HyperGAN
Search…
HyperGAN
About
Getting started
CLI guide
Configurations
Showcase
AI Explorer for Android
Youtube, Twitter, Discord +
Examples
2D
Text
Classification
Colorizer
Next Frame (video)
Tutorials
Training a GAN
Pygame inference
Creating an image dataset
Searching for hyperparameters
Components
GAN
Generator
Discriminator
Layers
Loss
Latent
Trainer
Optimizer
Train Hook
Adversarial Norm
Weight Constraint
Stabilizing Training
JARE
Learning Rate Dropout
Gradient Penalty
Rolling Memory
Other GAN implementations
Powered By
GitBook
Train Hook
Train hooks provide training events and loss modification to trainers.
​
https://github.com/HyperGAN/HyperGAN/tree/master/hypergan/train_hooks
​
Access
1
gan
.
trainer
.
train_hooks
# => [...]
Copied!
Train hooks are setup and invoked by the trainer.
Events
Override these methods to change the train loop
1
before_step
(
step
,
feed_dict
)
2
after_step
(
step
,
feed_dict
)
3
after_create
()
4
gradients
(
d_grads
,
g_grads
)
Copied!
before_step(feed_dict)
after_step(feed_dict)
Executed before/after the step takes place.
feed_dict
is what is being sent to the graph during the training step.
after_create()
Ran after the trainer is created.
gradients(d_grads, g_grads)
Refines the gradients before they are applied to the optimizer.
Components - Previous
Optimizer
Next
Adversarial Norm
Last modified
1yr ago
Copy link
Contents
Access
Events
before_step(feed_dict)
after_step(feed_dict)
after_create()
gradients(d_grads, g_grads)