search

AlexeyAB / darknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
http://pjreddie.com/darknet/
Other
21.65k stars 7.96k forks source link

Loss going nan while training on yolov4 #7089

Open hvudeshi opened 3 years ago

hvudeshi commented 3 years ago

Hello @AlexeyAB,

I have trained yolov4 on my custom dataset two days before. Now, I am again training yolov4 on the subset of the same custom dataset. I have used your yolov4 cfg and changed classes and filters of yolov4 and convolution layer above the yolov4 layer respectively. But, the loss is going nan. I have reduced the learning rate by 20 times, but still facing the same issue. Also, bad.list is also not generated by the check_mistakes flag that I have already enabled. As I have already trained on this dataset with more number of images for more than 100000 iterations, I don't think so there is an issue with the images. So, I want to know is there any bug or I am missing something? I want you to verify this.

Thank you.

AlexeyAB commented 3 years ago
hvudeshi commented 3 years ago

`[net] batch=64 subdivisions=32

Training

width=512

height=512

width=608 height=608 channels=3 momentum=0.949 decay=0.0005 angle=0 saturation = 1.5 exposure = 1.5 hue=.1

learning_rate=0.000561 burn_in=1000 max_batches = 500500 policy=steps steps=400000,450000 scales=.1,.1

cutmix=1

mosaic=1

:104x104 54:52x52 85:26x26 104:13x13 for 416

[convolutional] batch_normalize=1 filters=32 size=3 stride=1 pad=1 activation=mish

Downsample

[convolutional] batch_normalize=1 filters=64 size=3 stride=2 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish

[route] layers = -2

[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=32 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish

[route] layers = -1,-7

[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish

Downsample

[convolutional] batch_normalize=1 filters=128 size=3 stride=2 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish

[route] layers = -2

[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish

[route] layers = -1,-10

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish

Downsample

[convolutional] batch_normalize=1 filters=256 size=3 stride=2 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish

[route] layers = -2

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish

[route] layers = -1,-28

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish

Downsample

[convolutional] batch_normalize=1 filters=512 size=3 stride=2 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish

[route] layers = -2

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish

[route] layers = -1,-28

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish

Downsample

[convolutional] batch_normalize=1 filters=1024 size=3 stride=2 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish

[route] layers = -2

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish

[convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=mish

[shortcut] from=-3 activation=linear

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish

[route] layers = -1,-16

[convolutional] batch_normalize=1 filters=1024 size=1 stride=1 pad=1 activation=mish

##########################

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky

SPP

[maxpool] stride=1 size=5

[route] layers=-2

[maxpool] stride=1 size=9

[route] layers=-4

[maxpool] stride=1 size=13

[route] layers=-1,-3,-5,-6

End SPP

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky

[upsample] stride=2

[route] layers = 85

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky

[route] layers = -1, -3

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=512 activation=leaky

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=512 activation=leaky

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky

[upsample] stride=2

[route] layers = 54

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky

[route] layers = -1, -3

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=256 activation=leaky

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=256 activation=leaky

[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky

##########################

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=256 activation=leaky

[convolutional] size=1 stride=1 pad=1 filters=18 activation=linear

[yolo] mask = 0,1,2 anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 classes=1 num=9 jitter=.3 ignore_thresh = .7 truth_thresh = 1 scale_x_y = 1.2 iou_thresh=0.213 cls_normalizer=1.0 iou_normalizer=0.07 iou_loss=ciou nms_kind=greedynms beta_nms=0.6

[route] layers = -4

[convolutional] batch_normalize=1 size=3 stride=2 pad=1 filters=256 activation=leaky

[route] layers = -1, -16

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=512 activation=leaky

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=512 activation=leaky

[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=512 activation=leaky

[convolutional] size=1 stride=1 pad=1 filters=18 activation=linear

[yolo] mask = 3,4,5 anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 classes=1 num=9 jitter=.3 ignore_thresh = .7 truth_thresh = 1 scale_x_y = 1.1 iou_thresh=0.213 cls_normalizer=1.0 iou_normalizer=0.07 iou_loss=ciou nms_kind=greedynms beta_nms=0.6

[route] layers = -4

[convolutional] batch_normalize=1 size=3 stride=2 pad=1 filters=512 activation=leaky

[route] layers = -1, -37

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky

[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky

[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky

[convolutional] size=1 stride=1 pad=1 filters=18 activation=linear

[yolo] mask = 6,7,8 anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 classes=1 num=9 jitter=.3 ignore_thresh = .7 truth_thresh = 1 random=1 scale_x_y = 1.05 iou_thresh=0.213 cls_normalizer=1.0 iou_normalizer=0.07 iou_loss=ciou nms_kind=greedynms beta_nms=0.6 ` Run command: ./darknet detector train yolov4.conv.137 -dont_show -check_mistakes

Diaislam commented 3 years ago

Hello @AlexeyAB,

I have trained yolov4 on my custom dataset two days before. Now, I am again training yolov4 on the subset of the same custom dataset. I have used your yolov4 cfg and changed classes and filters of yolov4 and convolution layer above the yolov4 layer respectively. But, the loss is going nan. I have reduced the learning rate by 20 times, but still facing the same issue. Also, bad.list is also not generated by the check_mistakes flag that I have already enabled. As I have already trained on this dataset with more number of images for more than 100000 iterations, I don't think so there is an issue with the images. So, I want to know is there any bug or I am missing something? I want you to verify this.

Thank you.

check this https://github.com/AlexeyAB/darknet/issues/7097

AlexeyAB commented 3 years ago

There was a bug. I resolved it.