Xinwei He
Xinwei He
below is the script i am doing testing stuff on loading octree data: ``` package.path = package.path .. ';'.. '/home/name/project/octnet/th/oc/init.lua' require 'oc' data_cpu = oc.FloatOctree() -- works okay data_cpu:read_from_bin_batch({'./test_octrees/chair_128.oc'}) --...
Hi, in your code, [here](https://github.com/charlesq34/3dcnn.torch/blob/master/train.lua#L116) and [here](https://github.com/charlesq34/3dcnn.torch/blob/master/train.lua#L159) in train.lua (also similarly in train_mo.lua file), you assume the output of the models can be a table, and will take out the...
[here](https://github.com/iwasaki-kenta/keita/blob/ade6fd06ba5f1d58f351f5ecb550404f6758f4b8/losses/mahalanobis.py#L86), i suppose there is an error by dividing loss by num_pairs, because num_pairs may be 0 ( dividing 0 error).
I know that you split you dataset into train set and valid1 and valid2, but you used the calibration set in you training technique. can you tell me what the...
[here](https://github.com/s-gupta/visual-concepts/blob/master/run_mil.py#L40-L43)
Patch 1
hi, @szagoruyko , can not load model with only the prototxt file?
Hi, i am new to shape research. I was wondering if this repository supports torch interface of extraction of features for voxel data folder which contains the volumetic data?