Disclaimer: not for financial recommandation, educational purpose only.
The interest rate is farely low right now, however, is it really a free lunch to refinance - even no point no fee? I am going to show you how to analyze it by yourself. This is just a toy model, for your investment, please do your own due diligence.
Tensorflow community keeps improving to address problems with Tensorflow.
At the time of TF 2.0 release, I sitll found it is very painful to follow the TF documentation to get things done. Here I write down some random notes during my short journey to use TF Lite for the quantization. Also I hope this tour can guide some other people to find an easier life when use TF.
This article introduces the TensorFlow profiler for Python user in practice. First, I will present the basic configuration for the profiler, then I use an example to show how to integrate it with existing code. In the end, I conclude with how to access the results from the profiler's output.
TensorFlow profiler (profiler hereafter) is a tool for analyzing deep neural network and performance tuning.
This is a note on reducing randomness in model training in Keras. In the official documentaion, you can find a solution to fix the randomness. In the following, I am trying to disentangle different contributions.
More investigation on the code level is needed to understand the full picture. However, it is out of the scope of this work.