[Training issue]为什么在某些分辨率下，算法会对一类目标漏检？

[yiran-THU]

up主你好，感谢你的工作。

1.我最近在用一些自己的数据训练Yolov3_lite，然后进行测试。因为数据图像的尺度（1280*1280）固定，目标尺寸大小固定，所以我重新更改了网络结构，并用

It is very strange , can you try this way ?

的办法重新计算了anchor boxes，但是检测结果不理想，在测试集中该类目标一个都没检测出来！其他目标检测结果都正常；

2.此外，我还试过将图像分辨率（1024*1024）改小，并重新计算anchor，结果在该分辨率下，目标能检测出来，但是置信度较低。

3.若是将图像分辨率改为832*832，则该类目标检测结果正常。

My train prototxt

name: "MobileNet-YOLO"
layer {
name: "data"
type: "AnnotatedData"
top: "data"
top: "label"
include {
phase: TRAIN
}

transform_param {
scale: 0.007843
mirror: true
mean_value: 127.5
mean_value: 127.5
mean_value: 127.5

resize_param {
prob: 1.0
resize_mode: WARP
height: 1280
width: 1280
interp_mode: LINEAR
interp_mode: AREA
interp_mode: LANCZOS4
}
emit_constraint {
emit_type: CENTER
}
distort_param {
brightness_prob: 0.5
brightness_delta: 32.0
contrast_prob: 0.5
contrast_lower: 0.5
contrast_upper: 1.5
hue_prob: 0.5
hue_delta: 18.0
saturation_prob: 0.5
saturation_lower: 0.5
saturation_upper: 1.5
random_order_prob: 0.0
}
expand_param {
prob: 0.5
max_expand_ratio: 3.0
}
}
data_param {
source: "examples/VOC0712/VOC0712_trainval_lmdb"
batch_size: 1
backend: LMDB
}
annotated_data_param {
yolo_data_type : 1
yolo_data_jitter : 0.3
label_map_file: "data/VOC0712/labelmap_voc.prototxt"
}
}

