You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
cur_seq_len shouldn't really be 1, which means the video only consists of one frame. But I guess there's no hurt checking that too. Thanks for the info!
Thanks for your reply and great work.
Besides, the code will throw out dimension mismatching error while fetching data as bellow:
'invalid argument 0: Sizes of tensors must match except in dimension 0. Got 4 and 3 in dimension 1 at /opt/conda/conda-bld/pytorch_1573049306803/work/aten/src/TH/generic/THTensor.cpp:689'
Maybe it is better to filter out the video sequences which is too short, like less than the seq_len_max ?
I think
t_step = np.random.randint(max_t_step) + 1
in ./data/base_dataset.py would throw an error whencur_seq_len
equals to 1.Maybe an if-clause like
if max_t_step==0: t_step=1
should be added to avoid crash while training?The text was updated successfully, but these errors were encountered: