search

fjxmlzn / DoppelGANger

[IMC 2020 (Best Paper Finalist)] Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
http://arxiv.org/abs/1909.13403
BSD 3-Clause Clear License
296 stars 75 forks source link

The data generated ranges from 0 to 2 #28

Closed GuarderS closed 2 years ago

GuarderS commented 2 years ago

The trained model produces data in the range of [0-2], which I cannot restore to its original size by multiplying a value. Do you know what caused it? ( I guess the range should be [0-1]) image

fjxmlzn commented 2 years ago

Would you mind providing more details, e.g., the hyper-parameters, and what the original data looks like?

GuarderS commented 2 years ago

感谢您能回复我，我访问了您的主页，发现您是清华大佬，如果不介意的话我想用中文来描述，可能比较准确一点。 date_attribute_outputs and data_feature_outputs: image

data_attribute: image

data_feature: image

我在两个地方改动了参数，第一个是example_train里面的config： image

第二个是example_generate_data里面的config_generate_data： image

date_attribute是五维的代表五种事件，data_feature是二维的，分别是纬度和经度，除以一个数使其范围变成了0-1。

GuarderS commented 2 years ago

如果可以的话，我们可以邮件联系吗 PS: MU1758922095@163.com