layer {
name: "conv0"
type: "Convolution"
bottom: "data"
top: "conv0"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 32
bias_term: false
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv0/bn"
type: "BatchNorm"
bottom: "conv0"
top: "conv0"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv0/scale"
type: "Scale"
bottom: "conv0"
top: "conv0"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv0/relu"
type: "ReLU"
bottom: "conv0"
top: "conv0"
}
layer {
name: "conv1/dw"
type: "DepthwiseConvolution"
bottom: "conv0"
top: "conv1/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 32
bias_term: false
pad: 1
kernel_size: 3
group: 32
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv1/dw/bn"
type: "BatchNorm"
bottom: "conv1/dw"
top: "conv1/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv1/dw/scale"
type: "Scale"
bottom: "conv1/dw"
top: "conv1/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv1/dw/relu"
type: "ReLU"
bottom: "conv1/dw"
top: "conv1/dw"
}
layer {
name: "conv1"
type: "Convolution"
bottom: "conv1/dw"
top: "conv1"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 64
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv1/bn"
type: "BatchNorm"
bottom: "conv1"
top: "conv1"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv1/scale"
type: "Scale"
bottom: "conv1"
top: "conv1"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv1/relu"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "conv2/dw"
type: "DepthwiseConvolution"
bottom: "conv1"
top: "conv2/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 64
bias_term: false
pad: 1
kernel_size: 3
stride: 2
group: 64
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv2/dw/bn"
type: "BatchNorm"
bottom: "conv2/dw"
top: "conv2/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv2/dw/scale"
type: "Scale"
bottom: "conv2/dw"
top: "conv2/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv2/dw/relu"
type: "ReLU"
bottom: "conv2/dw"
top: "conv2/dw"
}
layer {
name: "conv2"
type: "Convolution"
bottom: "conv2/dw"
top: "conv2"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 128
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv2/bn"
type: "BatchNorm"
bottom: "conv2"
top: "conv2"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv2/scale"
type: "Scale"
bottom: "conv2"
top: "conv2"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv2/relu"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "conv3/dw"
type: "DepthwiseConvolution"
bottom: "conv2"
top: "conv3/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 128
bias_term: false
pad: 1
kernel_size: 3
group: 128
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv3/dw/bn"
type: "BatchNorm"
bottom: "conv3/dw"
top: "conv3/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv3/dw/scale"
type: "Scale"
bottom: "conv3/dw"
top: "conv3/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv3/dw/relu"
type: "ReLU"
bottom: "conv3/dw"
top: "conv3/dw"
}
layer {
name: "conv3"
type: "Convolution"
bottom: "conv3/dw"
top: "conv3"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 128
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv3/bn"
type: "BatchNorm"
bottom: "conv3"
top: "conv3"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv3/scale"
type: "Scale"
bottom: "conv3"
top: "conv3"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv3/relu"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4/dw"
type: "DepthwiseConvolution"
bottom: "conv3"
top: "conv4/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 128
bias_term: false
pad: 1
kernel_size: 3
stride: 2
group: 128
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv4/dw/bn"
type: "BatchNorm"
bottom: "conv4/dw"
top: "conv4/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv4/dw/scale"
type: "Scale"
bottom: "conv4/dw"
top: "conv4/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv4/dw/relu"
type: "ReLU"
bottom: "conv4/dw"
top: "conv4/dw"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv4/dw"
top: "conv4"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 256
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv4/bn"
type: "BatchNorm"
bottom: "conv4"
top: "conv4"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv4/scale"
type: "Scale"
bottom: "conv4"
top: "conv4"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv4/relu"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5/dw"
type: "DepthwiseConvolution"
bottom: "conv4"
top: "conv5/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 256
bias_term: false
pad: 1
kernel_size: 3
group: 256
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv5/dw/bn"
type: "BatchNorm"
bottom: "conv5/dw"
top: "conv5/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv5/dw/scale"
type: "Scale"
bottom: "conv5/dw"
top: "conv5/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv5/dw/relu"
type: "ReLU"
bottom: "conv5/dw"
top: "conv5/dw"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv5/dw"
top: "conv5"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 256
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv5/bn"
type: "BatchNorm"
bottom: "conv5"
top: "conv5"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv5/scale"
type: "Scale"
bottom: "conv5"
top: "conv5"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv5/relu"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "conv6/dw"
type: "DepthwiseConvolution"
bottom: "conv5"
top: "conv6/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 256
bias_term: false
pad: 1
kernel_size: 3
stride: 2
group: 256
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv6/dw/bn"
type: "BatchNorm"
bottom: "conv6/dw"
top: "conv6/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv6/dw/scale"
type: "Scale"
bottom: "conv6/dw"
top: "conv6/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv6/dw/relu"
type: "ReLU"
bottom: "conv6/dw"
top: "conv6/dw"
}
layer {
name: "conv6"
type: "Convolution"
bottom: "conv6/dw"
top: "conv6"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv6/bn"
type: "BatchNorm"
bottom: "conv6"
top: "conv6"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv6/scale"
type: "Scale"
bottom: "conv6"
