当在Caffe深度学习(或任何CNN框架)上训练一组课程(假设#clases(课程数量)= N)并且我对caffemodel进行查询时,我获得该图像概率的百分比没关系。
所以,让我们拍一张类似的1级照片,然后得到结果:
1.- 96%
2.- 4%
休息...... 0% 问题是:当我拍摄随机图片(例如我的环境)时,我会得到相同的结果,其中一个类占优势(概率> 90%),但它不属于任何类。< / p>
所以我想听到的是那些经历过这种情况的人的意见/答案,并且已经解决了如何处理神经网络的无意义输入。
我的目的是:
你会做什么?
非常感谢你。
圣拉斐尔。
修改
两个月后,我的一位同事给我一个线索:激活功能。
我已经看到我在每一层都使用 ReLU ,这意味着当x&gt;时x的值是x否则为0和0。这些是我的层次:
layers {
name: "conv1"
type: CONVOLUTION
bottom: "data"
top: "conv1"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "relu1"
type: RELU
bottom: "conv1"
top: "conv1"
}
layers {
name: "pool1"
type: POOLING
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layers {
name: "norm1"
type: LRN
bottom: "pool1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layers {
name: "conv2"
type: CONVOLUTION
bottom: "norm1"
top: "conv2"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu2"
type: RELU
bottom: "conv2"
top: "conv2"
}
layers {
name: "pool2"
type: POOLING
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layers {
name: "norm2"
type: LRN
bottom: "pool2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layers {
name: "conv3"
type: CONVOLUTION
bottom: "norm2"
top: "conv3"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "relu3"
type: RELU
bottom: "conv3"
top: "conv3"
}
layers {
name: "conv4"
type: CONVOLUTION
bottom: "conv3"
top: "conv4"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu4"
type: RELU
bottom: "conv4"
top: "conv4"
}
layers {
name: "conv5"
type: CONVOLUTION
bottom: "conv4"
top: "conv5"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu5"
type: RELU
bottom: "conv5"
top: "conv5"
}
layers {
name: "pool5"
type: POOLING
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layers {
name: "fc6"
type: INNER_PRODUCT
bottom: "pool5"
top: "fc6"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu6"
type: RELU
bottom: "fc6"
top: "fc6"
}
layers {
name: "drop6"
type: DROPOUT
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layers {
name: "fc7"
type: INNER_PRODUCT
bottom: "fc6"
top: "fc7"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layers {
name: "relu7"
type: RELU
relu_param {
negative_slope: -1
}
bottom: "fc7"
top: "fc7"
}
layers {
name: "drop7"
type: DROPOUT
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layers {
name: "fc8"
type: INNER_PRODUCT
bottom: "fc7"
top: "fc8"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 1000
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "loss"
type: SOFTMAX_LOSS
bottom: "fc8"
bottom: "label"
}
如果我将ReLU设为任何x的x(x <0则为负),我的网络收敛于精度= 0 ......
有更好的方法吗?
答案 0 :(得分:1)
用负面例子训练一个额外的课程 或者 - 这可能会起作用 - 如果网络定义满足您(例如从ImageNet),则使用预先训练好的网络和权重,并将类添加为附加标签。通过这种方式,你有更高的机会不适应那个额外的(负面)类。如果您的网络不同,您可以在较大的数据集上从头开始训练,而不是使用预先训练的权重。
答案 1 :(得分:0)
我也正在研究一个类似的问题,我不明白的是,即使你要告诉神经网络这是一个+ ve图像或-ve图像,我也不明白那将如何改变级联。我认为你必须从训练图像中挑选出特征。也许你可以构建一个改变XML级联的混合系统