Meng-Jiun Chiou

Hi @JingweiJ Thank you for the response. Just wondering, do you have a rough time schedule for the next release? I am asking as I would like to make use...

Thanks for your prompt reply! I understand the model is inside this code base, I was wondering is there any explanation about the architecture.

Hi @KaihuaTang 麻烦花时间看下哈，我认为是个蛮明显的 Bug，我也提供修复 patch 开了 PR 了，帮助之后的人不犯相同错误

Hi @KaihuaTang Thank you for your reply. Actually, the current version (of randomly sampling a predicate if a pair got multiple predicates; L162-164) is just nice. A recent NeurIPS 2020...

Hi @SISTMrL have you solved the problem? Hi @RomeroBarata could you please just provide the original yaml? Why do we kind of need to "guess" the original config? Thank you...

Good catch, that makes sense. Please feel free to add a PR and report the revised numbers.

Hi, please change `test_orig` to `icube_test_rearange ` at Line 163: https://github.com/coldmanck/zero-shot-indoor-localization-release/blob/a6f040b7798674de845980d2715c5dd4517f1299/eval-gln.py#L163 as it's the name of ICUBE validation set. I have also fixed the line.

Hi @liangxuy and @jz462 I also encountered this problem during training on pytorch-1.0 branch. I am wondering whether it matters or not, as most of the training losses (as showed...

Same issue here. Hope to get an update :-(

Same issue here. @anette123 may I know if you have solved this problem?