top: "conv6"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv6/relu"
type: "ReLU"
bottom: "conv6"
top: "conv6"
}
layer {
name: "conv7/dw"
type: "DepthwiseConvolution"
bottom: "conv6"
top: "conv7/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv7/dw/bn"
type: "BatchNorm"
bottom: "conv7/dw"
top: "conv7/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv7/dw/scale"
type: "Scale"
bottom: "conv7/dw"
top: "conv7/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv7/dw/relu"
type: "ReLU"
bottom: "conv7/dw"
top: "conv7/dw"
}
layer {
name: "conv7"
type: "Convolution"
bottom: "conv7/dw"
top: "conv7"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv7/bn"
type: "BatchNorm"
bottom: "conv7"
top: "conv7"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv7/scale"
type: "Scale"
bottom: "conv7"
top: "conv7"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv7/relu"
type: "ReLU"
bottom: "conv7"
top: "conv7"
}
layer {
name: "conv8/dw"
type: "DepthwiseConvolution"
bottom: "conv7"
top: "conv8/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv8/dw/bn"
type: "BatchNorm"
bottom: "conv8/dw"
top: "conv8/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv8/dw/scale"
type: "Scale"
bottom: "conv8/dw"
top: "conv8/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv8/dw/relu"
type: "ReLU"
bottom: "conv8/dw"
top: "conv8/dw"
}
layer {
name: "conv8"
type: "Convolution"
bottom: "conv8/dw"
top: "conv8"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv8/bn"
type: "BatchNorm"
bottom: "conv8"
top: "conv8"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv8/scale"
type: "Scale"
bottom: "conv8"
top: "conv8"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv8/relu"
type: "ReLU"
bottom: "conv8"
top: "conv8"
}
layer {
name: "conv9/dw"
type: "DepthwiseConvolution"
bottom: "conv8"
top: "conv9/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv9/dw/bn"
type: "BatchNorm"
bottom: "conv9/dw"
top: "conv9/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv9/dw/scale"
type: "Scale"
bottom: "conv9/dw"
top: "conv9/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv9/dw/relu"
type: "ReLU"
bottom: "conv9/dw"
top: "conv9/dw"
}
layer {
name: "conv9"
type: "Convolution"
bottom: "conv9/dw"
top: "conv9"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv9/bn"
type: "BatchNorm"
bottom: "conv9"
top: "conv9"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv9/scale"
type: "Scale"
bottom: "conv9"
top: "conv9"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv9/relu"
type: "ReLU"
bottom: "conv9"
top: "conv9"
}
layer {
name: "conv10/dw"
type: "DepthwiseConvolution"
bottom: "conv9"
top: "conv10/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv10/dw/bn"
type: "BatchNorm"
bottom: "conv10/dw"
top: "conv10/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv10/dw/scale"
type: "Scale"
bottom: "conv10/dw"
top: "conv10/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv10/dw/relu"
type: "ReLU"
bottom: "conv10/dw"
top: "conv10/dw"
}
layer {
name: "conv10"
type: "Convolution"
bottom: "conv10/dw"
top: "conv10"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv10/bn"
type: "BatchNorm"
bottom: "conv10"
top: "conv10"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv10/scale"
type: "Scale"
bottom: "conv10"
top: "conv10"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv10/relu"
type: "ReLU"
bottom: "conv10"
top: "conv10"
}
layer {
name: "conv11/dw"
type: "DepthwiseConvolution"
bottom: "conv10"
top: "conv11/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv11/dw/bn"
type: "BatchNorm"
bottom: "conv11/dw"
top: "conv11/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv11/dw/scale"
type: "Scale"
bottom: "conv11/dw"
top: "conv11/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv11/dw/relu"
type: "ReLU"
bottom: "conv11/dw"
top: "conv11/dw"
}
layer {
name: "conv11"
type: "Convolution"
bottom: "conv11/dw"
top: "conv11"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv11/bn"
type: "BatchNorm"
bottom: "conv11"
top: "conv11"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv11/scale"
type: "Scale"
bottom: "conv11"
top: "conv11"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv11/relu"
type: "ReLU"
bottom: "conv11"
top: "conv11"
}
layer {
name: "conv12/dw"
type: "DepthwiseConvolution"
bottom: "conv11"
top: "conv12/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
stride: 2
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv12/dw/bn"
type: "BatchNorm"
bottom: "conv12/dw"
top: "conv12/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv12/dw/scale"
type: "Scale"
bottom: "conv12/dw"
top: "conv12/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv12/dw/relu"
type: "ReLU"
bottom: "conv12/dw"
top: "conv12/dw"
}
layer {
name: "conv12"
type: "Convolution"
bottom: "conv12/dw"
top: "conv12"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 1024
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv12/bn"
type: "BatchNorm"
bottom: "conv12"
top: "conv12"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv12/scale"
type: "Scale"
bottom: "conv12"
top: "conv12"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv12/relu"
type: "ReLU"
bottom: "conv12"
top: "conv12"
}
layer {
name: "conv13/dw"
type: "DepthwiseConvolution"
bottom: "conv12"
top: "conv13/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 1024
bias_term: false
pad: 1
kernel_size: 3
group: 1024
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv13/dw/bn"
type: "BatchNorm"
bottom: "conv13/dw"
top: "conv13/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv13/dw/scale"
type: "Scale"
bottom: "conv13/dw"
top: "conv13/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv13/dw/relu"
type: "ReLU"
bottom: "conv13/dw"
top: "conv13/dw"
}
layer {
name: "conv13"
type: "Convolution"
bottom: "conv13/dw"
top: "conv13"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 1024
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv13/bn"
type: "BatchNorm"
bottom: "conv13"
top: "conv13"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv13/scale"
type: "Scale"
bottom: "conv13"
top: "conv13"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv13/relu"
type: "ReLU"
bottom: "conv13"
top: "conv13"
}

