Caffe中的多标签回归 [英] Multi label regression in Caffe
问题描述
我根据kaggle面部关键点竞争从输入图像中提取30个面部关键点(x,y).
i am extracting 30 facial keypoints (x,y) from an input image as per kaggle facialkeypoints competition.
我如何设置caffe以运行回归并产生30维输出?
How do i setup caffe to run a regression and produce 30 dimensional output??.
Input: 96x96 image
Output: 30 - (30 dimensions).
我如何相应地设置咖啡?我正在使用EUCLIDEAN_LOSS(平方和)来获取回归输出.这是一个使用caffe的简单Logistic回归模型,但无法正常工作.外观精度图层无法处理多标签输出.
How do i setup caffe accordingly?. I am using EUCLIDEAN_LOSS (sum of squares) to get the regressed output. Here is a simple logistic regressor model using caffe but it is not working. Looks accuracy layer cannot handle multi-label output.
I0120 17:51:27.039113 4113 net.cpp:394] accuracy <- label_fkp_1_split_1
I0120 17:51:27.039135 4113 net.cpp:356] accuracy -> accuracy
I0120 17:51:27.039158 4113 net.cpp:96] Setting up accuracy
F0120 17:51:27.039201 4113 accuracy_layer.cpp:26] Check failed: bottom[1]->channels() == 1 (30 vs. 1)
*** Check failure stack trace: ***
@ 0x7f7c2711bdaa (unknown)
@ 0x7f7c2711bce4 (unknown)
@ 0x7f7c2711b6e6 (unknown)
这是图层文件:
name: "LogReg"
layers {
name: "fkp"
top: "data"
top: "label"
type: HDF5_DATA
hdf5_data_param {
source: "train.txt"
batch_size: 100
}
include: { phase: TRAIN }
}
layers {
name: "fkp"
type: HDF5_DATA
top: "data"
top: "label"
hdf5_data_param {
source: "test.txt"
batch_size: 100
}
include: { phase: TEST }
}
layers {
name: "ip"
type: INNER_PRODUCT
bottom: "data"
top: "ip"
inner_product_param {
num_output: 30
}
}
layers {
name: "loss"
type: EUCLIDEAN_LOSS
bottom: "ip"
bottom: "label"
top: "loss"
}
layers {
name: "accuracy"
type: ACCURACY
bottom: "ip"
bottom: "label"
top: "accuracy"
include: { phase: TEST }
}
推荐答案
我找到了:)
我将SOFTLAYER替换为EUCLIDEAN_LOSS函数,并更改了输出数量.奏效了.
I replaced the SOFTLAYER to EUCLIDEAN_LOSS function and changed the number of outputs. It worked.
layers {
name: "loss"
type: EUCLIDEAN_LOSS
bottom: "ip1"
bottom: "label"
top: "loss"
}
HINGE_LOSS也是另一种选择.
HINGE_LOSS is also another option.
这篇关于Caffe中的多标签回归的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!