yolov3 training updated code from repo

[samueldedavid]

.\darknet.exe detector train data/omid.data cfg/yolov3Tumor.cfg.txt weights/darknet19_448.conv.23.weights -map yolov3Tumor layer filters size input output 0 conv 32 3 x 3 / 1 800 x 800 x 3 -> 800 x 800 x 32 1 conv 64 3 x 3 / 2 800 x 800 x 32 -> 400 x 400 x 64 2 conv 32 1 x 1 / 1 400 x 400 x 64 -> 400 x 400 x 32 3 conv 64 3 x 3 / 1 400 x 400 x 32 -> 400 x 400 x 64 4 Shortcut Layer: 1 5 conv 128 3 x 3 / 2 400 x 400 x 64 -> 200 x 200 x 128 6 conv 64 1 x 1 / 1 200 x 200 x 128 -> 200 x 200 x 64 7 conv 128 3 x 3 / 1 200 x 200 x 64 -> 200 x 200 x 128 8 Shortcut Layer: 5 9 conv 64 1 x 1 / 1 200 x 200 x 128 -> 200 x 200 x 64 10 conv 128 3 x 3 / 1 200 x 200 x 64 -> 200 x 200 x 128 11 Shortcut Layer: 8 12 conv 256 3 x 3 / 2 200 x 200 x 128 -> 100 x 100 x 256 13 conv 128 1 x 1 / 1 100 x 100 x 256 -> 100 x 100 x 128 14 conv 256 3 x 3 / 1 100 x 100 x 128 -> 100 x 100 x 256 15 Shortcut Layer: 12 16 conv 128 1 x 1 / 1 100 x 100 x 256 -> 100 x 100 x 128 17 conv 256 3 x 3 / 1 100 x 100 x 128 -> 100 x 100 x 256 18 Shortcut Layer: 15 19 conv 128 1 x 1 / 1 100 x 100 x 256 -> 100 x 100 x 128 20 conv 256 3 x 3 / 1 100 x 100 x 128 -> 100 x 100 x 256 21 Shortcut Layer: 18 22 conv 128 1 x 1 / 1 100 x 100 x 256 -> 100 x 100 x 128 23 conv 256 3 x 3 / 1 100 x 100 x 128 -> 100 x 100 x 256 24 Shortcut Layer: 21 25 conv 128 1 x 1 / 1 100 x 100 x 256 -> 100 x 100 x 128 26 conv 256 3 x 3 / 1 100 x 100 x 128 -> 100 x 100 x 256 27 Shortcut Layer: 24 28 conv 128 1 x 1 / 1 100 x 100 x 256 -> 100 x 100 x 128 29 conv 256 3 x 3 / 1 100 x 100 x 128 -> 100 x 100 x 256 30 Shortcut Layer: 27 31 conv 128 1 x 1 / 1 100 x 100 x 256 -> 100 x 100 x 128 32 conv 256 3 x 3 / 1 100 x 100 x 128 -> 100 x 100 x 256 33 Shortcut Layer: 30 34 conv 128 1 x 1 / 1 100 x 100 x 256 -> 100 x 100 x 128 35 conv 256 3 x 3 / 1 100 x 100 x 128 -> 100 x 100 x 256 36 Shortcut Layer: 33 37 conv 512 3 x 3 / 2 100 x 100 x 256 -> 50 x 50 x 512 38 conv 256 1 x 1 / 1 50 x 50 x 512 -> 50 x 50 x 256 39 conv 512 3 x 3 / 1 50 x 50 x 256 -> 50 x 50 x 512 40 Shortcut Layer: 37 41 conv 256 1 x 1 / 1 50 x 50 x 512 -> 50 x 50 x 256 42 conv 512 3 x 3 / 1 50 x 50 x 256 -> 50 x 50 x 512 43 Shortcut Layer: 40 44 conv 256 1 x 1 / 1 50 x 50 x 512 -> 50 x 50 x 256 45 conv 512 3 x 3 / 1 50 x 50 x 256 -> 50 x 50 x 512 46 Shortcut Layer: 43 47 conv 256 1 x 1 / 1 50 x 50 x 512 -> 50 x 50 x 256 48 conv 512 3 x 3 / 1 50 x 50 x 256 -> 50 x 50 x 512 49 Shortcut Layer: 46 50 conv 256 1 x 1 / 1 50 x 