Chainer sklearn wrapper
If you are familiar with machine learning before deep learning becomes popular, you might have been using sklearn (scikit-learn), which is very popula...
Author: corochann
Install Chainer
Once you have setup python environment, now we can install chainer. Nowadays it is important for deep learning library to use GPU to enhance its calculatio...
Setup python environment
※ This post is mainly just a summary/translation of the Japanese blog, データサイエンティストを目指す人のpython環境構築 2016 TL;DR; I recommend to install “anaconda” instead of...
Write predict code using concat_examples
This tutorial corresponds to 03_custom_dataset_mlp folder in the source code. We have trained the model with own dataset, MyDataset, in...
Training code for MyDataset
This tutorial corresponds to 03_custom_dataset_mlp folder in the source code. We have prepared your own dataset, MyDataset, in previous...
Create dataset class from your own data with DatasetMixin
This tutorial corresponds to 03_custom_dataset_mlp folder in the source code. In previous chapter we have learned how to train deep neural network using MNIST h...
Predict code for simple sequence dataset
Predict code is easy, implemented in predict_simple_sequence.py. First, construct the model and load the trained model parameters, Then we only specify the...
Chainer v2 released: difference from v1
Chainer version 2 has been released on 2017 June 1, #Chainer v2.0.0 has been released! Memory reduction (33% in ResNet), API clean up, and CuPy ...
Training RNN with simple sequence dataset
We have learned in previous post that RNN is expected to have an ability to remember the sequence information. Let’s do a easy experiment to check it before try...
Recurrent Neural Network (RNN) introduction
[Update 2017.06.11] Add chainer v2 code How can we deal with the sequential data in deep neural network? This formulation is especially important in natura...