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

Training Custom Dataset (High Avg Loss) #7078

Open LFRS opened 3 years ago

LFRS commented 3 years ago

Hi,

I'm having issues training a custom dataset, i'm getting "high Avg Loss" and i don't know why.

The dataset has 1 Class with:

9 images for "test" (Resolution 320x320)
35 images for "train" (Resolution 320x320)
10 images for "valid" (Resolution 320x320)

The "yolov4-obj.cfg" file is attached but the changes for one class were:

batch=16
subdivisions=16
width=160
height=160
...
filters=18
...
classes=1

The results that i'm getting are this, "High Avg Loss" and "High mAP":

Img1

Img2

What i'm doing wrong??? Thanks.

------ "yolov4-obj.cfg" ------

[net]

Testing

batch=1

subdivisions=1

Training

batch=16 subdivisions=16 width=160 height=160 channels=3 momentum=0.949 decay=0.0005 angle=0 saturation = 1.5 exposure = 1.5 hue=.1

learning_rate=0.001 burn_in=1000 max_batches=6000 policy=steps steps=48000,54000 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 stopbackward=800

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

[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 max_delta=5

[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 max_delta=5

[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 max_delta=5

TA-Engineer commented 3 years ago

I am having the same issue. After first few hundred iteration my average loss stays at around 37, 42.

Diaislam commented 3 years ago

I am having the same issue. After first few hundred iteration my average loss stays at around 37, 42.

checkout an old commit it solved my problem.

pycoco commented 3 years ago

i also meet the same issue. and i don't know why?

ROBYER1 commented 3 years ago

I am having the same issue. After first few hundred iteration my average loss stays at around 37, 42.

checkout an old commit it solved my problem.

What commit was it?

willSapgreen commented 2 years ago

@ROBYER1 ,

I am having the same issue. After first few hundred iteration my average loss stays at around 37, 42.

checkout an old commit it solved my problem.

What commit was it?

Maybe this one: https://github.com/AlexeyAB/darknet/issues/7097#issuecomment-742737350 (not sure but looks like)