv.weight INT8 (256,256,3,3) | 0x00599e00 0x00629e00 0x00090000
D RKNN: [17:53:26.794] 43 ConvExSwish model.6.m.0.cv2.conv.bias INT32 (256) | 0x00629e00 0x0062a600 0x00000800
D RKNN: [17:53:26.794] 45 ConvExSwish model.6.m.1.cv1.conv.weight INT8 (256,256,3,3) | 0x0062a600 0x006ba600 0x00090000
D RKNN: [17:53:26.794] 45 ConvExSwish model.6.m.1.cv1.conv.bias INT32 (256) | 0x006ba600 0x006bae00 0x00000800
D RKNN: [17:53:26.794] 46 ConvExSwish model.6.m.1.cv2.conv.weight INT8 (256,256,3,3) | 0x006bae00 0x0074ae00 0x00090000
D RKNN: [17:53:26.794] 46 ConvExSwish model.6.m.1.cv2.conv.bias INT32 (256) | 0x0074ae00 0x0074b600 0x00000800
D RKNN: [17:53:26.794] 48 ConvExSwish model.6.m.2.cv1.conv.weight INT8 (256,256,3,3) | 0x0074b600 0x007db600 0x00090000
D RKNN: [17:53:26.794] 48 ConvExSwish model.6.m.2.cv1.conv.bias INT32 (256) | 0x007db600 0x007dbe00 0x00000800
D RKNN: [17:53:26.794] 49 ConvExSwish model.6.m.2.cv2.conv.weight INT8 (256,256,3,3) | 0x007dbe00 0x0086be00 0x00090000
D RKNN: [17:53:26.794] 49 ConvExSwish model.6.m.2.cv2.conv.bias INT32 (256) | 0x0086be00 0x0086c600 0x00000800
D RKNN: [17:53:26.794] 51 ConvExSwish model.6.m.3.cv1.conv.weight INT8 (256,256,3,3) | 0x0086c600 0x008fc600 0x00090000
D RKNN: [17:53:26.794] 51 ConvExSwish model.6.m.3.cv1.conv.bias INT32 (256) | 0x008fc600 0x008fce00 0x00000800
D RKNN: [17:53:26.794] 52 ConvExSwish model.6.m.3.cv2.conv.weight INT8 (256,256,3,3) | 0x008fce00 0x0098ce00 0x00090000
D RKNN: [17:53:26.794] 52 ConvExSwish model.6.m.3.cv2.conv.bias INT32 (256) | 0x0098ce00 0x0098d600 0x00000800
D RKNN: [17:53:26.794] 54 ConvExSwish model.6.m.4.cv1.conv.weight INT8 (256,256,3,3) | 0x0098d600 0x00a1d600 0x00090000
D RKNN: [17:53:26.794] 54 ConvExSwish model.6.m.4.cv1.conv.bias INT32 (256) | 0x00a1d600 0x00a1de00 0x00000800
D RKNN: [17:53:26.794] 55 ConvExSwish model.6.m.4.cv2.conv.weight INT8 (256,256,3,3) | 0x00a1de00 0x00aade00 0x00090000
D RKNN: [17:53:26.794] 55 ConvExSwish model.6.m.4.cv2.conv.bias INT32 (256) | 0x00aade00 0x00aae600 0x00000800
D RKNN: [17:53:26.794] 57 ConvExSwish model.6.m.5.cv1.conv.weight INT8 (256,256,3,3) | 0x00aae600 0x00b3e600 0x00090000
D RKNN: [17:53:26.794] 57 ConvExSwish model.6.m.5.cv1.conv.bias INT32 (256) | 0x00b3e600 0x00b3ee00 0x00000800
D RKNN: [17:53:26.794] 58 ConvExSwish model.6.m.5.cv2.conv.weight INT8 (256,256,3,3) | 0x00b3ee00 0x00bcee00 0x00090000
D RKNN: [17:53:26.794] 58 ConvExSwish model.6.m.5.cv2.conv.bias INT32 (256) | 0x00bcee00 0x00bcf600 0x00000800
D RKNN: [17:53:26.794] 61 ConvExSwish model.6.cv2.conv.weight INT8 (512,2048,1,1) | 0x00408600 0x00508600 0x00100000
D RKNN: [17:53:26.794] 61 ConvExSwish model.6.cv2.conv.bias INT32 (512) | 0x00508600 0x00509600 0x00001000
