Three things we've released recently that I'm extremely excited about: 1. TensorFlow Cloud: add one-line to your notebook or project to start training your model in the cloud in a distributed way.https://keras.io/guides/training_keras_models_on_cloud/ …
-
Show this thread
-
2. Keras Preprocessing Layers: build end-to-end models that take as input raw strings or raw structured data samples. Handles string splitting, feature value indexing & encoding, image data augmentation, etc.https://keras.io/guides/preprocessing_layers/ …
4 replies 10 retweets 104 likesShow this thread -
3. KerasTuner: flexible and efficient hyperparameter tuning for Keras models.https://www.tensorflow.org/tutorials/keras/keras_tuner …
2 replies 18 retweets 136 likesShow this thread -
And in the pipeline: KerasCV and KerasNLP, domain-specific modeling packages.
2 replies 2 retweets 78 likesShow this thread -
Replying to @fchollet
Is there anything for audio processing in keras? If not, would love to see it
1 reply 0 retweets 0 likes
TF has some features for loading and processing audio data (not very advanced though), see this example:https://keras.io/examples/audio/speaker_recognition_using_cnn/ …
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.