layer {
name: "conv16/dw"
type: "DepthwiseConvolution"
bottom: "conv13"
top: "conv16/dw"
param {
lr_mult: 1
decay_mult: 1
}
convolution_param {
num_output: 1024
bias_term: false
pad: 1
kernel_size: 3
group: 1024
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv16/dw/bn"
type: "BatchNorm"
bottom: "conv16/dw"
top: "conv16/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv16/dw/scale"
type: "Scale"
bottom: "conv16/dw"
top: "conv16/dw"
param {
lr_mult: 1
decay_mult: 0.0
}
param {
lr_mult: 2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv16/dw/relu"
type: "ReLU"
bottom: "conv16/dw"
top: "conv16/dw"
}
layer {
name: "conv16"
type: "Convolution"
bottom: "conv16/dw"
top: "conv16"
param {
lr_mult: 1
decay_mult: 1
}
convolution_param {
num_output: 1024
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv16/bn"
type: "BatchNorm"
bottom: "conv16"
top: "conv16"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv16/scale"
type: "Scale"
bottom: "conv16"
top: "conv16"
param {
lr_mult: 1
decay_mult: 0.0
}
param {
lr_mult: 2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv16/relu"
type: "ReLU"
bottom: "conv16"
top: "conv16"
}
layer {
name: "upsample"
type: "Deconvolution"
bottom: "conv16"
top: "upsample"
param { lr_mult: 0 decay_mult: 0 }
convolution_param {
num_output: 512
kernel_size: 4 stride: 2 pad: 1
group: 512
weight_filler: { type: "bilinear" }
bias_term: false
}
}
layer {
name: "conv17/dw"
type: "DepthwiseConvolution"
bottom: "conv11"
top: "conv17/dw"
param {
lr_mult: 1
decay_mult: 1
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv17/dw/bn"
type: "BatchNorm"
bottom: "conv17/dw"
top: "conv17/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv17/dw/scale"
type: "Scale"
bottom: "conv17/dw"
top: "conv17/dw"
param {
lr_mult: 1
decay_mult: 0.0
}
param {
lr_mult: 2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv17/dw/relu"
type: "ReLU"
bottom: "conv17/dw"
top: "conv17/dw"
}
layer {
name: "conv17"
type: "Convolution"
bottom: "conv17/dw"
top: "conv17"
param {
lr_mult: 1
decay_mult: 1
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv17/bn"
type: "BatchNorm"
bottom: "conv17"
top: "conv17"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv17/scale"
type: "Scale"
bottom: "conv17"
top: "conv17"
param {
lr_mult: 1
decay_mult: 0.0
}
param {
lr_mult: 2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv17/relu"
type: "ReLU"
bottom: "conv17"
top: "conv17"
}
layer {
name: "conv17/sum"
type: "Eltwise"
bottom: "conv17"
bottom: "upsample"
top: "conv17/sum"
}
layer {
name: "conv18/dw"
type: "DepthwiseConvolution"
bottom: "conv17/sum"
top: "conv18/dw"
param {
lr_mult: 1
decay_mult: 1
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv18/dw/bn"
type: "BatchNorm"
bottom: "conv18/dw"
top: "conv18/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv18/dw/scale"
type: "Scale"
bottom: "conv18/dw"
top: "conv18/dw"
param {
lr_mult: 1
decay_mult: 0.0
}
param {
lr_mult: 2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv18/dw/relu"
type: "ReLU"
bottom: "conv18/dw"
top: "conv18/dw"
}
layer {
name: "conv18"
type: "Convolution"
bottom: "conv18/dw"
top: "conv18"
param {
lr_mult: 1
decay_mult: 1
}
convolution_param {
num_output: 1024
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv18/bn"
type: "BatchNorm"
bottom: "conv18"
top: "conv18"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv18/scale"
type: "Scale"
bottom: "conv18"
top: "conv18"
param {
lr_mult: 1
decay_mult: 0.0
}
param {
lr_mult: 2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv18/relu"
type: "ReLU"
bottom: "conv18"
top: "conv18"
}