D RKNN: [17:53:26.794] 62 ConvExSwish model.7.conv.weight INT8 (512,512,3,3) | 0x00bcf600 0x00e0f600 0x00240000
D RKNN: [17:53:26.794] 62 ConvExSwish model.7.conv.bias INT32 (512) | 0x00e0f600 0x00e10600 0x00001000
D RKNN: [17:53:26.794] 63 ConvExSwish model.8.cv1.conv.weight INT8 (512,512,1,1) | 0x00e10600 0x00e50600 0x00040000
D RKNN: [17:53:26.794] 63 ConvExSwish model.8.cv1.conv.bias INT32 (512) | 0x00e50600 0x00e51600 0x00001000
D RKNN: [17:53:26.794] 64 Split /model.8/Split_split INT64 (2) | 0x029cf9c0 0x029cf9d0 0x00000010
D RKNN: [17:53:26.794] 65 ConvExSwish model.8.m.0.cv1.conv.weight INT8 (256,256,3,3) | 0x00ef2600 0x00f82600 0x00090000
D RKNN: [17:53:26.794] 65 ConvExSwish model.8.m.0.cv1.conv.bias INT32 (256) | 0x00f82600 0x00f82e00 0x00000800
D RKNN: [17:53:26.794] 66 ConvExSwish model.8.m.0.cv2.conv.weight INT8 (256,256,3,3) | 0x00f82e00 0x01012e00 0x00090000
D RKNN: [17:53:26.794] 66 ConvExSwish model.8.m.0.cv2.conv.bias INT32 (256) | 0x01012e00 0x01013600 0x00000800
D RKNN: [17:53:26.794] 68 ConvExSwish model.8.m.1.cv1.conv.weight INT8 (256,256,3,3) | 0x01013600 0x010a3600 0x00090000
D RKNN: [17:53:26.794] 68 ConvExSwish model.8.m.1.cv1.conv.bias INT32 (256) | 0x010a3600 0x010a3e00 0x00000800
D RKNN: [17:53:26.794] 69 ConvExSwish model.8.m.1.cv2.conv.weight INT8 (256,256,3,3) | 0x010a3e00 0x01133e00 0x00090000
D RKNN: [17:53:26.794] 69 ConvExSwish model.8.m.1.cv2.conv.bias INT32 (256) | 0x01133e00 0x01134600 0x00000800
D RKNN: [17:53:26.794] 71 ConvExSwish model.8.m.2.cv1.conv.weight INT8 (256,256,3,3) | 0x01134600 0x011c4600 0x00090000
D RKNN: [17:53:26.794] 71 ConvExSwish model.8.m.2.cv1.conv.bias INT32 (256) | 0x011c4600 0x011c4e00 0x00000800
D RKNN: [17:53:26.794] 72 ConvExSwish model.8.m.2.cv2.conv.weight INT8 (256,256,3,3) | 0x011c4e00 0x01254e00 0x00090000
D RKNN: [17:53:26.794] 72 ConvExSwish model.8.m.2.cv2.conv.bias INT32 (256) | 0x01254e00 0x01255600 0x00000800
D RKNN: [17:53:26.794] 75 ConvExSwish model.8.cv2.conv.weight INT8 (512,1280,1,1) | 0x00e51600 0x00ef1600 0x000a0000
D RKNN: [17:53:26.794] 75 ConvExSwish model.8.cv2.conv.bias INT32 (512) | 0x00ef1600 0x00ef2600 0x00001000
D RKNN: [17:53:26.794] 76 ConvExSwish model.9.cv1.conv.weight INT8 (256,512,1,1) | 0x01255600 0x01275600 0x00020000
D RKNN: [17:53:26.794] 76 ConvExSwish model.9.cv1.conv.bias INT32 (256) | 0x01275600 0x01275e00 0x00000800
D RKNN: [17:53:26.794] 81 ConvExSwish model.9.cv2.conv.weight INT8 (512,1024,1,1) | 0x01275e00 0x012f5e00 0x00080000
D RKNN: [17:53:26.794] 81 ConvExSwish model.9.cv2.conv.bias INT32 (512) | 0x012f5e00 0x012f6e00 0x00001000
D RKNN: [17:53:26.794] 82 Resize /model.10/Constant_1_output_0 FLOAT (0) | 0x029cfc00 0x029cfc00 0x00000000
D RKNN: [17:53:26.794] 82 Resize /model.10/Constant_output_0 FLOAT (4) | 0x029cfb00 0x029cfc00 0x00000100
