TaeSoo-Kim

In classifier_entropy.py, I change the line: `acc_per_class /= target_classes.size(0)` to the following: `acc_per_class = acc_per_class / float( target_classes.size(0))` I observed 0 accuracies as well before this fix.

Autoom, feat_dim refers to the dimension of the per-frame feature. For this particular dataset (NTURGBD-skeletons), feat_dim should be 150 per frame (at most 2 actors, 25 joints per actor, 3...

Yes, this is a known issue. I believe the convention must have changed since when I first wrote this code (as indicated by the consistent results.) Thanks for letting us...

I have not tried the same experiments with the updated NTU+Keras 2.1. I am curious to see what do results look like with the new setup as well.

Hi Jue, Cross_subject and cross_view weights are added under weights/ directory. Thanks, TK

The shared weights are for the raw input

I believe this data I/O code is quite outdated. I dont think it is necessary anymore to read/write from lmdb anymore with current library's I/O speeds

Yes, I believe speed will not be an issue

sorry for the delayed response, did you have a chance to resolve this?