darren1231

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

1.Abstract

類神經網路在近幾年已取得巨大的突破，從最開始的Perceptron一直演化到AlexNet、VGG，精確度一直不斷的往上提升，但伴隨著的是模型複雜化，過度複雜的模型使得運算量極大以至於不能在低階產品(如手機上)運行，MobileNet的發明就是為了解決這想法而產生的，文中和許多當前有名的框架互相比較(Inception V3、VGG)，速度真的提升許多，雖然精確度有稍許下降，但也都控制在可以接受的範圍內。

2.Main idea

文中最核心的思想就是把傳統的卷積過程簡化成計算量更少的過程，算式並沒有完全等效，但有趨近於等效的功用，主要是把過程分成Depthwise convolution 和 pointwise convolution，文中用公式來舉例說明

darren1231

# ydata = b + w * xdata 
b = -120 # initial b
w = -4 # initial w
lr = 1 # learning rate
iteration = 100000

b_lr = 0.0
w_lr = 0.0

# Store initial values for plotting.

darren1231

# ydata = b + w * xdata 
b = -120 # initial b
w = -4 # initial w
lr = 0.0000001 # learning rate
iteration = 100000

# Store initial values for plotting.
b_history = [b]
w_history = [w]

darren1231

from matplotlib import pyplot as plt
import numpy as np
x_data = [ 338.,  333.,  328. , 207. , 226.  , 25. , 179. ,  60. , 208.,  606.]
y_data = [  640.  , 633. ,  619.  , 393.  , 428. ,   27.  , 193.  ,  66. ,  226. , 1591.]

x = np.arange(-200,-100,1) #bias
y = np.arange(-5,5,0.1) #weight
Z =  np.zeros((len(x), len(y)))
X, Y = np.meshgrid(x, y)
for i in range(len(x)):

darren1231

# -*- coding: utf-8 -*-
"""
Created on Sun Jun 10 16:41:39 2018

@author: darren
"""


import pandas as pd
import requests

darren1231

import cv2
import numpy as np


def draw_flow(img, flow, step=16):
    h, w = img.shape[:2]
    y, x = np.mgrid[step/2:h:step, step/2:w:step].reshape(2,-1).astype(int)
    fx, fy = flow[y,x].T
    lines = np.vstack([x, y, x+fx, y+fy]).T.reshape(-1, 2, 2)
    lines = np.int32(lines + 0.5)    

darren1231

import cv2

# Install instruction on Anaconda:
# conda install -c https://conda.anaconda.org/menpo opencv3
# OpenCV version: 3.1.0
# python version: 3.5.1


# 讀入圖片 (處理用)

darren1231

Sub fast()
        
    original_col = 26
    original_row = 106
    Do Until original_col = 1
        cut_number = copy_cut(original_row, original_col)
        original_col = original_col - cut_number
        If original_col = 1 Then
            Exit Do
        End If

darren1231

Public Function main()
    
     
    
    For all_row = 2 To 6
        been_chose_group = group_pick(all_row)
        
        For n_row = 2 To 6
            Cells(6 + n_row + 2, all_row) = been_chose_group(n_row, 0)
        Next n_row

darren1231

/* Markdown.css */
/* Authors: Kevin Burke: http://kev.inburke.com/, modified by Evan Wondrasek  */
/* https://bitbucket.org/kevinburke/markdowncss */


body{
    margin: 0 auto;
    font-family: Georgia, Palatino, serif;
    color: #444444;
    line-height: 1;