D RKNN: [17:53:26.794] 84 ConvExSwish model.12.cv1.conv.weight INT8 (512,1024,1,1) | 0x012f6e00 0x01376e00 0x00080000
D RKNN: [17:53:26.794] 84 ConvExSwish model.12.cv1.conv.bias INT32 (512) | 0x01376e00 0x01377e00 0x00001000
D RKNN: [17:53:26.794] 85 Split /model.12/Split_split INT64 (2) | 0x029cfa00 0x029cfa10 0x00000010
D RKNN: [17:53:26.794] 86 ConvExSwish model.12.m.0.cv1.conv.weight INT8 (256,256,3,3) | 0x01418e00 0x014a8e00 0x00090000
D RKNN: [17:53:26.794] 86 ConvExSwish model.12.m.0.cv1.conv.bias INT32 (256) | 0x014a8e00 0x014a9600 0x00000800
D RKNN: [17:53:26.794] 87 ConvExSwish model.12.m.0.cv2.conv.weight INT8 (256,256,3,3) | 0x014a9600 0x01539600 0x00090000
D RKNN: [17:53:26.794] 87 ConvExSwish model.12.m.0.cv2.conv.bias INT32 (256) | 0x01539600 0x01539e00 0x00000800
D RKNN: [17:53:26.794] 88 ConvExSwish model.12.m.1.cv1.conv.weight INT8 (256,256,3,3) | 0x01539e00 0x015c9e00 0x00090000
D RKNN: [17:53:26.794] 88 ConvExSwish model.12.m.1.cv1.conv.bias INT32 (256) | 0x015c9e00 0x015ca600 0x00000800
D RKNN: [17:53:26.794] 89 ConvExSwish model.12.m.1.cv2.conv.weight INT8 (256,256,3,3) | 0x015ca600 0x0165a600 0x00090000
D RKNN: [17:53:26.794] 89 ConvExSwish model.12.m.1.cv2.conv.bias INT32 (256) | 0x0165a600 0x0165ae00 0x00000800
D RKNN: [17:53:26.794] 90 ConvExSwish model.12.m.2.cv1.conv.weight INT8 (256,256,3,3) | 0x0165ae00 0x016eae00 0x00090000
D RKNN: [17:53:26.794] 90 ConvExSwish model.12.m.2.cv1.conv.bias INT32 (256) | 0x016eae00 0x016eb600 0x00000800
D RKNN: [17:53:26.794] 91 ConvExSwish model.12.m.2.cv2.conv.weight INT8 (256,256,3,3) | 0x016eb600 0x0177b600 0x00090000
D RKNN: [17:53:26.794] 91 ConvExSwish model.12.m.2.cv2.conv.bias INT32 (256) | 0x0177b600 0x0177be00 0x00000800
D RKNN: [17:53:26.794] 93 ConvExSwish model.12.cv2.conv.weight INT8 (512,1280,1,1) | 0x01377e00 0x01417e00 0x000a0000
D RKNN: [17:53:26.794] 93 ConvExSwish model.12.cv2.conv.bias INT32 (512) | 0x01417e00 0x01418e00 0x00001000
D RKNN: [17:53:26.794] 94 Resize /model.13/Constant_1_output_0 FLOAT (0) | 0x029cfd00 0x029cfd00 0x00000000
D RKNN: [17:53:26.794] 94 Resize /model.13/Constant_output_0 FLOAT (4) | 0x029cfc00 0x029cfd00 0x00000100
D RKNN: [17:53:26.794] 96 ConvExSwish model.15.cv1.conv.weight INT8 (256,768,1,1) | 0x0177be00 0x017abe00 0x00030000
D RKNN: [17:53:26.794] 96 ConvExSwish model.15.cv1.conv.bias INT32 (256) | 0x017abe00 0x017ac600 0x00000800
D RKNN: [17:53:26.794] 97 Split /model.15/Split_split INT64 (2) | 0x029cfa40 0x029cfa50 0x00000010
D RKNN: [17:53:26.794] 98 ConvExSwish model.15.m.0.cv1.conv.weight INT8 (128,128,3,3) | 0x017d4e00 0x017f8e00 0x00024000
D RKNN: [17:53:26.794] 98 ConvExSwish model.15.m.0.cv1.conv.bias INT32 (128) | 0x017f8e00 0x017f9200 0x00000400