50 x 512 -> 50 x 50 x 256 51 conv 512 3 x 3 / 1 50 x 50 x 256 -> 50 x 50 x 512 52 Shortcut Layer: 49 53 conv 256 1 x 1 / 1 50 x 50 x 512 -> 50 x 50 x 256 54 conv 512 3 x 3 / 1 50 x 50 x 256 -> 50 x 50 x 512 55 Shortcut Layer: 52 56 conv 256 1 x 1 / 1 50 x 50 x 512 -> 50 x 50 x 256 57 conv 512 3 x 3 / 1 50 x 50 x 256 -> 50 x 50 x 512 58 Shortcut Layer: 55 59 conv 256 1 x 1 / 1 50 x 50 x 512 -> 50 x 50 x 256 60 conv 512 3 x 3 / 1 50 x 50 x 256 -> 50 x 50 x 512 61 Shortcut Layer: 58 62 conv 1024 3 x 3 / 2 50 x 50 x 512 -> 25 x 25 x1024 63 conv 512 1 x 1 / 1 25 x 25 x1024 -> 25 x 25 x 512 64 conv 1024 3 x 3 / 1 25 x 25 x 512 -> 25 x 25 x1024 65 Shortcut Layer: 62 66 conv 512 1 x 1 / 1 25 x 25 x1024 -> 25 x 25 x 512 67 conv 1024 3 x 3 / 1 25 x 25 x 512 -> 25 x 25 x1024 68 Shortcut Layer: 65 69 conv 512 1 x 1 / 1 25 x 25 x1024 -> 25 x 25 x 512 70 conv 1024 3 x 3 / 1 25 x 25 x 512 -> 25 x 25 x1024 71 Shortcut Layer: 68 72 conv 512 1 x 1 / 1 25 x 25 x1024 -> 25 x 25 x 512 73 conv 1024 3 x 3 / 1 25 x 25 x 512 -> 25 x 25 x1024 74 Shortcut Layer: 71 75 conv 512 1 x 1 / 1 25 x 25 x1024 -> 25 x 25 x 512 76 conv 1024 3 x 3 / 1 25 x 25 x 512 -> 25 x 25 x1024 77 conv 512 1 x 1 / 1 25 x 25 x1024 -> 25 x 25 x 512 78 conv 1024 3 x 3 / 1 25 x 25 x 512 -> 25 x 25 x1024 79 conv 512 1 x 1 / 1 25 x 25 x1024 -> 25 x 25 x 512 80 conv 1024 3 x 3 / 1 25 x 25 x 512 -> 25 x 25 x1024 81 conv 21 1 x 1 / 1 25 x 25 x1024 -> 25 x 25 x 21 82 Type not recognized: [yolo] Unused field: 'mask = 6,7,8' Unused field: 'anchors = 10,13,16,30,33,23,30,61,62,45,59,119,116,90,156,198,373,326' Unused field: 'classes = 2' Unused field: 'num = 9' Unused field: 'jitter = .3' Unused field: 'ignore_thresh = .5' Unused field: 'truth_thresh = 1' Unused field: 'random = 1' 83 route 79 84 conv 256 1 x 1 / 1 25 x 25 x 512 -> 25 x 25 x 256 85 Type not recognized: [upsample] Unused field: 'stride = 2' 86 route 85 61 87 Layer before convolutional layer must output image.: No error yolov3Tumor.cfg.txt

I am training yolo for two classes and getting error like this . I cloned the repo a week ago . The previous post says to update the code so I believe I am using the latest code . Please advise .

[AlexeyAB]

@samueldedavid Hi,

• Do you use this repository? https://github.com/AlexeyAB/darknet

• Did you download it using git clone or using zip-archive?

• I successfully ran darknet with your cfg-file: darknet detector test cfg/coco.data yolov3Tumor.cfg

[samueldedavid]

Sorry , i checked it was from other repository.