Vimos Tan

tffm is working quite well on my machine, much faster than other single core libraries like libfm and fastFM. But I found a small problem for regression, tffm tends to...

Another interesting point, tffm seems using a lot more memory, a recent test shows that after init with about 40GB memory, the peak for each epoch may reach 70-80GB, but...

@aneesh-joshi , maybe you can give my branch [Tf1.8](https://github.com/Vimos/bi-att-flow/tree/tf1.8) a try, I was able to run it last month.

@aneesh-joshi , try the tf1.8 branch, not the master branch.

@aneesh-joshi Glad that it's helping! The official repo has a `dev` branch which contains modifications to be compatible with `>Tf1.0`. Although I pulled their code, there are still some conflicts...

追问一下，CGED2020 的数据有单独的训练集合吗？ 我看文章说提供了 ``` We provide 1129 training units with a total of 2,909 grammatical errors, categorized as redundant (678 instances), missing (801), word selection (1228) and word ordering (201)....

May I ask if this freebase for WebQuestions or SimpleQuestions? Or it's just a subset for fun? Here are the stats for the freebase vdb ``` minghuan@heatwave-PowerEdge-R710 ➜ virtuoso ./bin/isql...

Thank you for the reply! I noticed that different researchers may use different freebase subset for research. Recently I tried to use this freebase to evaluate another work, but failed...

``` (base) ➜ Audio which python /home/vimos/anaconda3/bin/python (base) ➜ Audio python --version Python 3.8.8 ``` ``` (base) ➜ Audio pip install bypy -U Requirement already satisfied: bypy in /home/vimos/anaconda3/lib/python3.8/site-packages (1.7.2)...

超级会员，也无法突破500k，如果api开放会员身份识别也许能提升速度