A free bird

pnet cls_loss的问题

8

您好，感谢开源代码。1 1。代码中关于pnet的损失是: loss = -tf.log(label_prob+1e-10) 跟论文中的cross_entropy = -y*log(p) + (1-y) * (1-log（p)) 好像不一样啊？ 当y=1时两者确实相同，但当y = 0时，就不同了 2.pnet 中我训练时，label中好像没有 -2（landmark样本）？

caffe编译出错

1

您好，感谢您的代码， 我替换文件后编译caffe，出现了如下错误，请问是什么原因呢？ guo@guo-System-Product-Name:~/caffe$ make all CXX src/caffe/layers/image_data_layer.cpp src/caffe/layers/image_data_layer.cpp: In instantiation of ‘void caffe::ImageDataLayer::load_batch(caffe::Batch*) [with Dtype = float]’: src/caffe/layers/image_data_layer.cpp:175:1: required from here src/caffe/layers/image_data_layer.cpp:157:29: error: cannot convert ‘std::vector’ to ‘float’ in assignment...

how to use the lfw dataset

1

thanks for your codes! i have a question that what is the protocol do you use in your training, there are PAIRS_TRAIN = "http://vis-www.cs.umass.edu/lfw/pairsDevTrain.txt" PAIRS_VAL = "http://vis-www.cs.umass.edu/lfw/pairsDevTest.txt" in the codes,but...