You should probably opt for keras-cv or keras-nlp now as they integrate computer vision and nlp applications better, tensorflow_addons is soon going to be deprecated.
Probably the best association would be Keras (formerly separate from but now for some time integrated in TF - you can you Keras as a high level API).
Note that you can also use tensorflow_addons (I personally enjoy working with it) package and other libraries&wrappers that come into the aid of TensorFlow, because since Keras is integrated into TF, you will be also very likely to use them on your Keras code.
发布评论
评论（1）
注意：
您可能应该选择
KERAS-CV或KERAS-NLP现在，它们可以更好地集成计算机视觉和NLP应用程序，tensorflow_addons很快就会被弃用。最好的关联可能是Keras（以前与TF集成在一起，但现在已经整合了一段时间 - 您可以作为高级API的Keras）。
请注意，您还可以使用
tensorflow_addons（我个人喜欢使用它）包和其他库的包装器，这些包装器可以帮助TensorFlow的帮助，因为由于Keras已集成到TF中，因此您也很可能会很可能在KERAS代码上使用它们。NOTE:
You should probably opt for
keras-cvorkeras-nlpnow as they integrate computer vision and nlp applications better,tensorflow_addonsis soon going to be deprecated.Probably the best association would be Keras (formerly separate from but now for some time integrated in TF - you can you Keras as a high level API).
Note that you can also use
tensorflow_addons(I personally enjoy working with it) package and other libraries&wrappers that come into the aid of TensorFlow, because since Keras is integrated into TF, you will be also very likely to use them on your Keras code.