Do you like the NumPy API? Do you wish you were able to write Keras models using the NumPy math syntax? You can! Find out how with this new tutorial on http://keras.io :https://keras.io/examples/keras_recipes/tensorflow_numpy_models/ …
-
Show this thread
-
You can learn more about the TensorFlow implementation of the NumPy API here: https://www.tensorflow.org/guide/tf_numpy It enables you to use TensorFlow as a distributable, GPU-accelerated NumPy. Fully compatible with Keras workflows.
1 reply 12 retweets 48 likesShow this thread
The one major difference with NumPy is that arrays aren't assignable -- you'll still have to use tf.Variable for storing mutable state.
12:27 PM - 30 Jul 2021
0 replies
3 retweets
14 likes
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.