D RKNN: [17:53:26.794] 99 ConvExSwish model.15.m.0.cv2.conv.weight INT8 (128,128,3,3) | 0x017f9200 0x0181d200 0x00024000
D RKNN: [17:53:26.794] 99 ConvExSwish model.15.m.0.cv2.conv.bias INT32 (128) | 0x0181d200 0x0181d600 0x00000400
D RKNN: [17:53:26.794] 100 ConvExSwish model.15.m.1.cv1.conv.weight INT8 (128,128,3,3) | 0x0181d600 0x01841600 0x00024000
D RKNN: [17:53:26.794] 100 ConvExSwish model.15.m.1.cv1.conv.bias INT32 (128) | 0x01841600 0x01841a00 0x00000400
D RKNN: [17:53:26.794] 101 ConvExSwish model.15.m.1.cv2.conv.weight INT8 (128,128,3,3) | 0x01841a00 0x01865a00 0x00024000
D RKNN: [17:53:26.794] 101 ConvExSwish model.15.m.1.cv2.conv.bias INT32 (128) | 0x01865a00 0x01865e00 0x00000400
D RKNN: [17:53:26.794] 102 ConvExSwish model.15.m.2.cv1.conv.weight INT8 (128,128,3,3) | 0x01865e00 0x01889e00 0x00024000
D RKNN: [17:53:26.794] 102 ConvExSwish model.15.m.2.cv1.conv.bias INT32 (128) | 0x01889e00 0x0188a200 0x00000400
D RKNN: [17:53:26.794] 103 ConvExSwish model.15.m.2.cv2.conv.weight INT8 (128,128,3,3) | 0x0188a200 0x018ae200 0x00024000
D RKNN: [17:53:26.794] 103 ConvExSwish model.15.m.2.cv2.conv.bias INT32 (128) | 0x018ae200 0x018ae600 0x00000400
D RKNN: [17:53:26.794] 105 ConvExSwish model.15.cv2.conv.weight INT8 (256,640,1,1) | 0x017ac600 0x017d4600 0x00028000
D RKNN: [17:53:26.794] 105 ConvExSwish model.15.cv2.conv.bias INT32 (256) | 0x017d4600 0x017d4e00 0x00000800
D RKNN: [17:53:26.794] 106 ConvExSwish model.16.conv.weight INT8 (256,256,3,3) | 0x018ae600 0x0193e600 0x00090000
D RKNN: [17:53:26.794] 106 ConvExSwish model.16.conv.bias INT32 (256) | 0x0193e600 0x0193ee00 0x00000800
D RKNN: [17:53:26.794] 108 ConvExSwish model.22.cv2.0.0.conv.weight INT8 (64,256,3,3) | 0x02469e00 0x0248de00 0x00024000
D RKNN: [17:53:26.794] 108 ConvExSwish model.22.cv2.0.0.conv.bias INT32 (64) | 0x0248de00 0x0248e000 0x00000200
D RKNN: [17:53:26.794] 109 ConvExSwish model.22.cv3.0.0.conv.weight INT8 (256,256,3,3) | 0x0253d000 0x025cd000 0x00090000
D RKNN: [17:53:26.794] 109 ConvExSwish model.22.cv3.0.0.conv.bias INT32 (256) | 0x025cd000 0x025cd800 0x00000800
D RKNN: [17:53:26.794] 110 ConvExSwish model.18.cv1.conv.weight INT8 (512,768,1,1) | 0x0193ee00 0x0199ee00 0x00060000
D RKNN: [17:53:26.794] 110 ConvExSwish model.18.cv1.conv.bias INT32 (512) | 0x0199ee00 0x0199fe00 0x00001000
D RKNN: [17:53:26.794] 111 Split /model.18/Split_split INT64 (2) | 0x029cfa80 0x029cfa90 0x00000010
D RKNN: [17:53:26.794] 112 ConvExSwish model.22.cv2.0.1.conv.weight INT8 (64,64,3,3) | 0x0248e000 0x02497000 0x00009000
D RKNN: [17:53:26.794] 112 ConvExSwish model.22.cv2.0.1.conv.bias INT32 (64) | 0x02497000 0x02497200 0x00000200
D RKNN: [17:53:26.794] 113 Conv model.22.cv2.0.2.weight INT8 (64,64,1,1) | 0x02497200 0x02498200 0x00001000
