Oleg Zabluda's blog
Tuesday, September 05, 2017
 
Deep learning for satellite imagery via image segmentation
Deep learning for satellite imagery via image segmentation
"""
In the recent Kaggle competition Dstl Satellite Imagery Feature Detection our deepsense.io team won 4th place among 419 teams. We applied a modified U-Net – an artificial neural network for image segmentation.
[...]
Competition

The challenge was organized by the Defence Science and Technology Laboratory (Dstl), an Executive Agency of the United Kingdom’s Ministry of Defence on Kaggle platform. As a training set, they provided 25 high-resolution satellite images representing 1 km2 areas. The task was to locate 10 different types of objects:

Buildings
Miscellaneous manmade structures
Roads
Tracks
Trees
Crops
Waterway
Standing water
Large vehicles
Small vehicles
"""
https://deepsense.io/deep-learning-for-satellite-imagery-via-image-segmentation/

https://deepsense.io/deep-learning-for-satellite-imagery-via-image-segmentation/

Labels:


- posted by Oleg Zabluda @ 8:02 PM | permalink | | | technorati | bloglines | feedster
 
Creating a Modern OCR Pipeline Using Computer Vision and Deep Learning
Creating a Modern OCR Pipeline Using Computer Vision and Deep Learning
https://blogs.dropbox.com/tech/2017/04/creating-a-modern-ocr-pipeline-using-computer-vision-and-deep-learning/
https://blogs.dropbox.com/tech/2017/04/creating-a-modern-ocr-pipeline-using-computer-vision-and-deep-learning/

Labels:


- posted by Oleg Zabluda @ 7:48 PM | permalink | | | technorati | bloglines | feedster
 
DIY Powerwall Builders Are Using Recycled Laptop Batteries to Power Their Homes
DIY Powerwall Builders Are Using Recycled Laptop Batteries to Power Their Homes
https://motherboard.vice.com/en_us/article/kzz7zm/diy-powerwall-builders-are-using-recycled-laptop-batteries-to-power-their-homes
https://motherboard.vice.com/en_us/article/kzz7zm/diy-powerwall-builders-are-using-recycled-laptop-batteries-to-power-their-homes

Labels:


- posted by Oleg Zabluda @ 11:01 AM | permalink | | | technorati | bloglines | feedster
 
Title


Labels:


- posted by Oleg Zabluda @ 9:13 AM | permalink | | | technorati | bloglines | feedster
 
"""
"""
the bottom 80% of men (in terms of attractiveness) are competing for the bottom 22% of women and the top 78% of women are competing for the top 20% of men. [...] a man of average attractiveness would be “liked” by approximately 0.87% (1 in 115) of women on Tinder. [...] attractiveness%=16.8*ln(like%)+52.3

"""
https://medium.com/@worstonlinedater/tinder-experiments-ii-guys-unless-you-are-really-hot-you-are-probably-better-off-not-wasting-your-2ddf370a6e9a
https://medium.com/@worstonlinedater/tinder-experiments-ii-guys-unless-you-are-really-hot-you-are-probably-better-off-not-wasting-your-2ddf370a6e9a

Labels:


- posted by Oleg Zabluda @ 9:00 AM | permalink | | | technorati | bloglines | feedster

Powered by Blogger