Inception blocks behaviour

  • 3 Replies
  • 199 Views
*

Kaeldric

  • Roomba
  • *
  • 20
Inception blocks behaviour
« on: June 03, 2018, 03:01:19 pm »
Hello.

I'm studying the GoogLeNet by implementing a personal implementation in Tensorflow.
Last day I introduced a bug and changed the structure of the inception block a little.
Before that the algorithm run very poorly ... actually it never learned anything.  :(
After the modification (that changed the structure from the official paper one) the network start working as a charm  8) (with a little overfitting, but this is another story)!

You can find the two different structures here ---> https://imgur.com/a/vQiy0Te
where the bad one is the inception block described in the original paper and the good one is the modified version.

Is there a way to know why this modification leaded to a such big performance improvement?  ???

Thank you.  :)


*

spydaz

  • Trusty Member
  • ******
  • Autobot
  • *
  • 230
  • Developing Conversational AI (Natural Language/ML)
    • SpydazWeb
Re: Inception blocks behaviour
« Reply #1 on: June 03, 2018, 06:16:21 pm »
Hello.

I'm studying the GoogLeNet by implementing a personal implementation in Tensorflow.
Last day I introduced a bug and changed the structure of the inception block a little.
Before that the algorithm run very poorly ... actually it never learned anything.  :(
After the modification (that changed the structure from the official paper one) the network start working as a charm  8) (with a little overfitting, but this is another story)!

You can find the two different structures here ---> https://imgur.com/a/vQiy0Te
where the bad one is the inception block described in the original paper and the good one is the modified version.

Is there a way to know why this modification leaded to a such big performance improvement?  ???

Thank you.  :)

In this case the picture does not tell a thousand tales .... the pictures do not have enough information to make any sound judgement...at a glance its obvious that optimising the structure has made a difference although immeasurable but the information contained in the picture

*

Kaeldric

  • Roomba
  • *
  • 20
Re: Inception blocks behaviour
« Reply #2 on: June 03, 2018, 11:50:19 pm »
In short .... there is no way to know.  :)

*

spydaz

  • Trusty Member
  • ******
  • Autobot
  • *
  • 230
  • Developing Conversational AI (Natural Language/ML)
    • SpydazWeb
Re: Inception blocks behaviour
« Reply #3 on: June 04, 2018, 07:21:41 am »
In short .... there is no way to know.  :)

So a futile question

 


Users Online

37 Guests, 0 Users

Most Online Today: 50. Most Online Ever: 208 (August 27, 2008, 09:36:30 am)

Articles