Hao Tang
I see @ennauata, now I have another question. Do we need to train 5 models to evaluate 5 different groups? Specifically, - To evaluate `1-3`, we need to train a...
@ennauata thanks, now I have two more questions. What does `--num_variations` mean? and how to select an image to compare with other methods in Fig. 6 of your paper since...
Thanks again. Can you share the generated results of other baselines (i.e., CNN-only, GCN, Ashual et al., and Johnson et al.) with me? My email is [email protected], in this way,...
@ennauata when I run `python evaluate_parallel.py`, I get the following error: > Traceback (most recent call last): > File "evaluate_parallel.py", line 239, in > run_parallel(graphs) > File "evaluate_parallel.py", line 225,...
+1
Hi, the code will be released after the NIPS deadline. Please stay tuned!
How to train 64*64 images with the code you provided? Thanks.
@kregmi can you release `mynetG_64_64` and `crossview_G_64` so that I can train with 64*64 image resolution?
Hao Tang is a tenure-track professor at the School of Computer Science, Peking University, see https://cs.pku.edu.cn/info/1227/3210.htm