DCGAN overriding training step- Keras 3 Migration (Only Tensorflow Backend) #1693
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
fchollet
reviewed
Dec 24, 2023
| @@ -154,10 +156,10 @@ def train_step(self, real_images): | |||
| ) | |||
|
|
|||
| # Sample random points in the latent space | |||
| random_latent_vectors = tf.random.normal(shape=(batch_size, self.latent_dim)) | |||
| random_latent_vectors = keras.random.normal(shape=(batch_size, self.latent_dim)) | |||
There was a problem hiding this comment.
Critically, this needs to be seeded with a SeedGenerator instance attached to the model.
There was a problem hiding this comment.
Sure, made the required changes
fchollet
reviewed
Dec 29, 2023
| import matplotlib.pyplot as plt | ||
| import os | ||
| import gdown | ||
| from zipfile import ZipFile | ||
|
|
||
| seed_generator = keras.random.SeedGenerator(42) |
There was a problem hiding this comment.
The seed generator must be attached to the layer. So you should do:
class GAN(keras.Model):
def __init__(self, **kwargs):
...
self.seed_generator = keras.random.SeedGenerator(1337)
sineeli
commented
Dec 30, 2023
| @@ -185,9 +193,13 @@ class GANMonitor(keras.callbacks.Callback): | |||
| def __init__(self, num_img=3, latent_dim=128): | |||
| self.num_img = num_img | |||
| self.latent_dim = latent_dim | |||
| self.seed_generator = keras.random.SeedGenerator(42) | |||
There was a problem hiding this comment.
Hope this is the correct way to declare for epoch end random number generation
fchollet
reviewed
Dec 31, 2023
|
Retrained and generated the required files, Thanks! |
37 tasks
SuryanarayanaY
pushed a commit
to SuryanarayanaY/keras-io
that referenced
this pull request
Jan 19, 2024
…ckend) (keras-team#1693) * Migrate to Keras 3 * Keras 3 Migration * Add seed generator to keras.random * Train using seed generator * Update dcgan_overriding_train_step.py * Rgenerate files * Migration to Keras 3 * Revert "Migration to Keras 3" This reverts commit 7b003f5.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
DCGAN overriding training step- Keras 3 Migration (Only Tensorflow Backend) fix it - KerasCV-Fixit