Comments (5)
请问您超参数用的是什么,建议您多跑几个epoch 调一下参数试试看,transe是个强基线效果不错的。
from openbg500.
您好!建议尝试一下https://github.com/OpenBGBenchmark/OpenBG-IMG/tree/main/TransE 中的参数设置。
from openbg500.
代码的参数设置是借鉴的OpenBG-IMG/tree/main/TransE 中的参数设置
`# dataloader for training
train_dataloader = TrainDataLoader(
in_path = data_path,
nbatches = 100,
threads = 8,
sampling_mode = "normal",
bern_flag = 1,
filter_flag = 1,
neg_ent = 25,
neg_rel = 0)
dataloader for test
test_dataloader = TestDataLoader(data_path, "link")
define the model
transe = TransE(
ent_tot = train_dataloader.get_ent_tot(),
rel_tot = train_dataloader.get_rel_tot(),
dim = 200,
p_norm = 1,
norm_flag = True)
define the loss function
model = NegativeSampling(
model = transe,
loss = MarginLoss(margin = 5.0),
batch_size = train_dataloader.get_batch_size()
)
train the model
trainer = Trainer(model = model, data_loader = train_dataloader, train_times = 1000, alpha = 1.0, use_gpu = True)
trainer.run()
transe.save_checkpoint('./checkpoints/openbg_500.ckpt')
`
最后跑出来的结果是这样的
`metric: MRR MR hit@10 hit@3 hit@1
l(raw): 0.000000 0.000000 0.000000 0.000000 0.000000
r(raw): 0.000018 131553.234375 0.000000 0.000000 0.000000
averaged(raw): 0.000009 65776.617188 0.000000 0.000000 0.000000
l(filter): 0.000000 0.000000 0.000000 0.000000 0.000000
r(filter): 0.000018 131553.234375 0.000000 0.000000 0.000000
averaged(filter): 0.000009 65776.617188 0.000000 0.000000 0.000000
type constraint results:
metric: MRR MR hit@10 hit@3 hit@1
l(raw): 0.000000 0.000000 0.000000 0.000000 0.000000
r(raw): 0.055832 479.256195 0.194600 0.044200 0.000000
averaged(raw): 0.027916 239.628098 0.097300 0.022100 0.000000
l(filter): 0.000000 0.000000 0.000000 0.000000 0.000000
r(filter): 0.055832 479.256195 0.194600 0.044200 0.000000
averaged(filter): 0.027916 239.628098 0.097300 0.022100 0.000000
MRR: 0.027916, MR: 239.628098, HITS@10: 0.097300, HITS@3: 0.022100, HITS@1: 0.000000
`
from openbg500.
你好,我尝试复现了一下,问题在于OpenKE中用于计算指标的文件是test文件,请你检查一下你的test文件是否包含完整的三元组。我们提供的OpenBG500数据集中所使用的test只包含头实体和关系,预测尾实体的过程需要像https://github.com/OpenBGBenchmark/OpenBG-IMG/tree/main/TransE 中一样,先把尾实体使用ent_000000来填充,然后再生成result文件,如果你遵循的是以上步骤,请你将result文件提交到阿里云天池OpenBG Benchmark中进行结果评测。如果你想在本地使用OpenKE取得正确的结果,请你使用以下数据集中的OpenBG500_answer.tsv文件来替代你的test文件进行模型评估,谢谢。
https://drive.google.com/file/d/1pD_icqV-lLbCXN2rfBaq-Y5i_XcKVCzM/view
from openbg500.
问题已经解决 感谢答疑!!
from openbg500.
Related Issues (3)
- 建议更新一下READEME HOT 2
- 关于模型参数和指标问题 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from openbg500.