Closed andrealbh closed 4 years ago
You just have to implement a subclass of the abstract class ConditionalTrueSampler
yourself. Only you know the distribution of the dataset you want to sample.
Thank you for your reply. I am a bit confused. I thought SinWaveTrueSampler generated a true sinwave dataset. But if I have already the true dataset, no need to generate more, how to implement the truesampler with existing true datasets? As I find the truesampler is needed for GAN train.
I don't think it has anything to do with this case, but this library has been extensively updated in the last 10 days, so please reinstall it just in case.
By the way, this model is not a model for predicting the true distribution. I suppose this model fundamentally does not meet your needs.
I tried to create a true sampler object from the existing numerical datasets via ConditionalTrueSampler but the error message said Can't instantiate abstract class ConditionalTrueSampler with abstract methods add_condition, draw. How can I create the true sample using my own data?