Notes about image processing.

Convolution

Implementation of convolution

• Implementing convolution as a matrix multiplication

提取灰度特征和边缘特征的卷积核：

# Set up a convolutional weights holding 2 filters, each 3x3
w = np.zeros((2, 3, 3, 3))

# The first filter converts the image to grayscale.
# Set up the red, green, and blue channels of the filter.
w[0, 0, :, :] = [[0, 0, 0], [0, 0.3, 0], [0, 0, 0]]
w[0, 1, :, :] = [[0, 0, 0], [0, 0.6, 0], [0, 0, 0]]
w[0, 2, :, :] = [[0, 0, 0], [0, 0.1, 0], [0, 0, 0]]

# Second filter detects horizontal edges in the blue channel.
w[1, 2, :, :] = [[1, 2, 1], [0, 0, 0], [-1, -2, -1]]

im2col

An example for im2col

Quick notes

• .d-none, hide elements
  • .d-{sm,md,lg,xl}-none
  • Tips: use d-none first, and specify screen display mode to cover it.
• container-fluid, full width container

Responsive breakpoints

Github issue: Bootstrap default breakpoints

Viewport dimensions.

• xs, extra small
  • \( xs \le 575.98px \)
• sm, small
  • \( 576px \le sm \le 767.98px \)
• md, medium
  • \( 768px \le md \le 991.98px \)
• lg, large
  • \( 992px \le lg \le 1199.98px \)
• xl, extra large
  • \( xl \ge 1200px \)

Take control over the viewport:

<meta name="viewport" content="width=device-width, initial-scale=1.0">

Links

• Docker cheat sheet
• Awesome docker

Quick notes

Commands

• docker images
• docker run -it ubuntu <shell>
  • -v <host_dir>/<container_dir>
  • -p
  • --rm, automatically aremove the container when it exists
• docker exec -it <container_name> bash
• docker history <image>
• 自下而上构建镜像层的缓存，<...>: Already existes
• docker ps
  • -a for all

• 2018-01-07 大钟寺博物馆-中华民族园博物馆-中国动物博物馆
• 2018-01-14 清华大学艺术博物馆-香巴拉户外用品专卖店-中国人民大学
• 2018-01-21 惠新西街南口-天坛
• 2018-01-28 石刻艺术博物馆-古代钱币展览馆（德胜门箭楼）
• 2018-02-05 西直门-阜成门-宣武门-中国铁道博物馆正阳门展馆-正阳门城楼
• 2018-03-04 中国海关博物馆（雄关漫道：丝绸之路上的谷关）-北京古观象台
• 2018-03-10 国家典籍博物馆-中国古动物馆-李大钊故居
• 2018-03-17 首都博物馆
  1. 天路文华，西藏历史文化展
  2. 读城，发现北京四合院之美

速记

龙之九子

• 龙有九个儿子，是跟谁生的？为什么「龙生九子，各不成龙」？ - 豆子的回答 - 知乎
• 龙有九个儿子，是跟谁生的？为什么「龙生九子，各不成龙」？ - 知乎

一说

龍生九子不成龍，各有所好：
囚牛，龍種，平生好音樂，今胡琴頭上刻獸是其遺像；
睚眦，平生好殺，今刀柄上龍吞口是其遺像；
嘲風，平生好險，今殿角走獸是其遺像；
蒲牢，平生好鳴，今鐘上獸鈕是其遺像；
狻猊，平生好坐，今佛座獅子是其遺像；
霸上，平生好負重，今碑座獸是其遺像；
狴犴，平生好訟，今獄門上獅子頭是其遺像；
贔屭，平生好文，今碑兩旁龍是其遺像；
蚩吻，平生好吞，今殿脊獸頭是其遺像。

李东阳（1447年－1516年） 《怀麓堂集》

出发

旧岁之末，新年伊始，我们来到了五台山。

这是我第一次进行多天的徒步。

去之前的心情还是比较放松的，因为从照片上看，五台山的山势平缓。

路，看起来相当的很好走。

仅有的一丝丝忐忑不安，仅仅是有点低的温度。

Notes about using Tensorflow

Quick notes

trainable: If True, the default, also adds the variable to the graph collection GraphKeys.TRAINABLE_VARIABLES. This collection is used as the default list of variables to use by the Optimizer classes.

Tensorflow gpu auto growth

config = tf.ConfigProto()
config.gpu_options.allow_growth = True

Reset default graph

tf.reset_default_graph()

Tensorboard

with tf.Session(config=config) as sess:

    # ...

    writer = tf.summary.FileWriter('./graphs/test', sess.graph)
    writer.flush()
    writer.close()

Startup tensorboard:

Course notes of CS231n, Convolutional Neural Networks for Visual Recognition.

2. Image Classification pipeline

• Challenges
  • Viewpoint variation 多视角
  • Illumination 光线
  • Deformation 变形
  • Occlusion 遮挡
  • Background Clutter 杂乱的背景
  • Intraclass variation 内类多样性
• Nearest Neighbor
  • Compute the distances of testing images and training images
  • \(L_n\) norm
    • \((\sum_{i}{|X^i|^n})^{\frac{1}{n}}\)
  • \(L_n\) distance
    • \((\sum_{i}{|X_1^i - X_2^i|^n})^{\frac{1}{n}}\)
  • method
    • For each testing image, find the nearest training image
    • Use the label of finding training image as the prediction
  • complexity
    • Training: \(O(1)\)
    • Testing: \(O(n)\)

MCB80x, the fundamental of neuroscience, is a free, open, online Neuroscience course from HarvardX led by Professor David Cox. Animation by Daniela Sherer + Music by Dan Deacon. Edited by Alex Auriema.

Welcome

• Harvard
• brain
• Three parts
  • explore science in Harvard and Boston
  • guided interactivity
  • DIY science
• Modules
  • THE ELECTRICAL PROPERTIES OF THE NEURON
    • signal generating, transfering
  • NEURONS AND NETWORKS
    • groups of neurons
  • THE BRAIN
    • society, intelligence

Quick notes

! Matlab start from 1, not 0 !

switch

dataset = 'minist';
switch(dataset):
    case 'cifar-10'
        code;
    case 'minist'
        code;
    otherwise
        error('Unrecognized dataset!')
end