Open deimsdeutsch opened 4 years ago
Are you sure your using the latest repo ?
@AlexeyAB I am using the latest repo. Am i doing something wrong ? I don't understand.
@deimsdeutsch Delete old Darknet library. And re-compile Darknet with LIBSO=1.
@AlexeyAB I got similar issue,
I cloned latest repo to a new folder and change "LIBSO = 0" to "LIBSO = 1" in makefile then compiled it.
but still got
Unused field: 'uc_normalizer = 0.07'
Unused field: 'beta1 = 0.6'
command :
darknet.exe detector train data.data csresnext50-panet-spp-original-optimal.cfg -map -gpus 0,1
log :
CUDA-version: 10000 (10010) Warning: CUDA-version is lower than Driver-version! , cuDNN: 7.6.1, CUDNN_HALF=1, GPU count: 2 OpenCV version: 4.1.0 0,1 Prepare additional network for mAP calculation... compute_capability = 750, cudnn_half = 1 net.optimized_memory = 0 batch = 1, time_steps = 1, train = 0 layer filters size/strd(dil) input output 0 conv 64 7 x 7/ 2 128 x 128 x 3 -> 64 x 64 x 64 0.077 BF 1 max 2x 2/ 2 64 x 64 x 64 -> 32 x 32 x 64 0.000 BF 2 conv 128 1 x 1/ 1 32 x 32 x 64 -> 32 x 32 x 128 0.017 BF 3 route 1 -> 32 x 32 x 64 4 conv 64 1 x 1/ 1 32 x 32 x 64 -> 32 x 32 x 64 0.008 BF 5 conv 128 1 x 1/ 1 32 x 32 x 64 -> 32 x 32 x 128 0.017 BF 6 conv 128/ 32 3 x 3/ 1 32 x 32 x 128 -> 32 x 32 x 128 0.009 BF 7 conv 128 1 x 1/ 1 32 x 32 x 128 -> 32 x 32 x 128 0.034 BF 8 Shortcut Layer: 4, wt = 0, wn = 0, outputs: 32 x 32 x 128 0.000 BF ( 32 x 32 x 128) + ( 32 x 32 x 64) 9 conv 128 1 x 1/ 1 32 x 32 x 128 -> 32 x 32 x 128 0.034 BF 10 conv 128/ 32 3 x 3/ 1 32 x 32 x 128 -> 32 x 32 x 128 0.009 BF 11 conv 128 1 x 1/ 1 32 x 32 x 128 -> 32 x 32 x 128 0.034 BF 12 Shortcut Layer: 8, wt = 0, wn = 0, outputs: 32 x 32 x 128 0.000 BF 13 conv 128 1 x 1/ 1 32 x 32 x 128 -> 32 x 32 x 128 0.034 BF 14 conv 128/ 32 3 x 3/ 1 32 x 32 x 128 -> 32 x 32 x 128 0.009 BF 15 conv 128 1 x 1/ 1 32 x 32 x 128 -> 32 x 32 x 128 0.034 BF 16 Shortcut Layer: 12, wt = 0, wn = 0, outputs: 32 x 32 x 128 0.000 BF 17 conv 128 1 x 1/ 1 32 x 32 x 128 -> 32 x 32 x 128 0.034 BF 18 route 17 2 -> 32 x 32 x 256 19 conv 256 1 x 1/ 1 32 x 32 x 256 -> 32 x 32 x 256 0.134 BF 20 conv 256/ 32 3 x 3/ 2 32 x 32 x 256 -> 16 x 16 x 256 0.009 BF 21 conv 256 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 256 0.034 BF 22 route 20 -> 16 x 16 x 256 23 conv 256 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 256 0.034 BF 24 conv 256 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 256 0.034 BF 25 conv 256/ 32 3 x 3/ 1 16 x 16 x 256 -> 16 x 16 x 256 0.009 BF 26 conv 256 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 256 0.034 BF 27 Shortcut Layer: 23, wt = 0, wn = 0, outputs: 16 x 16 x 256 0.000 BF 28 conv 256 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 256 0.034 BF 29 conv 256/ 32 3 x 3/ 1 16 x 16 x 256 -> 16 x 16 x 256 0.009 BF 30 conv 256 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 256 0.034 BF 31 Shortcut Layer: 27, wt = 0, wn = 0, outputs: 16 x 16 x 256 0.000 BF 32 conv 256 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 256 0.034 BF 33 conv 256/ 32 3 x 3/ 1 16 x 16 x 256 -> 16 x 16 x 256 0.009 BF 34 conv 256 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 256 0.034 BF 35 Shortcut Layer: 31, wt = 0, wn = 0, outputs: 16 x 16 x 256 0.000 BF 36 conv 256 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 256 0.034 BF 37 route 36 21 -> 16 x 16 x 512 38 conv 512 1 x 1/ 1 16 x 16 x 512 -> 16 