search

unsky / Deformable-ConvNets-caffe

Deformable Convolutional Networks on caffe
160 stars 83 forks source link

deformable_conv_cxx/deformable_conv_layer.cu missing a '}' #6

Closed ksnzh closed 6 years ago

ksnzh commented 6 years ago

https://github.com/unsky/Deformable-ConvNets-caffe/blob/8dded4f7571c8556304c07d92cb3e9a93d4b514f/deformable_conv_cxx/deformable_conv_layer.cu#L118

And it will throw error when compiling.

At end of source: error: expected a "}"
ksnzh commented 6 years ago

deformable_conv_cxx/deformable_conv_layer.cpp missing 'REGISTER_LAYER_CLASS(DeformableConvolution);'

And it will throw error like bellow:

I1214 00:23:24.195385  5149 layer_factory.hpp:77] Creating layer dec
F1214 00:23:24.195410  5149 layer_factory.hpp:81] Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: DeformableConvolution (known types: AbsVal, Accuracy, ArgMax, Axpy, BNLL, BatchNorm, BatchReindex, Bias, BoxAnnotatorOHEM, Concat, ContrastiveLoss, Convolution, ConvolutionDepthwise, Crop, Data, Deconvolution, DeformablePSROIPooling, DenseCRF, DepthwiseConvolution, Dropout, DummyData, ELU, Eltwise, Embed, EuclideanLoss, Exp, Filter, Flatten, FocalLoss, FrcnnAnchorTarget, FrcnnProposal, FrcnnProposalTarget, HDF5Data, HDF5Output, HingeLoss, Im2col, ImageData, ImageSegData, InfogainLoss, InnerProduct, InnerProductBlob, Input, Interp, LRN, LSTM, LSTMUnit, LargeMarginInnerProduct, Log, MVN, MarginInnerProduct, MaskPooling, MaskResize, MemoryData, MultinomialLogisticLoss, PReLU, PSROIPooling, Parameter, Pooling, Power, Python, RNN, ROIAlign, ROIMaskPooling, ROIPooling, ROIWarping, ReLU, Reduction, Reshape, SPP, Scale, SeLu, SeLuDropout, SegAccuracy, Sigmoid, SigmoidCrossEntropyLoss, Silence, Slice, SmoothL1Loss, SmoothL1LossOHEM, Softmax, SoftmaxWithLoss, SoftmaxWithLossOHEM, Split, TanH, Threshold, Tile, WindowData)
unsky commented 6 years ago

@ksnzh use new codes