jimmywangheng / knowledge_representation_pytorch Goto Github PK
View Code? Open in Web Editor NEWSeveral knowledge graph representation algorithms implemented with pytorch
License: MIT License
Several knowledge graph representation algorithms implemented with pytorch
License: MIT License
只在初始化里normalize了吧??
原paper的伪代码意思是每次loop都得normalize吧??
运行[python transH_pytorch.py -d FB15k]报错:
FileNotFoundError: [Errno 2] No such file or directory: './model/FB15k/l_0.001_es_0_L_1_em_100_nb_100_n_1000_m_1.0_f_1_mo_0.9_s_0_op_1_lo_0_TransH.ckpt'
请问是否少上传了什么文件 还是什么问题
I noticed that you used testList = random.choices(testList, k=k)
to randomly select validation examples. Does it mean the validation set is different every time and you just used one batch in validation? Thank you :)
(1)你好,运行你的代码报 [Errno 111] 。我是新建data文件夹,然后把FB15K文件夹拷贝过去。运行指令为:transE_pytorch.py -d FB15k -np 1 。我看了你的transE配置参数没看到相关HTTPConnection。升级了requests包也没用;
(2)错误提示行:trainCurve = agent.register(trainHyperparameters, 'train loss', overwrite=True)
r = requests.get(url, auth = self.auth, data = data);
(3)错误内容:requests.exceptions.ConnectionError: HTTPConnectionPool(host='127.0.0.1', port=5000): Max retries exceeded with url: /register (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7fdf7c5909b0>: Failed to establish a new connection: [Errno 111] Connection refused',))。
Is there any way to learn embeddings for entities which are not present in the dataset on which it is trained ?
您好,我能问一下关于transE中的normloss是用来干嘛的,我看原文中好像没有这个
推荐用 tensorboardX,贼好用,[手动滑稽]
one to one,one to many这些是分别代表啥实际含义啊?
Hi, what is the best performance (hits@10, mean rank) for each model in your experiments? Could you please share the results and settings?
datasets中的fb13和wn11都有对应的负例,求问如何得到fb15k和wn18对应的负例数据集合呢,非常感谢!
Traceback (most recent call last):
File "transE_pytorch.py", line 255, in
agent.append(trainCurve, epoch, total_loss[0])
File "/home/shan/venv/lib/python3.5/site-packages/hyperboard/agent.py", line 45, in append
value = value,
File "/usr/lib/python3.5/json/init.py", line 230, in dumps
return _default_encoder.encode(obj)
File "/usr/lib/python3.5/json/encoder.py", line 198, in encode
chunks = self.iterencode(o, _one_shot=True)
File "/usr/lib/python3.5/json/encoder.py", line 256, in iterencode
return _iterencode(o, 0)
File "/usr/lib/python3.5/json/encoder.py", line 179, in default
raise TypeError(repr(o) + " is not JSON serializable")
TypeError: tensor(253923.8438, device='cuda:0') is not JSON serializable
agent 报错,请问你用的 pyTorch 和 hyperboard 版本是多少呢?
Hi,
I met a problem when I tried the code "transR_pytorch.py" to run the demo data. The error messenge showed: No such file: './transE_%s_%s_best.pkl'. But, when I ran the script "transE_pytorch.py", it didn't generate any file like './transE_%s_%s_best.pkl'. May I know how I could generate './transE_%s_%s_best.pkl'?
Thank you and best regards.
Jianing
你好,代码里不包括这个预训练的模型吗,请问从哪里下载?
刚开始学习知识图谱的小白,希望得到解释!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.