x 16 x 512 0.134 BF 39 conv 512/ 32 3 x 3/ 2 16 x 16 x 512 -> 8 x 8 x 512 0.009 BF 40 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 41 route 39 -> 8 x 8 x 512 42 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 43 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 44 conv 512/ 32 3 x 3/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.009 BF 45 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 46 Shortcut Layer: 42, wt = 0, wn = 0, outputs: 8 x 8 x 512 0.000 BF 47 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 48 conv 512/ 32 3 x 3/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.009 BF 49 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 50 Shortcut Layer: 46, wt = 0, wn = 0, outputs: 8 x 8 x 512 0.000 BF 51 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 52 conv 512/ 32 3 x 3/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.009 BF 53 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 54 Shortcut Layer: 50, wt = 0, wn = 0, outputs: 8 x 8 x 512 0.000 BF 55 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 56 conv 512/ 32 3 x 3/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.009 BF 57 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 58 Shortcut Layer: 54, wt = 0, wn = 0, outputs: 8 x 8 x 512 0.000 BF 59 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 60 conv 512/ 32 3 x 3/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.009 BF 61 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 62 Shortcut Layer: 58, wt = 0, wn = 0, outputs: 8 x 8 x 512 0.000 BF 63 conv 512 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 512 0.034 BF 64 route 63 40 -> 8 x 8 x1024 65 conv 1024 1 x 1/ 1 8 x 8 x1024 -> 8 x 8 x1024 0.134 BF 66 conv 1024/ 32 3 x 3/ 2 8 x 8 x1024 -> 4 x 4 x1024 0.009 BF 67 conv 1024 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x1024 0.034 BF 68 route 66 -> 4 x 4 x1024 69 conv 1024 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x1024 0.034 BF 70 conv 1024 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x1024 0.034 BF 71 conv 1024/ 32 3 x 3/ 1 4 x 4 x1024 -> 4 x 4 x1024 0.009 BF 72 conv 1024 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x1024 0.034 BF 73 Shortcut Layer: 69, wt = 0, wn = 0, outputs: 4 x 4 x1024 0.000 BF 74 conv 1024 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x1024 0.034 BF 75 conv 1024/ 32 3 x 3/ 1 4 x 4 x1024 -> 4 x 4 x1024 0.009 BF 76 conv 1024 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x1024 0.034 BF 77 Shortcut Layer: 73, wt = 0, wn = 0, outputs: 4 x 4 x1024 0.000 BF 78 conv 1024 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x1024 0.034 BF 79 route 78 67 -> 4 x 4 x2048 80 conv 2048 1 x 1/ 1 4 x 4 x2048 -> 4 x 4 x2048 0.134 BF 81 conv 512 1 x 1/ 1 4 x 4 x2048 -> 4 x 4 x 512 0.034 BF 82 conv 1024 3 x 3/ 1 4 x 4 x 512 -> 4 x 4 x1024 0.151 BF 83 conv 512 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x 512 0.017 BF 84 max 5x 5/ 1 4 x 4 x 512 -> 4 x 4 x 512 0.000 BF 85 route 83 -> 4 x 4 x 512 86 max 9x 9/ 1 4 x 4 x 512 -> 4 x 4 x 512 0.001 BF 87 route 83 -> 4 x 4 x 512 88 max 13x13/ 1 4 x 4 x 512 -> 4 x 4 x 512 0.001 BF 89 route 88 86 84 83 -> 4 x 4 x2048 90 conv 512 1 x 1/ 1 4 x 4 x2048 -> 4 x 4 x 512 0.034 BF 91 conv 1024 3 x 3/ 1 4 x 4 x 512 -> 4 x 4 x1024 0.151 BF 92 conv 512 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x 512 0.017 BF 93 conv 256 1 x 1/ 1 4 x 4 x 512 -> 4 x 4 x 