search

yun-liu / RCF

Richer Convolutional Features for Edge Detection
Other
758 stars 260 forks source link

Run RCF-multiscale.ipynb failed: Un #66

Open Lotayou opened 5 years ago

Lotayou commented 5 years ago

I installed caffe with python support successfully and has already trained with several other projects. However, when testing with your ipynb notebook (which I copied all the code and pasted them in a new python file), I encountered the following error.

By the way, I already changed the caffe syspath to where my caffe is installed.

Here's the error log, seems like some layer is not recognized.

(caffe) eric@eric-XPS-8920:~/projects/rcf/examples/rcf$ python RCF-multiscale.py
WARNING: Logging before InitGoogleLogging() is written to STDERR
F1120 20:46:58.500839 19654 layer_factory.hpp:81] Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: AutoCrop (known types: AbsVal, Accuracy, ArgMax, BNLL, BatchNorm, BatchReindex, Bias, Concat, ContrastiveLoss, Convolution, Crop, Data, Deconvolution, Dropout, DummyData, ELU, Eltwise, Embed, EuclideanLoss, Exp, Filter, Flatten, HDF5Data, HDF5Output, HingeLoss, Im2col, ImageData, InfogainLoss, InnerProduct, Input, LRN, LSTM, LSTMUnit, Log, MVN, MemoryData, MultinomialLogisticLoss, PReLU, Parameter, Pooling, Power, Python, RNN, ReLU, Reduction, Reshape, SPP, Scale, Sigmoid, SigmoidCrossEntropyLoss, Silence, Slice, Softmax, SoftmaxWithLoss, Split, TanH, Threshold, Tile, WindowData)
*** Check failure stack trace: ***
Aborted (core dumped)

can you help me with this error? Thanks!

yun-liu commented 5 years ago

Please use my Caffe, other than the standard Caffe.