diff --git a/README.md b/README.md index 68299b7a..baf26aef 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,5 @@ +# Making changes in README.md file + # What's new in TensorFlow 2.x The following are all the changes coming in TensorFlow 2.x. Let's have a closer look at them: @@ -14,14 +16,16 @@ The following are all the changes coming in TensorFlow 2.x. Let's have a closer * Tidying up the API * The conversion tool * Alternative variable scoping - + + ## Eager Execution + Lack of eager execution was one of the main complaints against TensorFlow. We all can relate. Having to execute the whole graph and then trying to debug based on the errors was very tedious. Especially, since values of intermediate results haven't been accessible without printing them out by mixing in debug statements into the production code. -With TensorFlow 2.0, eager execution is activated by default and the very cool thing is that the code nearly doesn't change. Under the hood, you are just working with so-called "EagerTensors" instead of "Tensors" but since they share the same interface, the difference is barely noticeable. Even in execution speed, the difference is hard to see. +With TensorFlow 2.0, eager execution is activated by default and the very cool thing is that the code nearly doesn't change. Under the hood, you are just working with so-called "EagerTensors" instead of "Tensors" but since they share the same interface, the difference is barely noticeable. Even in execution speed, the difference is hard to see. This means, from now on, TensorFlow code can be used and debugged as ordinary python code (using numpy for example). This is one aspect of making TensorFlow more pythonic. @@ -32,7 +36,8 @@ Below there are two tasks. I highly recommend doing them because while watching 1. [Watch me coding](https://www.youtube.com/watch?v=J3_b4461qxU) -2. [Code yourself](https://github.com/romeokienzler/TensorFlow/blob/master/notebooks/tf2.eagerexec.ipynb) + +1. [Code yourself](https://github.com/romeokienzler/TensorFlow/blob/master/notebooks/tf2.eagerexec.ipynb) ## Integration of the Keras API @@ -49,7 +54,8 @@ For now, just follow along the video and code exercise below to get an idea how 1. [Watch me coding](https://www.youtube.com/watch?v=D4mJZQdgV0Y) -2. [Code yourself](https://github.com/romeokienzler/TensorFlow/blob/master/notebooks/tf2.keras.ipynb) + +1. [Code yourself](https://github.com/romeokienzler/TensorFlow/blob/master/notebooks/tf2.keras.ipynb)