Face-generation-GAN
Face-generation-GAN copied to clipboard
Generate realistic human images that do not exist in reality using GAN
Hi, is it possible to generate headshot like images using this repo, with solid background? Thank you.
I am a bit new to GANs and Neural Networks in general. I noticed that the loss remains more or less stagnant throughout the epochs. Why does this happen? ![image](https://user-images.githubusercontent.com/55236006/144064740-43bd2e68-8374-4bba-ab0f-afb05ee24d0d.png)
I'm getting a new error now. I'm using tf 2.1.0. Keras installs: ``` Keras 2.1.0 Keras-Applications 1.0.8 Keras-Preprocessing 1.1.2 ``` ``` --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in 64...
I'm `from keras import Input` I receive this error: module `'keras.utils.generic_utils' has no attribute 'populate_dict_with_module_objects'` ``` --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in ----> 1 from keras import Input...
How would one save the state of the model so that the program does not have to train every single time the program is launched. I have very limited hardware...
Hello, would that be possible for you to do that?