zys1994
zys1994
you said that outer weight is from a text file.can you provide the weight file, my train model can't be convergence.
train: ``` name: "ResNet-18" layer { name: "data" type: "ImageData" top: "data" top: "label" include { phase: TRAIN } transform_param { mirror: true scale: 0.0078125 mean_value: 127.5 mean_value: 127.5 mean_value:...
The net and data is followed by you, why the model size is different? My model is 8.5M and your model is 4M.
如您回答，我刚刚测了caffe模型的lfw只有99.566，测的图片是bgr的。我想问一下模型是rgb的吗？
(w=10,e=2) is fine
@xialuxi @briantse100 how to use Wingloss? when i use WingLoss layer like this ``` layer { name: "landmarkloss" type: "WingLoss" bottom: "fc4" bottom: "hdf_data" top: "landmarkloss" loss_weight: 1 include {...
cpu目前可以train,不过速度很慢 。 gpu版本是出了什么问题吗
cpu train了半天才6000个batch。期待你把gpu版本的改好来训 哈哈
make all -j 的时候报错了 ``` src/caffe/layers/wing_loss_layer.cpp:28:47: error: ‘one_dot_data’ was not declared in this scope ``` ``` void WingLossLayer::LayerSetUp(const vector& bottom, const vector& top) { w = this->layer_param_.wing_loss_param().w(); DCHECK(w > 0);...
改了之后make可以通过， 但用cpu,gpu 在train都会报错 用EuclideanLoss是可以跑的，应该还是Wingloss有点问题 ``` F0622 10:32:27.929319 17830 blob.cpp:133] Check failed: data_ *** Check failure stack trace: *** @ 0x7f44f71c15cd google::LogMessage::Fail() @ 0x7f44f71c3433 google::LogMessage::SendToLog() @ 0x7f44f71c115b google::LogMessage::Flush() @ 0x7f44f71c3e1e google::LogMessageFatal::~LogMessageFatal()...