search

accel-brain / accel-brain-code

The purpose of this repository is to make prototypes as case study in the context of proof of concept(PoC) and research and development(R&D) that I have written in my website. The main research topics are Auto-Encoders in relation to the representation learning, the statistical machine learning for energy-based models, adversarial generation networks(GANs), Deep Reinforcement Learning such as Deep Q-Networks, semi-supervised learning, and neural network language model for natural language processing.
https://accel-brain.co.jp
GNU General Public License v2.0
310 stars 92 forks source link

pygan true_sampler #11

Closed andrealbh closed 4 years ago

andrealbh commented 4 years ago

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?

chimera0 commented 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.

andrealbh commented 4 years ago

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.

accel-brain commented 4 years ago

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.

accel-brain commented 4 years ago

By the way, this model is not a model for predicting the true distribution. I suppose this model fundamentally does not meet your needs.