D RKNN: [17:53:26.794] 113 Conv model.22.cv2.0.2.bias INT32 (64) | 0x02498200 0x02498400 0x00000200
D RKNN: [17:53:26.794] 115 ConvExSwish model.22.cv3.0.1.conv.weight INT8 (256,256,3,3) | 0x025cd800 0x0265d800 0x00090000
D RKNN: [17:53:26.794] 115 ConvExSwish model.22.cv3.0.1.conv.bias INT32 (256) | 0x0265d800 0x0265e000 0x00000800
D RKNN: [17:53:26.794] 116 ConvExSwish model.18.m.0.cv1.conv.weight INT8 (256,256,3,3) | 0x01a40e00 0x01ad0e00 0x00090000
D RKNN: [17:53:26.794] 116 ConvExSwish model.18.m.0.cv1.conv.bias INT32 (256) | 0x01ad0e00 0x01ad1600 0x00000800
D RKNN: [17:53:26.794] 117 ConvSigmoid model.22.cv3.0.2.weight INT8 (80,256,1,1) | 0x0265e000 0x02663000 0x00005000
D RKNN: [17:53:26.794] 117 ConvSigmoid model.22.cv3.0.2.bias INT32 (80) | 0x02663000 0x02663300 0x00000300
D RKNN: [17:53:26.794] 119 ConvExSwish model.18.m.0.cv2.conv.weight INT8 (256,256,3,3) | 0x01ad1600 0x01b61600 0x00090000
D RKNN: [17:53:26.794] 119 ConvExSwish model.18.m.0.cv2.conv.bias INT32 (256) | 0x01b61600 0x01b61e00 0x00000800
D RKNN: [17:53:26.794] 120 ConvClip /model.22/ReduceSum_2conv_i1 INT8 (1,80,1,1) | 0x029cfe80 0x029cff20 0x000000a0
D RKNN: [17:53:26.794] 120 ConvClip /model.22/ReduceSum_2conv_i1_bias_0 INT32 (1) | 0x029d0040 0x029d00c0 0x00000080
D RKNN: [17:53:26.794] 122 ConvExSwish model.18.m.1.cv1.conv.weight INT8 (256,256,3,3) | 0x01b61e00 0x01bf1e00 0x00090000
D RKNN: [17:53:26.794] 122 ConvExSwish model.18.m.1.cv1.conv.bias INT32 (256) | 0x01bf1e00 0x01bf2600 0x00000800
D RKNN: [17:53:26.794] 123 ConvExSwish model.18.m.1.cv2.conv.weight INT8 (256,256,3,3) | 0x01bf2600 0x01c82600 0x00090000
D RKNN: [17:53:26.794] 123 ConvExSwish model.18.m.1.cv2.conv.bias INT32 (256) | 0x01c82600 0x01c82e00 0x00000800
D RKNN: [17:53:26.794] 124 ConvExSwish model.18.m.2.cv1.conv.weight INT8 (256,256,3,3) | 0x01c82e00 0x01d12e00 0x00090000
D RKNN: [17:53:26.794] 124 ConvExSwish model.18.m.2.cv1.conv.bias INT32 (256) | 0x01d12e00 0x01d13600 0x00000800
D RKNN: [17:53:26.794] 125 ConvExSwish model.18.m.2.cv2.conv.weight INT8 (256,256,3,3) | 0x01d13600 0x01da3600 0x00090000
D RKNN: [17:53:26.794] 125 ConvExSwish model.18.m.2.cv2.conv.bias INT32 (256) | 0x01da3600 0x01da3e00 0x00000800
D RKNN: [17:53:26.794] 127 ConvExSwish model.18.cv2.conv.weight INT8 (512,1280,1,1) | 0x0199fe00 0x01a3fe00 0x000a0000
D RKNN: [17:53:26.794] 127 ConvExSwish model.18.cv2.conv.bias INT32 (512) | 0x01a3fe00 0x01a40e00 0x00001000
D RKNN: [17:53:26.794] 128 ConvExSwish model.19.conv.weight INT8 (512,512,3,3) | 0x01da3e00 0x01fe3e00 0x00240000
D RKNN: [17:53:26.794] 128 ConvExSwish model.19.conv.bias INT32 (512) | 0x01fe3e00 0x01fe4e00 0x00001000
D RKNN: [17:53:26.794] 130 ConvExSwish model.22.cv2.1.0.conv.weight INT8 (64,512,3,3) | 0x02498400 0x024e0400 0x00048000
