用caffe训练数据时accuracy层出现错误
I1031 10:00:24.056213 495 net.cpp:84] Creating Layer accuracy
I1031 10:00:24.056218 495 net.cpp:406] accuracy <- score_reluscore_0_split_0
I1031 10:00:24.056226 495 net.cpp:406] accuracy <- label_data_1_split_0
I1031 10:00:24.056237 495 net.cpp:380] accuracy -> accuracy
F1031 10:00:24.056254 495 accuracy_layer.cpp:27] Check failed: bottom[1]->height() == 1 (256 vs. 1)
*** Check failure stack trace: ***
Aborted (core dumped)
val.prototxt中关于accuracy层的代码如下:
layer {
name: “reluscore”
type: “Sigmoid”
bottom: “score”
top: “score”
}
layer {
name: “accuracy”
type: “Accuracy”
bottom: “score”
bottom: “label”
top: “accuracy”
include {
phase: TEST
}
}
layer {
name: “loss”
type: “SoftmaxWithLoss”
bottom: “score”
bottom: “label”
top: “loss”
loss_param {
ignore_label: 255
normalize: false
}
}
caffe新手,求大神指点!