Zhen

Local Response Normalization (LRN) in different frameworks.

2018-09-19
Local Response Normalization (LRN) has different implementations in different Frameworks.

Caffe

Document
- Parameters (LRNParameter lrn_param) Optional
  - local_size [default 5]: the number of channels to sum over (for cross channel LRN) or the side length of the square region to sum over (for within channel LRN)
  - alpha [default 1]: the scaling parameter (see below)
  - beta [default 5]: the exponent (see below)
  - norm_region [default ACROSS_CHANNELS]: whether to sum over adjacent channels (ACROSS_CHANNELS) or nearby spatial locations (WITHIN_CHANNEL)
- 计算公式
\[b_{x,y}^i = a_{x,y}^i \left(1 + \frac{\alpha}{n} \sum_{j=\max(0, i-n/2)}^{\min(N-1,i+n/2)}a_{x,y}^2\right)^{-\beta}\]
TensorFlow

different from Caffe version. refer to this post.
- 计算公式
\[b_{x,y}^i = a_{x,y}^i \left(b + \alpha \sum_{j=\max(0, i-r)}^{\min(N-1,i+r)}a_{x,y}^2\right)^{-\beta}\]
PyTorch

Document

same as Caffe version, the parameters can be used directly.
- 计算公式
\[b_{c} = a_{c}\left(k + \frac{\alpha}{n} \sum_{c'=\max(0, c-n/2)}^{\min(N-1,c+n/2)}a_{c'}^2\right)^{-\beta}\]
Read All
Crawl data and import to Google Spreadsheet

2018-07-22
1. using scrapy or any other tools you like to crawl data
2. using gspread, a 3rd party Google Spreadsheet API wrapper in Python
links
- https://city.shaform.com/zh/2016/03/19/gspread/
- https://github.com/burnash/gspread
Read All
She is NOT that into you

2018-06-12
Not everyone going to like you, There are plenty of fish in the sea.
1. Sibling comparison
2. Unresponsive to advances
3. Crush talk
4. Friend zoned
5. Group events only
6. Always busy
7. Ask for relationship advice
8. Only go to you when they need stuff
9. No flirting
10. They don’t dress up
11. Try to set you up
12. Just not interested
links
- https://weibo.com/1666978981/GkSn47gmX
- http://psych2go.net
Read All

21/35

Local Response Normalization (LRN) in different frameworks.

Caffe

TensorFlow

PyTorch

Crawl data and import to Google Spreadsheet

links

She is NOT that into you

links