![]() |
Coursera Deep Learning MOOC by Andrew Ng Convolutional Neural Net |
Your byte size news and commentary from Silicon Valley the land of startup vanities, coding, learn-to-code and unicorn billionaire stories.
Sunday, November 12, 2017
Matrix Vector Representation of an Image - Image Classification for Machine Learning
Each pixel intensity can be represented with RGB values - red green blue. See this Coursera Deep Learning MOOC by Andrew Ng. The RGB data of an image is known as the three 3 channels. Each is a matrix. We vectorize the RGB data into feature matrix X. Dimension length of X is = width_pixel multiply by height_pixel multiply by number of channels 3. E.g. the digits in LSMNT are 28 by 28 by 1 because they are black and white, so instead of 3 channels, it only has one channel.
Subscribe to:
Post Comments (Atom)
Debug Google Cloud Error - Failed to enable API please make sure you have the IAM permission to enable API
If you are not expecting this message, and think you have the permission to enable API read on. Before using Google Cloud services, genera...

-
Can hack schools solve Silicon Valley's talent crunch? The truth about coding bootcamps and the students left behind http://t.co/xXNfqN...
-
In this downtown startup work space design the designers used fat boy bean bags and an extra wide step tiered staircase to create work space...
-
The bogus request from P2PU to hunt for HTML tags in real life has yielded a lot of good thoughts. My first impression was that this is stup...

No comments:
Post a Comment