D RKNN: [17:53:26.794] 130 ConvExSwish model.22.cv2.1.0.conv.bias INT32 (64) | 0x024e0400 0x024e0600 0x00000200
D RKNN: [17:53:26.794] 131 ConvExSwish model.22.cv3.1.0.conv.weight INT8 (256,512,3,3) | 0x02663300 0x02783300 0x00120000
D RKNN: [17:53:26.794] 131 ConvExSwish model.22.cv3.1.0.conv.bias INT32 (256) | 0x02783300 0x02783b00 0x00000800
D RKNN: [17:53:26.794] 132 ConvExSwish model.21.cv1.conv.weight INT8 (512,1024,1,1) | 0x01fe4e00 0x02064e00 0x00080000
D RKNN: [17:53:26.794] 132 ConvExSwish model.21.cv1.conv.bias INT32 (512) | 0x02064e00 0x02065e00 0x00001000
D RKNN: [17:53:26.794] 133 Split /model.21/Split_split INT64 (2) | 0x029cfac0 0x029cfad0 0x00000010
D RKNN: [17:53:26.794] 134 ConvExSwish model.22.cv2.1.1.conv.weight INT8 (64,64,3,3) | 0x024e0600 0x024e9600 0x00009000
D RKNN: [17:53:26.794] 134 ConvExSwish model.22.cv2.1.1.conv.bias INT32 (64) | 0x024e9600 0x024e9800 0x00000200
D RKNN: [17:53:26.794] 135 Conv model.22.cv2.1.2.weight INT8 (64,64,1,1) | 0x024e9800 0x024ea800 0x00001000
D RKNN: [17:53:26.794] 135 Conv model.22.cv2.1.2.bias INT32 (64) | 0x024ea800 0x024eaa00 0x00000200
D RKNN: [17:53:26.794] 137 ConvExSwish model.22.cv3.1.1.conv.weight INT8 (256,256,3,3) | 0x02783b00 0x02813b00 0x00090000
D RKNN: [17:53:26.794] 137 ConvExSwish model.22.cv3.1.1.conv.bias INT32 (256) | 0x02813b00 0x02814300 0x00000800
D RKNN: [17:53:26.794] 138 ConvExSwish model.21.m.0.cv1.conv.weight INT8 (256,256,3,3) | 0x02106e00 0x02196e00 0x00090000
D RKNN: [17:53:26.794] 138 ConvExSwish model.21.m.0.cv1.conv.bias INT32 (256) | 0x02196e00 0x02197600 0x00000800
D RKNN: [17:53:26.794] 139 ConvSigmoid model.22.cv3.1.2.weight INT8 (80,256,1,1) | 0x02814300 0x02819300 0x00005000
D RKNN: [17:53:26.794] 139 ConvSigmoid model.22.cv3.1.2.bias INT32 (80) | 0x02819300 0x02819600 0x00000300
D RKNN: [17:53:26.794] 141 ConvExSwish model.21.m.0.cv2.conv.weight INT8 (256,256,3,3) | 0x02197600 0x02227600 0x00090000
D RKNN: [17:53:26.794] 141 ConvExSwish model.21.m.0.cv2.conv.bias INT32 (256) | 0x02227600 0x02227e00 0x00000800
D RKNN: [17:53:26.794] 142 ConvClip /model.22/ReduceSum_1_2conv_i1 INT8 (1,80,1,1) | 0x029cfdc0 0x029cfe60 0x000000a0
D RKNN: [17:53:26.794] 142 ConvClip /model.22/ReduceSum_1_2conv_i1_bias_0 INT32 (1) | 0x029cffc0 0x029d0040 0x00000080
D RKNN: [17:53:26.794] 144 ConvExSwish model.21.m.1.cv1.conv.weight INT8 (256,256,3,3) | 0x02227e00 0x022b7e00 0x00090000
D RKNN: [17:53:26.794] 144 ConvExSwish model.21.m.1.cv1.conv.bias INT32 (256) | 0x022b7e00 0x022b8600 0x00000800
D RKNN: [17:53:26.794] 145 ConvExSwish model.21.m.1.cv2.conv.weight INT8 (256,256,3,3) | 0x022b8600 0x02348600 0x00090000
D RKNN: [17:53:26.794] 145 ConvExSwish model.21.m.1.cv2.conv.bias INT32 (256) | 0x02348600 0x02348e00 0x00000800
