最近在复盘今年上半年做的一些事情，不管是训练模型、部署模型搭建服务，还是写一些组件代码，零零散散是有一些产出。

BN是2015年论文Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift提出的一种**数据归一化方法**。现在也是大多数神经网络结构的**标配**，我们可能已经**熟悉的不能再熟...

When training with methods such as tf.GradientTape(), use tf.summary to log the required information.

Return a list of physical devices visible to the host runtime.

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 neede...

对着代码凭空想象，多少让人有点头皮微凉。于是，有人干脆用Unity给它完整3D可视化了出来。

https://github.com/oborchers/Medium_Repo/blob/master/Putting%20GPT-Neo%20into%20Production%20using%C2%A0ONNX/ONNX-Export.ipynb

我自己写的代码和该教程略有不一样，有三处改动，第一个地方是用归一化(均值为0，方差为1)代替数值缩放([0, 1])，代替的理由是能提升准确率

The Keras Tuner is a library that helps you pick the optimal set of hyperparameters for your TensorFlow program. The process of selecting the right set of hyper...

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 import...