search

facebookarchive / fb-caffe-exts

Some handy utility libraries and tools for the Caffe deep learning framework.
Other
457 stars 154 forks source link

Error in test.lua #6

Open omkarparkhi opened 8 years ago

omkarparkhi commented 8 years ago

Hi,

I am trying to run th torch2caffe/test.lua. It seems to be failing with following error.

I0303 14:42:44.412389 146 layer_factory.hpp:77] Creating layer caffe.LogSoftmax_2 F0303 14:42:44.412438 146 layer_factory.hpp:81] Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: LogSoftmax (known types: AbsVal, Accuracy, ArgMax, BNLL, BatchNorm, BatchReindex, Bias, Concat, ContrastiveLoss, Convolution, Data, Deconvolution, Dropout, DummyData, ELU, Eltwise, Embed, EuclideanLoss, Exp, Filter, Flatten, HDF5Data, HDF5Output, HingeLoss, Im2col, ImageData, InfogainLoss, InnerProduct, Input, LRN, Log, MVN, MemoryData, MultinomialLogisticLoss, PReLU, Pooling, Power, ReLU, Reduction, Reshape, SPP, Scale, Sigmoid, SigmoidCrossEntropyLoss, Silence, Slice, Softmax, SoftmaxWithLoss, Split, TanH, Threshold, Tile, WindowData)

Any suggestions as to whats going wrong?

czhang96 commented 8 years ago

I'm also having this issue, does anyone have a solution?

zlqhem commented 7 years ago

I'm also having this issue.

huyn commented 6 years ago

because caffe does not support LogSoftmax, thus you need to replace it by an existed
equivalent layer in caffe by yourself