layer {
name: "conv20_new"
type: "Convolution"
bottom: "conv16"
top: "conv20_new"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 1024
kernel_size: 1
pad: 0
stride: 1
weight_filler {
type: "msra"
}
bias_filler {
value: 0
}
}
}
layer {
name: "conv20_new/bn"
type: "BatchNorm"
bottom: "conv20_new"
top: "conv20_new"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv20_new/scale"
type: "Scale"
bottom: "conv20_new"
top: "conv20_new"
param {
lr_mult: 1
decay_mult: 0.0
}
param {
lr_mult: 2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}

layer {
name: "conv20_new/relu"
type: "ReLU"
bottom: "conv20_new"
top: "conv20_new"
}

layer {
name: "conv21"
type: "Convolution"
bottom: "conv18"
top: "conv21"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 75
kernel_size: 1
pad: 0
stride: 1
weight_filler {
type: "msra"
}
bias_filler {
value: 0
}
}
}

layer {
name: "conv22/dw"
type: "DepthwiseConvolution"
bottom: "conv20_new"
top: "conv22/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 1024
bias_term: true
pad: 1
kernel_size: 3
stride: 2
group: 1024
engine: CAFFE
weight_filler {
type: "msra"
}
}
}

layer {
name: "conv22/dw/bn"
type: "BatchNorm"
bottom: "conv22/dw"
top: "conv22/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv22/dw/scale"
type: "Scale"
bottom: "conv22/dw"
top: "conv22/dw"
param {
lr_mult: 1
decay_mult: 0.0
}
param {
lr_mult: 2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv22/dw/relu"
type: "ReLU"
bottom: "conv22/dw"
top: "conv22/dw"
}
layer {
name: "conv22"
type: "Convolution"
bottom: "conv22/dw"
top: "conv22"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 1024
bias_term: true
kernel_size: 1
weight_filler {
type: "msra"
}
}
}

layer {
name: "conv22/bn"
type: "BatchNorm"
bottom: "conv22"
top: "conv22"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv22/scale"
type: "Scale"
bottom: "conv22"
top: "conv22"
param {
lr_mult: 1
decay_mult: 0.0
}
param {
lr_mult: 2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}

layer {
name: "conv22/relu"
type: "ReLU"
bottom: "conv22"
top: "conv22"
}
layer {
name: "conv23/dw"
type: "DepthwiseConvolution"
bottom: "conv22"
top: "conv23/dw"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 1024
bias_term: true
pad: 1
kernel_size: 3
group: 1024
engine: CAFFE
weight_filler {
type: "msra"
}
}
}

layer {
name: "conv23/dw/bn"
type: "BatchNorm"
bottom: "conv23/dw"
top: "conv23/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv23/dw/scale"
type: "Scale"
bottom: "conv23/dw"
top: "conv23/dw"
param {
lr_mult: 1
decay_mult: 0.0
}
param {
lr_mult: 2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv23/dw/relu"
type: "ReLU"
bottom: "conv23/dw"
top: "conv23/dw"
}

layer {
name: "conv23"
type: "Convolution"
bottom: "conv23/dw"
top: "conv23"
param {
lr_mult: 0.1
decay_mult: 0.1
}
convolution_param {
num_output: 75
bias_term: true
kernel_size: 1
weight_filler {
type: "msra"
}
}
}

layer {
name: "conv20_old"
type: "Convolution"
bottom: "conv20_new"
top: "conv20_old"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 75
kernel_size: 1
pad: 0
stride: 1
weight_filler {
type: "msra"
}
bias_filler {
value: 0
}
}
}

layer {
name: "Yolov3Loss1"
type: "Yolov3"
bottom: "conv23"
bottom: "label"
top: "det_loss1"
loss_weight: 1
yolov3_param {
side: 13
num_class: 20
num: 3
object_scale: 5.0
noobject_scale: 1.0
class_scale: 1.0
coord_scale: 1.0
thresh: 0.6
anchors_scale : 64
use_logic_gradient : false
#10,14, 23,27, 37,58, 81,82, 135,169, 344,319
biases: 34
biases: 43
biases: 66
biases: 51
biases: 54
biases: 76
biases: 183
biases: 84
biases: 128
biases: 142
biases: 317
biases: 270
biases: 77
biases: 85
biases: 85
biases: 104
biases: 100
biases: 116

