tomokishii

#
#   fashion_mnist_theano.py
#       date. 10/2/2017
#
#   REM: I read the article for stopping development of "THEANO".
#        The deep learning framework stimulated me and made me write codes. 
#        I'd like to say thank you to Theano supporting team.
#

import os

tomokishii

PyTorch Logistic Regression ~ MLP model

1. logistic_regression.py - Using torch.nn module, analysing sklearn DIGITS dataset
2. logistic_regression_low.py - NOT using torch.nn module, analysing sklearn DIGITS dataset
3. mnist_mlp.py

tomokishii

1. mnist_cnn.py - baseline code (till TF 1.2)
2. mnist_estimator.py - using TF 1.3 tf.estimator API

tomokishii

Chainer vs. PyTorch Linear Regression

1. linear_reg_chainer.py (Chainer version)
2. linear_reg_pytorch.py (PyTorch version)

• Python 3.5.2 (or 3.5.3)
• Chainer 2.0.0
• PyTorch 0.1.12

tomokishii

Modern Gradient Boosting models - how to use GridSearchCV

My current environment is...

• Python 3.5.2
• Scikit-learn 0.18.1
• XGBoost (python-package) 0.6
• LightGBM (python-package) v2.0

tomokishii

TensorFlow の名前空間を理解して共有変数を使いこなす

関連ファイル:

1. mnist_ae_varscope.py
2. mnist_2nets.py

tomokishii

Collaborative Filtering Tutorial Codes

The original codes comes from "Coursera Machine Learning" by prof. Andrew Ng, the program assignment of week 9.
I implemented this by Python,
1.Numpy + Scipy.Optimize
2.TensorFlow

• ex8_cofi.py: Numpy + Scipy.Optimize code
• check_costfun.py: support functions for ex8_cofi.py
• cofi_tf.py: TensorFlow code

tomokishii

tomokishii

tomokishii

#
#   tf_logistic_reg.py
#       date. 11/18/2015
#       date. 1/29/2017 - checked under tensorflow 0.12.1
#
#   The baseline is the code for 'Theano'.

from __future__ import print_function

import numpy as np