Implementing a Convolutional Neural Network Using Only NumPy(victorzhou.com)

126 pointsby vzhou842vor 7 Jahren12 comments

Implementing a Convolutional Neural Network Using Only NumPy

https://victorzhou.com/blog/intro-to-cnns-part-2/

4 comments

vzhou842vor 7 Jahren

Hey, author here. Happy to hear any comments or answer any questions.

Runnable code from the article: https://repl.it/@vzhou842/A-CNN-from-scratch-Part-2

stuqqqvor 7 Jahren

You keep posting this a few times this week: https://news.ycombinator.com/from?site=victorzhou.com

minimaxirvor 7 Jahren

HN allows a small number of reposts for a given post if the original didn't get much traction.

In this case however, this particular is a Part 2 to a Part 1 that was successful on HN, which may not be sufficiently different.

vzhou842vor 7 Jahren

One of those was the prequel to this post: https://news.ycombinator.com/item?id=19981736 (titles are similar because content is similar)

The other two were reposts because they didn’t gain traction.

modsiwvor 7 Jahren

Did you change anything to help get traction? Seems to me that’s just a verbose way of saying you spammed it.

Cybiotevor 7 Jahren

The page contains superb, high quality work. I find the negativity in this branch incomprehensible. I and I suspect, many others, did not see any of the other times the author posted it. I am probably not alone in being glad they persevered at sharing it.

bjornsingvor 7 Jahren

Anon84vor 7 Jahren

Doesn't HN get rid of duplicates?

neurohackervor 7 Jahren

If you want to downsample segmentation produced from convnet output using only numpy, I have this technique to contribute :)

https://towardsdatascience.com/countless-high-performance-2x...

khasretovor 7 Jahren

Wow nice job in the next part you can implement regression :) , This is done better than my lectures do at university haha. Greetings

panpannavor 7 Jahren

Andrew Ng's coursed learn you to build CNN (and lots more) from scratch using only numpy.

Hope does this compare to that?

rahimnathwanivor 7 Jahren

Victor's CNN posts cover roughly the same ground as section 1 (of 4) of Andrew's CNN course.

Andrew's explanations in the videos are really well crafted, and cover the 'why' of everything clearly.

Sections 2-4 of Andrew's course cover more advanced CNN architectures, and also more advanced use cases that image classification.