supriya-gdptl

Links to blogs that explain how attention mechanism works in Computer Vision and Natural Language Processing tasks.

1. Attention Mechanism by Heuritech Le Blog

2. Visual Attention Model in Deep Learning by Tristan

3. Attention and Menory in Deep LEarning and NLP: wildml post by Denny Britz

4. Attention in Convolutional Neural Nets by Dan Vatterott

odats

# TAVARES and PADILHA approach
def merge_line_segments(line_i, line_j, use_log=False):    
    # line distance
    line_i_length = math.hypot(line_i[1][0] - line_i[0][0], line_i[1][1] - line_i[0][1])
    line_j_length = math.hypot(line_j[1][0] - line_j[0][0], line_j[1][1] - line_j[0][1])
    
    # centroids
    Xg = line_i_length*(line_i[0][0]+line_i[1][0]) + line_j_length*(line_j[0][0]+line_j[1][0])
    Xg /= 2 * (line_i_length + line_j_length)
    

orangle

#!/usr/bin/env python
# -*- coding: utf-8 -*-
#python2.7x
#random_weight.py 
#author: orangleliu@gmail.com 2014-10-11

'''
每个元素都有权重，然后根据权重随机取值

输入 {"A":2, "B":2, "C":4, "D":10, "E": 20}

scturtle

import cv2
import numpy as np

canny = rho = threshold = minLen = maxGap = None


def draw():
    lines = cv2.HoughLinesP(canny, rho, np.pi / 180,
                            threshold, None, minLen, maxGap)
    dst = cv2.cvtColor(canny, cv2.COLOR_GRAY2BGR)