Article

Cost I recently used GCP’s Document AI and was surprised by the cost, so I wrote it down. cost Form parser was 50 times more expensive than Document OCR; I thought Form parser was about the same as CloudVision, but it was almost 50 times more expensive and the bill was outrageous. If you are one of those people, you might want to be careful.
Python Tips A personal note on some useful notations for using python. github The jupyter notebook format file on github is here. google colaboratory If you want to run it in google colaboratory here 010/010_nb.ipynb) Author’s environment sw_vers ProductName: Mac OS X ProductName: Mac OS X ProductVersion: 10.14.6 BuildVersion: 18G95 Python -V Python 3.5.5 :: Anaconda, Inc. Fast aggregate retrieval after groupby in pandas A pandas specialist once told me about a fast way to get the results (DataFrame type) after a groupby.
GC (garbage collection) and reference counters in Python This is a personal note on some useful notations for using python. I’m not going to cover the basics, and I’m limiting this to things I’ve found useful. github The jupyter notebook format file on github is here. google colaboratory If you want to run it on google colaboratory here 009/009_nb.ipynb) Author’s environment sw_vers ProductName: Mac OS X ProductName: Mac OS X ProductVersion: 10.
tensorflow tutorials Text classification using RNN Now that tensorflow is 2.0, the tutorials have been updated. I would like to try to do all the tutorials in my environment for study. The code is a copy of the tutorials. The parts that I noticed and should be noted are the added value of this article. https://www.tensorflow.org/tutorials/text/text_classification_rnn?hl=ja !sw_vers ProductName: Mac OS X ProductVersion: 10.14.6 BuildVersion: 18G6032 Python -V Python 3.
tensorflow tutorials メモ tensorflowが2.0になってチュートリアルも新しくなりました。勉強がてら、すべてのチュートリアルを自分の環境で行ってみたいと
Currency (FX) prediction using RNN [In the previous article, I tried to predict the stock price, so I will try to predict the forex market. As with stock prices, there are a variety of factors that can cause fluctuations, so it will be difficult to make a prediction using only a neural network model, but I’ll try it as an exercise in Keras. github The file in jupyter notebook format is here google colaboratory If you want to run it in google colaboratory here Author’s environment The author’s OS is macOS, and the options are different from Linux and Unix commands.
Stock prediction using RNN, LSTM RNN and LSTM are used for forecasting time series data. There are many kinds of time series data, such as temperature of a certain place, number of visitors, price of a product, etc. However, I would like to use RNN and LSTM to predict the stock price, which is the easiest data to obtain. However, neural nets can only make predictions within the scope of the data obtained, and the model is almost useless when the situation is unexpected.
keras and sequnece to sequence In the previous article, we implemented the LSTM model, and now we will implement the sequence to sequence model. Nowadays, the sequnece to sequence and attention-based models are often used in natural language processing such as machine translation, and BERT is also based on the attention model. In this section, we will review and implement the basic sequnece to sequence. We will build a model that translates $y=\sin x$ to $y=\cos x$.
Basics of keras and GRU, Comparison with LSTM GRU is a model designed to compensate for the high number of parameters in LSTM, i.e., its high computational cost. It combines the operations of memory updating and memory forgetting into a single operation, thereby reducing the computational cost. I’ll spare you the details, as you can find plenty of them by searching. Here is a comparison between GRU and LSTM. github The file in jupyter notebook format is here google colaboratory If you want to run it in google colaboratory here Author’s environment The author’s OS is macOS, and the options are different from Linux and Unix commands.
Basics of keras and LSTM, Comparison with RNN LSTM stands for Long Short Term Memory, and is said to be able to learn long-term dependencies. LSTM is a type of RNN, and the basic idea is the same. I’m not going to go into the details, because you can find plenty of them by searching. Also, here is a comparison between LSTM and RNN. github The file in jupyter notebook format is here google colaboratory If you want to run it in google colaboratory here Author’s environment The author’s OS is macOS, and the options are different from Linux and Unix commands.