Justin-Tan / generative-compression

TensorFlow Implementation of Generative Adversarial Networks for Extreme Learned Image Compression
MIT License
512 stars 106 forks source link

Loss term of entropy H(w_hat) #33

Open zs-zhong opened 4 years ago

zs-zhong commented 4 years ago

Hi, Justin-Tan,

Thanks for your code! After checking the code and the original paper, I didn't find the loss term of entropy H(w_hat) in your project. So is there no entropy loss part in your project? I also wonder how to compute this term. I hope to get your response. Thanks~