摘要：Tensor，它能够是0维、一维以及多维的数组，你能够将它看作为神经网络界的Numpy，它与Numpy类似，二者能够共享内存，且之间的转换十分不便。

In machine learning, to improve something you often need to be able to measure it. TensorBoard is a tool for providing the measurements and visualizations needed during the machine learning workflow. It enables tracking experiment metrics like loss and accuracy, visualizing the model graph, proje…

Physical devices are hardware devices present on the host machine. By default all discovered CPU and GPU devices are considered visible.

This notebook classifies movie reviews as positive or negative using the text of the review. This is an example of binary—or two-class—classification, an important and widely applicable kind of machine learning problem.

TensorFlow makes it easy for beginners and experts to create machine learning models. See the sections below to get started.

In the featurization tutorial we incorporated multiple features beyond just user and movie identifiers into our models, but we haven’t explored whether those features improve model accuracy.

To select rows whose column value equals a scalar, some_value, use ==:

tensorflow的以及全面更新到tf2，其官网显示老版本的tensorflow 1.15只反对python3.7以及cuda10，并且新版本的ubuntu的官网apt源基本没有python3.7。

tf的estimator api应用起来十分不便，填充下几个函数，就能写出高度结构化的模型代码。但封装越高级，应用中一旦遇到问题，解决起来就会相当麻烦。

应用事后训练的模型进行特征提取：应用小型数据集时，通常的做法是利用在雷同域中的较大数据集上训练的模型中学习的特色。这是通过实例化预训练的模型并在顶部增加齐全连贯的分类器来实现的。事后训练的模型是“解冻的”，训练过程中仅更新分类器的权重。在这种状况下，卷积根底提取了与每个图像关联的所有特色，而您刚刚…