Recurrent Neural Network (ver.Python) 참고자료¶https://www.tensorflow.org (TensorFlow) 출처¶https://medium.com/@erikhallstrm/hello-world-rnn-83cd7105b767 (How to build a Recurrent Neural Network in TensorFlow (1/7), Erik Hall strom) 함께보기¶Recurrent Neural Network (ver.R) Recurrent Neural Network (ver.Python)¶ In [1]: import tensorflow as tf import numpy as np import matplotlib.pyplot as plt num_epochs ..
Autoencoder (ver.Python) DATA SET 출처¶http://archive.ics.uci.edu/ml/datasets/Iris (UCI, Iris Data Set)https://gist.githubusercontent.com/netj/8836201/raw/6f9306ad21398ea43cba4f7d537619d0e07d5ae3/iris.csv (Github, Iris Data Set) 참고자료¶https://www.tensorflow.org (TensorFlow) 함께보기¶Autoencoder (ver.R) Clustering using Autoencoder (ver.Python)¶ Iris¶ In [1]: import pandas as pd In [2]: iris = pd.read_c..
Tensorflow-GPU installation on Ubuntu16.04 Tensorflow-GPU installation on Ubuntu16.04 https://www.tensorflow.org/install/install_linuxhttp://docs.nvidia.com/cuda/cuda-installation-guide-linux/#axzz4VZnqTJ2Ahttps://developer.nvidia.com/cudnn Tensorflow for R GPU버전 설치 on Ubuntu16.04 1 “CUDA® Toolkit 8.0” Installation 1.1 Pre-Installation actions. 1.1.1 Verify You Have a CUDA-Capable GPU 1.1.2 Veri..
MLP 출처¶http://jorditorres.org/first-contact-with-tensorflow/#cap5 (First Contact with tensorflow) Multi-layer Neural Networks in TensorFlow (ver. python)¶Convolutional Neural Network¶ The MNIST data-set¶ In [1]: import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("~/MNIST_data/", one_hot=True) Extracting ~/MNIST_data/train-imag..
Untitled 출처¶http://jorditorres.org/first-contact-with-tensorflow/#cap4 (First Contact with tensorflow) 단일신경망 Single Layer Neural Network (ver. python)¶ The MNIST data-set¶숫자 손글씨(hand-written digits)에 관한 엄청 유명한 데이터 셋.training set으로 6만개 이상, test set으로 1만개이다.흑백사진으로 이루어져있고, anti-aliasing 돼있다. 전 처리가 다 돼있기 때문에, 패턴인식을 시작하는 사람들에게 이상적이라고 한다.supervised learning의 한 예이다. In [1]: import tensorflow as tf from..
Clustering+ver_Python 출처¶http://jorditorres.org/first-contact-with-tensorflow/#cap3 (First contact with tensorflow) k-means 군집화 (ver. 파이썬)¶k-means Clustering (ver. Python)¶ 1. 좌표값 생성¶ In [1]: import numpy as np num_puntos = 2000 conjunto_puntos = [] for i in range(num_puntos): if np.random.random()
출처¶ http://jorditorres.org/first-contact-with-tensorflow/#cap2 (First contact with tensorflow) 선형 회귀분석 (ver. 파이썬)¶ linear regression (ver. Python)¶ 1. 좌표값 생성¶ numpy 모듈 임포트 In [1]: import numpy as np 좌표값 생성 In [2]: num_points = 1000 vectors_set = [] for i in range(num_points): x1 = np.random.normal(0.0, 0.55) y1 = x1 * 0.1 + 0.3 + np.random.normal(0.0, 0.03) vectors_set.append([x1, y1]) x_dat..