Pages: 1 ... 3 4 [5]   Go Down

Author Topic: Camera calibration using a neural network: questions  (Read 2042 times)

32BT

  • Sr. Member
  • ****
  • Offline Offline
  • Posts: 2911
    • Pictures
Re: Camera calibration using a neural network: questions
« Reply #80 on: June 10, 2019, 02:52:04 am »


For me it's clear that going beyond (16,16) NN's for Lab models and beyond (4,4) for XYZ models doesn't add, so it's just invoking: "overfitting, come to me". This makes sense looking at the DeltaE evolution we already saw, which was actually very insightful in finding out where to stop regarding NN complexity:

Regards

It's also interesting to mention perhaps that it takes at least 3 nodes to produce a perceptual curve, while it takes only 1 node to properly represent linear, despite a tanh activation curve. Which probably explains why XYZ performs so much better as far as complexity is concerned.

This entire exercise raises one additional question that might be useful as amendment: how does a one layer config perform?

And, for some future exercise, it would be interesting to know what happens if you could define a custom activation function.
Logged
Regards,
~ O ~
If you can stomach it: pictures

Jack Hogan

  • Sr. Member
  • ****
  • Offline Offline
  • Posts: 780
    • Hikes -more than strolls- with my dog
Re: Camera calibration using a neural network: questions
« Reply #81 on: June 11, 2019, 09:08:50 am »

Excellent job Guillermo, starting to make sense now.
Logged

Guillermo Luijk

  • Sr. Member
  • ****
  • Offline Offline
  • Posts: 1810
    • http://www.guillermoluijk.com
Re: Camera calibration using a neural network: questions
« Reply #82 on: June 16, 2019, 08:37:10 am »

Doing some infographics to decorate the story:



Regards

Jack Hogan

  • Sr. Member
  • ****
  • Offline Offline
  • Posts: 780
    • Hikes -more than strolls- with my dog
Re: Camera calibration using a neural network: questions
« Reply #83 on: June 20, 2019, 05:21:36 pm »

Nice!
Logged
Pages: 1 ... 3 4 [5]   Go Up