Darknet: Not detecting with my own weights

Created on 8 Jun 2019  路  8Comments  路  Source: AlexeyAB/darknet

Guys I did train for 3 classes of objects and got 4000 iterations following: https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects , the graph saturated and
I did save the weights to backup/yolov3-tiny_4000.weights
So I assume this was oki.

But when I try to use it in order to detect images it fails:

./darknet detect cfg/yolo-obj.cfg backup/yolov3-tiny_4000.weights /home/imanewbie/Source/lab_serpro/darknet-AlexeyAB/darknet/data/x64/Release/data/img/0001964-88.2018.4.03.6301_180.jpg -i 0 --tresh 0.5
layer     filters    size              input                output
   0 conv     32  3 x 3 / 1   416 x 416 x   3   ->   416 x 416 x  32 0.299 BF
   1 conv     64  3 x 3 / 2   416 x 416 x  32   ->   208 x 208 x  64 1.595 BF
   2 conv     32  1 x 1 / 1   208 x 208 x  64   ->   208 x 208 x  32 0.177 BF
   3 conv     64  3 x 3 / 1   208 x 208 x  32   ->   208 x 208 x  64 1.595 BF
   4 Shortcut Layer: 1
   5 conv    128  3 x 3 / 2   208 x 208 x  64   ->   104 x 104 x 128 1.595 BF
   6 conv     64  1 x 1 / 1   104 x 104 x 128   ->   104 x 104 x  64 0.177 BF
   7 conv    128  3 x 3 / 1   104 x 104 x  64   ->   104 x 104 x 128 1.595 BF
   8 Shortcut Layer: 5
   9 conv     64  1 x 1 / 1   104 x 104 x 128   ->   104 x 104 x  64 0.177 BF
  10 conv    128  3 x 3 / 1   104 x 104 x  64   ->   104 x 104 x 128 1.595 BF
  11 Shortcut Layer: 8
  12 conv    256  3 x 3 / 2   104 x 104 x 128   ->    52 x  52 x 256 1.595 BF
  13 conv    128  1 x 1 / 1    52 x  52 x 256   ->    52 x  52 x 128 0.177 BF
  14 conv    256  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x 256 1.595 BF
  15 Shortcut Layer: 12
  16 conv    128  1 x 1 / 1    52 x  52 x 256   ->    52 x  52 x 128 0.177 BF
  17 conv    256  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x 256 1.595 BF
  18 Shortcut Layer: 15
  19 conv    128  1 x 1 / 1    52 x  52 x 256   ->    52 x  52 x 128 0.177 BF
  20 conv    256  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x 256 1.595 BF
  21 Shortcut Layer: 18
  22 conv    128  1 x 1 / 1    52 x  52 x 256   ->    52 x  52 x 128 0.177 BF
  23 conv    256  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x 256 1.595 BF
  24 Shortcut Layer: 21
  25 conv    128  1 x 1 / 1    52 x  52 x 256   ->    52 x  52 x 128 0.177 BF
  26 conv    256  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x 256 1.595 BF
  27 Shortcut Layer: 24
  28 conv    128  1 x 1 / 1    52 x  52 x 256   ->    52 x  52 x 128 0.177 BF
  29 conv    256  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x 256 1.595 BF
  30 Shortcut Layer: 27
  31 conv    128  1 x 1 / 1    52 x  52 x 256   ->    52 x  52 x 128 0.177 BF
  32 conv    256  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x 256 1.595 BF
  33 Shortcut Layer: 30
  34 conv    128  1 x 1 / 1    52 x  52 x 256   ->    52 x  52 x 128 0.177 BF
  35 conv    256  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x 256 1.595 BF
  36 Shortcut Layer: 33
  37 conv    512  3 x 3 / 2    52 x  52 x 256   ->    26 x  26 x 512 1.595 BF
  38 conv    256  1 x 1 / 1    26 x  26 x 512   ->    26 x  26 x 256 0.177 BF
  39 conv    512  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 512 1.595 BF
  40 Shortcut Layer: 37
  41 conv    256  1 x 1 / 1    26 x  26 x 512   ->    26 x  26 x 256 0.177 BF
  42 conv    512  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 512 1.595 BF
  43 Shortcut Layer: 40
  44 conv    256  1 x 1 / 1    26 x  26 x 512   ->    26 x  26 x 256 0.177 BF
  45 conv    512  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 512 1.595 BF
  46 Shortcut Layer: 43
  47 conv    256  1 x 1 / 1    26 x  26 x 512   ->    26 x  26 x 256 0.177 BF
  48 conv    512  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 512 1.595 BF
  49 Shortcut Layer: 46
  50 conv    256  1 x 1 / 1    26 x  26 x 512   ->    26 x  26 x 256 0.177 BF
  51 conv    512  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 512 1.595 BF
