Yolov4 模型测试结果错误

VIM3
1

目前我用自己训练的yolov4模型做转换，最后输出的结果看起来全是错的，目前确认模型是没问题的。

image
image730×728 252 KB

2

原始的模型测试过没有呢？是否也是一样的？

3

原始模型用pytorch加载测试了是没有问题的，同样的流程我在 yolov3上面是可以的，不知道是不是因为 有 SPP层导致的。

4

验证 yolov3-spp是可以的，目前就是 yolov4不行，就是网络结构的连接方式复杂了点，其他都没变，yolov4.cfg如下

[net]

Testing

#batch=1
#subdivisions=1

Training

batch=64
subdivisions=8
width=640
height=640
channels=3
momentum=0.949
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

learning_rate=0.00261
burn_in=1000
max_batches = 500500
policy=steps
steps=400000,450000
scales=.1,.1

mosaic=1

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

Downsample

[convolutional]
batch_normalize=1
filters=32
size=3
stride=2
pad=1
activation=leaky

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

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

[shortcut]
from=-3
activation=linear

Downsample

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

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

[route]
layers = -2

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

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

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

[shortcut]
from=-3
activation=linear

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

[route]
layers = -1,-7

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

Downsample

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

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

[route]
layers = -2

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

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

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

[shortcut]
from=-3
activation=linear

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

[route]
layers = -1,-7

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

Downsample

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

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

[route]
layers = -2

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

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

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

[shortcut]
from=-3
activation=linear

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

[route]
layers = -1,-7

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

Downsample

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

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

[route]
layers = -2

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

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

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

[shortcut]
from=-3
activation=linear

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

[route]
layers = -1,-7

[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

[route]
layers = -2

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

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

[route]
layers = -1, -11

[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 = 34

[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
filters=128
size=1
stride=1
pad=1
activation=leaky

[route]
layers = -2

[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=128
activation=leaky

[route]
layers = -1, -4

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

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

[upsample]
stride=2

[route]
layers = 24

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

[route]
layers = -1, -3

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

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

[route]
layers = -2

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

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

[route]
layers = -1, -4

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

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

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

[convolutional]
size=1
stride=1
pad=1
filters=30
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
anchors = 12,12, 24,24, 24,48, 48,24, 48,48, 48,96, 96, 48, 96, 96, 160, 160

classes=5
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

[route]
layers = -4

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

[route]
layers = -1, -18

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

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

[route]
layers = -2

[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=128
activation=leaky

[route]
layers = -1,-4

[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=30
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
anchors = 12,12, 24,24, 24,48, 48,24, 48,48, 48,96, 96, 48, 96, 96, 160, 160
classes=5
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

[route]
layers = -4

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

[route]
layers = -1, -43

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

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

[route]
layers = -2

[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=256
activation=leaky

[route]
layers = -1,-4

[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=30
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
anchors = 12,12, 24,24, 24,48, 48,24, 48,48, 48,96, 96, 48, 96, 96, 160, 160
classes=5
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

5

我测试了yolov4原有的模型，预测结果还是混乱的。

6

我们近期也会测试YoloV4的模型，到时会反馈测试结果。