我正在从输入图像中提取30个面部关键点（x,y），这是根据Kaggle面部关键点竞赛的要求进行的。

我该如何设置Caffe来运行回归并生成30维的输出？

输入：96x96图像输出：30 -（30维）。

我该如何相应地设置Caffe？我使用EUCLIDEAN_LOSS（平方和）来获得回归输出。这里有一个使用Caffe的简单逻辑回归模型，但它不起作用。看起来准确度层无法处理多标签输出。

I0120 17:51:27.039113  4113 net.cpp:394] accuracy <- label_fkp_1_split_1I0120 17:51:27.039135  4113 net.cpp:356] accuracy -> accuracyI0120 17:51:27.039158  4113 net.cpp:96] Setting up accuracyF0120 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 }}

回答：

我找到了解决方法:)

我将SOFTLAYER替换为EUCLIDEAN_LOSS函数，并更改了输出的数量。它起作用了。

layers {  name: "loss"  type: EUCLIDEAN_LOSS  bottom: "ip1"  bottom: "label"  top: "loss"}

HINGE_LOSS也是另一个选择。