  52 Shortcut Layer: 49
  53 conv    256  1 x 1 / 1    26 x  26 x 512   ->    26 x  26 x 256 0.177 BF
  54 conv    512  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 512 1.595 BF
  55 Shortcut Layer: 52
  56 conv    256  1 x 1 / 1    26 x  26 x 512   ->    26 x  26 x 256 0.177 BF
  57 conv    512  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 512 1.595 BF
  58 Shortcut Layer: 55
  59 conv    256  1 x 1 / 1    26 x  26 x 512   ->    26 x  26 x 256 0.177 BF
  60 conv    512  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 512 1.595 BF
  61 Shortcut Layer: 58
  62 conv   1024  3 x 3 / 2    26 x  26 x 512   ->    13 x  13 x1024 1.595 BF
  63 conv    512  1 x 1 / 1    13 x  13 x1024   ->    13 x  13 x 512 0.177 BF
  64 conv   1024  3 x 3 / 1    13 x  13 x 512   ->    13 x  13 x1024 1.595 BF
  65 Shortcut Layer: 62
  66 conv    512  1 x 1 / 1    13 x  13 x1024   ->    13 x  13 x 512 0.177 BF
  67 conv   1024  3 x 3 / 1    13 x  13 x 512   ->    13 x  13 x1024 1.595 BF
  68 Shortcut Layer: 65
  69 conv    512  1 x 1 / 1    13 x  13 x1024   ->    13 x  13 x 512 0.177 BF
  70 conv   1024  3 x 3 / 1    13 x  13 x 512   ->    13 x  13 x1024 1.595 BF
  71 Shortcut Layer: 68
  72 conv    512  1 x 1 / 1    13 x  13 x1024   ->    13 x  13 x 512 0.177 BF
  73 conv   1024  3 x 3 / 1    13 x  13 x 512   ->    13 x  13 x1024 1.595 BF
  74 Shortcut Layer: 71
  75 conv    512  1 x 1 / 1    13 x  13 x1024   ->    13 x  13 x 512 0.177 BF
  76 conv   1024  3 x 3 / 1    13 x  13 x 512   ->    13 x  13 x1024 1.595 BF
  77 conv    512  1 x 1 / 1    13 x  13 x1024   ->    13 x  13 x 512 0.177 BF
  78 conv   1024  3 x 3 / 1    13 x  13 x 512   ->    13 x  13 x1024 1.595 BF
  79 conv    512  1 x 1 / 1    13 x  13 x1024   ->    13 x  13 x 512 0.177 BF
  80 conv   1024  3 x 3 / 1    13 x  13 x 512   ->    13 x  13 x1024 1.595 BF
  81 conv     24  1 x 1 / 1    13 x  13 x1024   ->    13 x  13 x  24 0.008 BF
  82 yolo
[yolo] params: iou loss: mse, iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00
  83 route  79
  84 conv    256  1 x 1 / 1    13 x  13 x 512   ->    13 x  13 x 256 0.044 BF
  85 upsample            2x    13 x  13 x 256   ->    26 x  26 x 256
  86 route  85 61
  87 conv    256  1 x 1 / 1    26 x  26 x 768   ->    26 x  26 x 256 0.266 BF
  88 conv    512  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 512 1.595 BF
  89 conv    256  1 x 1 / 1    26 x  26 x 512   ->    26 x  26 x 256 0.177 BF
  90 conv    512  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 512 1.595 BF
  91 conv    256  1 x 1 / 1    26 x  26 x 512   ->    26 x  26 x 256 0.177 BF
  92 conv    512  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 512 1.595 BF
  93 conv     24  1 x 1 / 1    26 x  26 x 512   ->    26 x  26 x  24 0.017 BF
  94 yolo
[yolo] params: iou loss: mse, iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00
  95 route  91
  96 conv    128  1 x 1 / 1    26 x  26 x 256   ->    26 x  26 x 128 0.044 BF
  97 upsample            2x    26 x  26 x 128   ->    52 x  52 x 128
  98 route  97 36
  99 conv    128  1 x 1 / 1    52 x  52 x 384   ->    52 x  52 x 128 0.266 BF
 100 conv    256  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x 256 1.595 BF
 101 conv    128  1 x 1 / 1    52 x  52 x 256   ->    52 x  52 x 128 0.177 BF
 102 conv    256  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x 256 1.595 BF
 103 conv    128  1 x 1 / 1    52 x  52 x 256   ->    52 x  52 x 128 0.177 BF
 104 conv    256  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x 256 1.595 BF
 105 conv     24  1 x 1 / 1    52 x  52 x 256   ->    52 x  52 x  24 0.033 BF
 106 yolo
[yolo] params: iou loss: mse, iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00
Total BFLOPS 65.304 
 Allocate additional workspace_size = 52.43 MB 
Loading weights from backup/yolov3-tiny_4000.weights...
 seen 64 
Done!
/home/imanewbie/Source/lab_serpro/darknet-AlexeyAB/darknet/data/x64/Release/data/img/0001964-88.2018.4.03.6301_180.jpg: Predicted in 52.175000 milli-seconds

