rotationnet
rotationnet copied to clipboard
  'r-cnn-release1-data.tgz' file doesn't work. Can you bring me the solution?
so, rotationnet use image. However, those images can not directly acquried from mesh data and point cloud data? then what is the point?
Hi, I am confused about how you handle both pose estimation and category classification. For this purpose, do you use different CNNs? When I have checked the code it seems...
Sorry for bothering you. I download initial weights for fine-tuning the models, but when I unzip the package, I got the following information: > gzip: stdin: not in gzip format...
When I try to run the training operation: ./caffe-rotationnet2/build/tools/caffe train -solver Training/rotationnet_modelnet40_case2_solver.prototxt -weights caffe_nets/ilsvrc_2012_train_iter_310k 2>&1 | tee log.txt I failed and get the information: *** Aborted at 1513600058 (unix time)...
I can make caffe, but not caffe-rotationnet2. Can anyone provide binaries for Windows/Linux?
Hello, I want to ask what is the value of Vi.For example, the example given in picture 2 in the paper,How are V1, V2 and V3 values.