GuarderS opened this issue 3 years ago · 3 comments
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])
Would you mind providing more details, e.g., the hyper-parameters, and what the original data looks like?
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:
data_attribute:
data_feature:
我在两个地方改动了参数,第一个是example_train里面的config:
第二个是example_generate_data里面的config_generate_data:
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。
如果可以的话,我们可以邮件联系吗 PS: MU1758922095@163.com