I dont even grasp what is this seen 64. The images I tested again are into my defined classes so I would expect a true detection. What am I missing?

Solved
Source
picture vfbsilva

Most helpful comment

@AlexeyAB Sorry my mistake, I'm from germany and here stands billion for 10^12. xD

picture phamngocthanhtrung on 12 Jun 2019
😄1 👍1

All 8 comments

What mAP do you get?

AlexeyAB picture AlexeyAB on 8 Jun 2019

On the end it did work. I believe I goofed some config file on my first attempt.
CUDA allocate done!

calculation mAP (mean average precision)...

detections_count = 308, unique_truth_count = 18
rank = 0 of ranks = 308
rank = 100 of ranks = 308
rank = 200 of ranks = 308
rank = 300 of ranks = 308
class_id = 0, name = rgfrente, ap = 87.50% (TP = 7, FP = 2)
class_id = 1, name = rgverso, ap = 100.00% (TP = 8, FP = 1)
class_id = 2, name = cnh, ap = 100.00% (TP = 2, FP = 0)

for conf_thresh = 0.25, precision = 0.85, recall = 0.94, F1-score = 0.89
for conf_thresh = 0.25, TP = 17, FP = 3, FN = 1, average IoU = 69.43 %

IoU threshold = 50 %, used Area-Under-Curve for each unique Recall
mean average precision ([email protected]) = 0.958333, or 95.83 %

Set -points flag:
-points 101 for MS COCO
-points 11 for PascalVOC 2007 (uncomment difficult in voc.data)
-points 0 (AUC) for ImageNet, PascalVOC 2010-2012, your custom dataset

mean_average_precision ([email protected]) = 0.958333

vfbsilva picture vfbsilva on 10 Jun 2019

It is very good result!

AlexeyAB picture AlexeyAB on 10 Jun 2019

@AlexeyAB can you tell me what BF means?

phamngocthanhtrung picture phamngocthanhtrung on 11 Jun 2019

@phamngocthanhtrung
gigaFLOPS: https://en.wikipedia.org/wiki/FLOPS

AlexeyAB picture AlexeyAB on 11 Jun 2019
👍1

@AlexeyAB thank you, at first I thought that B stands for billion and therefore means TeraFlops.

phamngocthanhtrung picture phamngocthanhtrung on 12 Jun 2019

@phamngocthanhtrung
Yes,
BFLOPS = billions flops = gigaFLOPS = 1 000 000 000

AlexeyAB picture AlexeyAB on 12 Jun 2019

@AlexeyAB Sorry my mistake, I'm from germany and here stands billion for 10^12. xD

phamngocthanhtrung picture phamngocthanhtrung on 12 Jun 2019
😄1 👍1
Was this page helpful?
0 / 5 - 0 ratings

Related issues

Mididou picture Mididou  路  3Comments
louisondumont picture louisondumont  路  3Comments
Cipusha picture Cipusha  路  3Comments
Jacky3213 picture Jacky3213  路  3Comments
hemp110 picture hemp110  路  3Comments