H13-311_V3.5 · Question #266
The following belongs to TensorFlow2.0 The characteristic is?
The correct answer is A. Introduce Keras interface C. Support more platforms and more languages D. Continue to be compatible Tensorflowl.x Related modules. TensorFlow 2.0 made Keras its official high-level API (A), deeply integrating tf.keras to simplify model building - this was one of the flagship changes of the 2.0 release. It also expanded support for more platforms (mobile, browser via TF.js, edge devices) and additional…
Question
The following belongs to TensorFlow2.0 The characteristic is?
Options
- AIntroduce Keras interface
- BSupport static image mechanism
- CSupport more platforms and more languages
- DContinue to be compatible Tensorflowl.x Related modules
How the community answered
(28 responses)- A75% (21)
- B25% (7)
Explanation
TensorFlow 2.0 made Keras its official high-level API (A), deeply integrating tf.keras to simplify model building - this was one of the flagship changes of the 2.0 release. It also expanded support for more platforms (mobile, browser via TF.js, edge devices) and additional language bindings (C), and provided the tf.compat.v1 module to maintain backward compatibility with TensorFlow 1.x code (D).
Option B is the distractor and the key conceptual point: TF 1.x relied on a static computation graph (build-then-run), while TF 2.0 switched to eager execution (dynamic, define-by-run) as the default - the opposite of what B claims.
Memory tip: Think "2.0 = Dynamic + Keras + Wider reach + Backward compat." The one thing TF2.0 dropped as default was the static graph - if an option praises static graphs as a TF2.0 feature, it's a trap.
Topics
Community Discussion
No community discussion yet for this question.