mask:3
mask:4
mask:5
}
}
layer {
name: "Yolov3Loss2"
type: "Yolov3"
bottom: "conv21"
bottom: "label"
top: "det_loss2"
loss_weight: 1
yolov3_param {
side: 26
num_class: 20
num: 3
object_scale: 5.0
noobject_scale: 1.0
class_scale: 1.0
coord_scale: 1.0
thresh: 0.6
anchors_scale : 16
use_logic_gradient : false
#10,14, 23,27, 37,58, 81,82, 135,169, 344,319
biases: 34
biases: 43
biases: 66
biases: 51
biases: 54
biases: 76
biases: 183
biases: 84
biases: 128
biases: 142
biases: 317
biases: 270
biases: 77
biases: 85
biases: 85
biases: 104
biases: 100
biases: 116

mask:0
mask:1
mask:2
}
}

layer {
name: "Yolov3Loss3"
type: "Yolov3"
bottom: "conv20_old"
bottom: "label"
top: "det_loss3"
loss_weight: 1
yolov3_param {
side: 13
num_class: 20
num: 3
object_scale: 5.0
noobject_scale: 1.0
class_scale: 1.0
coord_scale: 1.0
thresh: 0.6
anchors_scale : 32
use_logic_gradient : false
#10,14, 23,27, 37,58, 81,82, 135,169, 344,319
biases: 34
biases: 43
biases: 66
biases: 51
biases: 54
biases: 76
biases: 183
biases: 84
biases: 128
biases: 142
biases: 317
biases: 270
biases: 77
biases: 85
biases: 85
biases: 104
biases: 100
biases: 116
mask:6
mask:7
mask:8
}
}

请问下，为什么会出现这种情况？
如果我想要在1280*1280分辨率下正确检测出该目标，应该怎么做？

[yiran-THU]

@eric612

Anchor box是按照1280的分辨率计算的，大佬能否指点一二，谢谢！

[eric612]

不太理解，方便上傳log 嗎

[yiran-THU]

@eric612

我今天做了测试，构建了一个训练集，里面只有上述测试中漏检的目标，然后在1280*1280的分辨率下训练，结果能检测出之前漏检的那类目标。

今天我打算在之前的训练集内大量加入漏检目标数据（相同图像复制的方式），然后训练，log明天白天上传。

我比较奇怪的是，相同数量和比例数据的训练集，为什么在832832的分辨率下一切正常，而在12801280的分辨率下却一个都没检测出来！

---

我今天做了測試，構建了壹個訓練集，裏面只有上述測試中漏檢的目標，然後在1280*1280的分辨率下訓練，結果能檢測出之前漏檢的那類目標。

今天我打算在之前的訓練集內大量加入漏檢目標數據（相同圖像復制的方式），然後訓練，log明天白天上傳。

我比較奇怪的是，相同數量和比例數據的訓練集，為什麽在832832的分辨率下壹切正常，而在12801280的分辨率下卻壹個都沒檢測出來！

[yiran-THU]

train.log

初步训练了下，多加数据后，能框出来，但是置信度特别低，而且框得不准。
为什么在832832下一切正常，而12801280下对该目标就不行呢。

[eric612]

log 看起來沒什麼異常，但裡面沒有anchor的數值和test的結果，方便上傳嗎

[yiran-THU]

@eric612

我的显存不够，没有在训练的时候做过test。
目前用的anchor数值如下：
biases: 120
biases: 90
biases: 120
biases: 170
biases: 140
biases: 160
biases: 200
biases: 200
biases: 440
biases: 160
biases: 480
biases: 400
biases: 230
biases: 230
biases: 230
biases: 213
biases: 213
biases: 213

mask:3
mask:4
mask:5
mask:0
mask:1
mask:2
mask:6
mask:7
mask:8

anchors_scale:64
anchors_scale:16
anchors_scale:32
mask_group_num:3

[yyqgood]

楼主，你这个问题最终怎么解决的呢？