Proposal: better training script.

[warmspringwinds]

Hello.

Thank you so much for such a great training script for FCN.

I wanted to offer a small improvement that you might find useful:

While using your script I was a little confused with the 3-stage training process for FCN-8.
I understood the idea that I have to first train FCN-32, then use those weights to fine-tune FCN-16, and finally use FCN-16 weights to fine-tune FCN-8 only after reading the original paper from Berkley.

I wrote a small add-on that makes it more clear and easier to do.

If you find it interesting, let me know, I can make a pull request.

[vedaldi]

Hi,

sure, thanks, I'll be happy to have a look.

Best wishes,

Andrea

On 19 Mar 2016, at 22:08, Daniil Pakhomov [email protected] wrote:

Hello.

Thank you so much for such a great training script for FCN.

I wanted to offer a small improvement that you might find useful:

While using your script I was a little confused with the 3-stage training process for FCN-8.
I understood the idea that I have to first train FCN-32, then use those weights to fine-tune FCN-16, and finally use FCN-16 weights to fine-tune FCN-8 only after reading the original paper from Berkley.

I wrote a small add-on that makes it more clear and easier to do.

If you find it interesting, let me know, I can make a pull request.

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub #19