zeakey / ldlforests Goto Github PK

Hi,
Thank you very much for sharing your code. One thing that puzzles me is that the code dose not provide "data/ldl/get_ldl.sh" . The link “http://kaiz.xyz/ldlf” you provided also seems to have expired. Can you upload the data again?
I am very looking forward to your help.
Best wishes!
Chen

Hi,

I am trying to run the ipython notebook demo, but I cannot seem to find the pretrained model and prototxt mentioned in the repo. Could you please provide the pretrained model and prototox mentioned in the ipynb -

Morph-deploy-ratio0.6.prototxt
Morph-Ratio0.6_iter_10000.caffemodel

TIA

Hi

While running the run.py I received the following error:

Check failed: bottom[1]->shape()[1] == neural_decision_forest_param.num_classes() (5 vs. 2) num_classes_ must be equal to bottom[1]->shape[1]

I am using the Movie.mat from the Dataset as set in the code, and for both test-kld.prototxt and train.prototoxt , output_num: 512, what am I doing wrong?

Thanks.

EDIT: I commented out the assertion check in neural_decision_forest_layer.cpp , and it worked.

      //  CHECK_EQ(bottom[1]->shape()[1], neural_decision_forest_param.num_classes())
        //         <<"num_classes_ must be equal to bottom[1]->shape[1]!";

Thank you for sharing the code! I tried to run the code in CPU-ONLY mode on the Ubuntu 16 system, but there was an error (as shown below):

/usr/lib/python2.7/dist-packages/matplotlib/__init__.py:1352: UserWarning: This call to matplotlib.use() has no effect because the backend has already been chosen;
matplotlib.use() must be called *before* pylab, matplotlib.pyplot, or matplotlib.backends is imported for the first time.

warnings.warn(_use_error_msg)
WARNING: Logging before InitGoogleLogging() is written to STDERR F0420 12:41:10.873113 4844 common.cpp:66] Cannot use GPU in CPU-only Caffe: check mode.
*** Check failure stack trace: ***
Aborted (core dumped)