borgwang

borgwang

import numpy as np
from sklearn.datasets import load_iris


def softmax(inputs):
    return np.exp(inputs) / np.sum(np.exp(inputs), 1)[:, None]


def construct_net(in_dim, out_dim, hidden_dim=20):
    bound1 = np.sqrt(6.0 / (in_dim + hidden_dim))

borgwang

class TrieNode(object):

    def __init__(self):
        self.children = dict()
        self.is_word = False


class TrieTree(object):

    def __init__(self):

borgwang

import numpy as np
import matplotlib.pyplot as plt

data = [[1.658985, 4.285136], [-3.453687, 3.424321], [4.838138, -1.151539],
        [-5.37971, -3.362104], [0.972564, 2.924086], [-3.567919, 1.531611],
        [0.450614, -3.302219], [-3.487105, -1.724432], [2.668759, 1.594842],
        [-3.15648, 3.191137], [3.165506, -3.999838], [-2.786837, -3.099354],
        [4.208187, 2.984927], [-2.123337, 2.943366], [0.704199, -0.479481],
        [-0.392370, -3.963704], [2.831667, 1.574018], [-0.790153, 3.343144],
        [2.943496, -3.357075], [-3.195883, -2.283926], [2.336445, 2.875106],

borgwang

from __future__ import division
import csv
import numpy as np
import random
import tensorflow as tf

# data prepare

X, y = [], []

borgwang

import numpy as np
import matplotlib.pyplot as plt
from PIL import Image


def eig_decomposition(img, p=0.9):
    A = np.array(img, dtype=float)
    mean_A = np.mean(A)
    A -= mean_A
    # calculate covarience matrix