Daniel Jiwoong Im

I think β1,t ← 1 − (1 − β1)λ^(t−1) becomes close 1 and make the momentum degenerate (β1=0.1 here). This particular ADAM code was based on version 2 of the...

I don't think it is optimizer's problem, because ours work fine.. I suspect that the reason might be due to hyper-parameter tuning. Our pre-processed version of LSUN churches, living room...

Also get an error on nationality ``` File ".../python3.7/site-packages/sportsreference/nba/roster.py", line 331, in _parse_nationality nationality = NATIONALITY[nationality] KeyError: 'ni' ``` Need to add ``` ni: Niagara,``` to the `./nba/constant` file. Same...

I also notice the same thing. https://www.basketball-reference.com/boxscores/202010020LAL.html 202010020LAL game score is 124:114 But the API returns 56 for home team. ``` boxscore_obj = nba_boxscore.Boxscore(gamecode) (Pdb) boxscore_obj.__getattribute__('home_points') 56 ``` --------- Sidenote:...

I notice that i only have Hayao weights in checkpoint: [ji641@cassio AnimeGAN]$ ls checkpoint/ AnimeGAN_Hayao_lsgan_300_300_1_2_10 generator_Hayao_weight Is there only pretrained other models, or do i need to re-train? I don't...

Python main.py doesn't crush and runs on GTX1080. However it fails to train at all. When I trained on k40, python main.py works. I get "{'perplexity': 88.218780156903421, 'epoch': 24, 'valid_perplexity':...

Someone please take a look at this issue! The logs aren't being parsed properly on polygonscan amoy because the contracts haven't been verified.

我懂了。性能如何？ 性能真的好吗？

你能分享一下你在哪些 GPU 上进行训练吗？ 1080ti? 2080ti?

Thanks! I think you are missing one file though. It's called **synthetic_rnn_data** ```from synthetic_rnn_data import generate_synthetic_rnn_data```.