New code walkthrough on http://keras.io : unsupervised image clustering with a contrastive loss.https://keras.io/examples/vision/semantic_image_clustering/ …
Show this thread
-
This example features a model with a custom `train_step()`. Overriding `train_step()` enables you to write arbitrary training logic (unsupervised clustering in this case) while benefiting from the features of `fit()`: callbacks, built-in distribution, step fusing on TPU...pic.twitter.com/XUaIt0TFyo
Show this thread
You can learn more about this pattern here:https://keras.io/guides/customizing_what_happens_in_fit/ …
-
-
@threader_app please compile it. -
Hey, the thread is ready and compiled. You can read the whole version here:https://threader.app/thread/1366431928799297537 …
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.