我不明白tiny-yolo-v3中的串联

时间:2018-11-16 13:36:13

标签: deep-learning convolution yolo

.cfg文件中描述了网络的结构(请参见下文)。 “块”以[.....]

开头

所有使用的过滤器是:

  • 步幅为1且填充为1的3x3->它不会更改输出的高度和宽度
  • 1x1图层跨步1并且填充= 1->功能图=(宽度+2,高度+2,深度)

  • 上采样层->我读到它乘以高度和宽度的2倍

  • 路线:

    • 如果只有1个参数:(即“ -4”:它需要此路线层之前的第4层要素地图)
    • 如果有2个参数:(即-1,8:它将获取上一层的特征图并将其与网络第8层的特征图连接起来)

我不理解“ [route] Layers:-1,8”所应用的串联,因为如果我正确的话,它将32x32x ...与26x26x ...串联,这在技术上是不可能的吗? / p>

我重写了cfg文件,使其更易于可视化。您能告诉我我的抄写是否正确以及这种串联的工作方式吗? (我不理解的结果功能图用红色表示。)

my transcription of the cfg file

[\[net\]
# Testing
batch=1
subdivisions=1
# Training
# batch=64
# subdivisions=2
width=416
height=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

learning_rate=0.001
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1

\[convolutional\]
batch_normalize=1
filters=16
size=3
stride=1
pad=1
activation=leaky

\[maxpool\]
size=2
stride=2

\[convolutional\]
batch_normalize=132
filters=32
size=3
stride=1
pad=1
activation=leaky

\[maxpool\]
size=2
stride=2

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

\[maxpool\]
size=2
stride=2

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

\[maxpool\]
size=2
stride=2

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

\[maxpool\]
size=2
stride=2

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

\[maxpool\]
size=2
stride=1

\[convolutional\]
batch_normalize=1
filters=1024
size=3
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=512
size=3
stride=1
pad=1
activation=leaky

\[convolutional\]
size=1
stride=1
pad=1
filters=255
activation=linear



\[yolo\]
mask = 3,4,5
anchors = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
classes=80
num=6
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1

\[route\]
layers = -4

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

\[upsample\]
stride=2

\[route\]
layers = -1, 8

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

\[convolutional\]
size=1
stride=1
pad=1
filters=255
activation=linear

\[yolo\]
mask = 0,1,2
anchors = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
classes=80
num=6
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1

0 个答案:

没有答案