D RKNN: [17:53:26.794] 146 ConvExSwish model.21.m.2.cv1.conv.weight INT8 (256,256,3,3) | 0x02348e00 0x023d8e00 0x00090000
D RKNN: [17:53:26.794] 146 ConvExSwish model.21.m.2.cv1.conv.bias INT32 (256) | 0x023d8e00 0x023d9600 0x00000800
D RKNN: [17:53:26.794] 147 ConvExSwish model.21.m.2.cv2.conv.weight INT8 (256,256,3,3) | 0x023d9600 0x02469600 0x00090000
D RKNN: [17:53:26.794] 147 ConvExSwish model.21.m.2.cv2.conv.bias INT32 (256) | 0x02469600 0x02469e00 0x00000800
D RKNN: [17:53:26.794] 149 ConvExSwish model.21.cv2.conv.weight INT8 (512,1280,1,1) | 0x02065e00 0x02105e00 0x000a0000
D RKNN: [17:53:26.794] 149 ConvExSwish model.21.cv2.conv.bias INT32 (512) | 0x02105e00 0x02106e00 0x00001000
D RKNN: [17:53:26.794] 150 ConvExSwish model.22.cv2.2.0.conv.weight INT8 (64,512,3,3) | 0x024eaa00 0x02532a00 0x00048000
D RKNN: [17:53:26.794] 150 ConvExSwish model.22.cv2.2.0.conv.bias INT32 (64) | 0x02532a00 0x02532c00 0x00000200
D RKNN: [17:53:26.794] 151 ConvExSwish model.22.cv3.2.0.conv.weight INT8 (256,512,3,3) | 0x02819600 0x02939600 0x00120000
D RKNN: [17:53:26.794] 151 ConvExSwish model.22.cv3.2.0.conv.bias INT32 (256) | 0x02939600 0x02939e00 0x00000800
D RKNN: [17:53:26.794] 152 ConvExSwish model.22.cv2.2.1.conv.weight INT8 (64,64,3,3) | 0x02532c00 0x0253bc00 0x00009000
D RKNN: [17:53:26.794] 152 ConvExSwish model.22.cv2.2.1.conv.bias INT32 (64) | 0x0253bc00 0x0253be00 0x00000200
D RKNN: [17:53:26.794] 153 Conv model.22.cv2.2.2.weight INT8 (64,64,1,1) | 0x0253be00 0x0253ce00 0x00001000
D RKNN: [17:53:26.794] 153 Conv model.22.cv2.2.2.bias INT32 (64) | 0x0253ce00 0x0253d000 0x00000200
D RKNN: [17:53:26.794] 155 ConvExSwish model.22.cv3.2.1.conv.weight INT8 (256,256,3,3) | 0x02939e00 0x029c9e00 0x00090000
D RKNN: [17:53:26.794] 155 ConvExSwish model.22.cv3.2.1.conv.bias INT32 (256) | 0x029c9e00 0x029ca600 0x00000800
D RKNN: [17:53:26.794] 156 ConvSigmoid model.22.cv3.2.2.weight INT8 (80,256,1,1) | 0x029ca600 0x029cf600 0x00005000
D RKNN: [17:53:26.794] 156 ConvSigmoid model.22.cv3.2.2.bias INT32 (80) | 0x029cf600 0x029cf900 0x00000300
D RKNN: [17:53:26.794] 158 ConvClip /model.22/ReduceSum_2_2conv_i1 INT8 (1,80,1,1) | 0x029cfd00 0x029cfda0 0x000000a0
D RKNN: [17:53:26.794] 158 ConvClip /model.22/ReduceSum_2_2conv_i1_bias_0 INT32 (1) | 0x029cff40 0x029cffc0 0x00000080
D RKNN: [17:53:26.794] -------------------------------------------------------------------------------+---------------------------------
D RKNN: [17:53:26.828] ----------------------------------------
D RKNN: [17:53:26.828] Total Internal Memory Size: 16000KB
D RKNN: [17:53:26.828] Total Weight Memory Size: 42818.2KB
D RKNN: [17:53:26.828] ----------------------------------------
D RKNN: [17:53:26.828] <<<<<<<< end: rknn::RKNNMemStatisticsPass