256 0.004 BF 94 upsample 2x 4 x 4 x 256 -> 8 x 8 x 256 95 route 65 -> 8 x 8 x1024 96 conv 256 1 x 1/ 1 8 x 8 x1024 -> 8 x 8 x 256 0.034 BF 97 route 96 94 -> 8 x 8 x 512 98 conv 256 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 256 0.017 BF 99 conv 512 3 x 3/ 1 8 x 8 x 256 -> 8 x 8 x 512 0.151 BF 100 conv 256 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 256 0.017 BF 101 conv 512 3 x 3/ 1 8 x 8 x 256 -> 8 x 8 x 512 0.151 BF 102 conv 256 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 256 0.017 BF 103 conv 128 1 x 1/ 1 8 x 8 x 256 -> 8 x 8 x 128 0.004 BF 104 upsample 2x 8 x 8 x 128 -> 16 x 16 x 128 105 route 38 -> 16 x 16 x 512 106 conv 128 1 x 1/ 1 16 x 16 x 512 -> 16 x 16 x 128 0.034 BF 107 route 106 104 -> 16 x 16 x 256 108 conv 128 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 128 0.017 BF 109 conv 256 3 x 3/ 1 16 x 16 x 128 -> 16 x 16 x 256 0.151 BF 110 conv 128 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 128 0.017 BF 111 conv 256 3 x 3/ 1 16 x 16 x 128 -> 16 x 16 x 256 0.151 BF 112 conv 128 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 128 0.017 BF 113 conv 256 3 x 3/ 1 16 x 16 x 128 -> 16 x 16 x 256 0.151 BF 114 conv 21 1 x 1/ 1 16 x 16 x 256 -> 16 x 16 x 21 0.003 BF 115 yolo [yolo] params: iou loss: ciou (4), iou_norm: 0.07, cls_norm: 1.00, scale_x_y: 1.20 nms_kind: greedynms (1), beta = 0.600000 Unused field: 'uc_normalizer = 0.07' Unused field: 'beta1 = 0.6' 116 route 112 -> 16 x 16 x 128 117 conv 256 3 x 3/ 2 16 x 16 x 128 -> 8 x 8 x 256 0.038 BF 118 route 117 102 -> 8 x 8 x 512 119 conv 256 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 256 0.017 BF 120 conv 512 3 x 3/ 1 8 x 8 x 256 -> 8 x 8 x 512 0.151 BF 121 conv 256 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 256 0.017 BF 122 conv 512 3 x 3/ 1 8 x 8 x 256 -> 8 x 8 x 512 0.151 BF 123 conv 256 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 256 0.017 BF 124 conv 512 3 x 3/ 1 8 x 8 x 256 -> 8 x 8 x 512 0.151 BF 125 conv 21 1 x 1/ 1 8 x 8 x 512 -> 8 x 8 x 21 0.001 BF 126 yolo [yolo] params: iou loss: ciou (4), iou_norm: 0.07, cls_norm: 1.00, scale_x_y: 1.10 nms_kind: greedynms (1), beta = 0.600000 Unused field: 'uc_normalizer = 0.07' Unused field: 'beta1 = 0.6' 127 route 123 -> 8 x 8 x 256 128 conv 512 3 x 3/ 2 8 x 8 x 256 -> 4 x 4 x 512 0.038 BF 129 route 128 92 -> 4 x 4 x1024 130 conv 512 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x 512 0.017 BF 131 conv 1024 3 x 3/ 1 4 x 4 x 512 -> 4 x 4 x1024 0.151 BF 132 conv 512 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x 512 0.017 BF 133 conv 1024 3 x 3/ 1 4 x 4 x 512 -> 4 x 4 x1024 0.151 BF 134 conv 512 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x 512 0.017 BF 135 conv 1024 3 x 3/ 1 4 x 4 x 512 -> 4 x 4 x1024 0.151 BF 136 conv 21 1 x 1/ 1 4 x 4 x1024 -> 4 x 4 x 21 0.001 BF 137 yolo [yolo] params: iou loss: ciou (4), iou_norm: 0.07, cls_norm: 1.00, scale_x_y: 1.05 nms_kind: greedynms (1), beta = 0.600000 Unused field: 'uc_normalizer = 0.07' Unused field: 'beta1 = 0.6' Total BFLOPS 4.405 avg_outputs = 48809 Allocate additional workspace_size = 52.43 MB
@phonygene
Unused field: 'uc_normalizer = 0.07' Unused field: 'beta1 = 0.6'
This is normal.
I am using the latest repo.
The following errors are not coming via ./darknet detector demo command line option. The following errors are happening when i load the code by making instance of the
Detector class.