upload the training and testing dataset about machine-learning-for-image-colorization HOT 6 CLOSED

Is there any requirement for the training and testing images? (Like portrait or landscape or blahblah)

from machine-learning-for-image-colorization.

Not really.

On Saturday, 5 November 2016, Chong Guo [email protected] wrote:

Is there any requirement for the training and testing images? (Like
portrait or landscape or blahblah)

—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
#2 (comment),
or mute the thread
https://github.com/notifications/unsubscribe-auth/AEbvNJcd-1kNojEzsSL7HgjT-qWFqS9gks5q7XTggaJpZM4Kqe0t
.

from machine-learning-for-image-colorization.

I think you mistook my meaning. What I do is to split COCO dataset into Train / Valid set, rather using whole COCO dataset for testing.

We can take some life case pictures for demo/posters, but I don't think it is necessary to make a "new" dataset.

from machine-learning-for-image-colorization.

You mean doing cross-validation? I think that's too slow. Why not just use
the whole coco as training set and find some other images as testing set.
Our task is not what coco designed for so I think it has no problem if we
use coco as training set and images elsewhere as testing set

On Saturday, 5 November 2016, Lyken Syu [email protected] wrote:

I think you mistook my meaning. What I do is to split COCO dataset into
Train / Valid set, rather using whole COCO dataset for testing.

We can take some life case pictures for demo/posters, but I don't think it
is necessary to make a "new" dataset.

—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
#2 (comment),
or mute the thread
https://github.com/notifications/unsubscribe-auth/AEbvNCY-SNI18siS4X3HqeUh2LDsEa2jks5q7XZWgaJpZM4Kqe0t
.

from machine-learning-for-image-colorization.

No cross-validation.

For example, if COCO dataset has 6000 images. Then I pick 4000 as training set, 1000 for validation and 1000 for testing . And when switching to other method(s), the same 4000, 1000 and 1000 images are used for training, validation and testing respectively.

from machine-learning-for-image-colorization.

It still means we should make it clear which 4000 are training images. Did
you already seperate them?

On Saturday, 5 November 2016, Lyken Syu [email protected] wrote:

No cross-validation.

For example, if COCO dataset has 6000 images. Then I pick 4000 as training
set, 1000 for validation and 1000 for testing . And when switching to other
method(s), the same 4000, 1000 and 1000 images are used for training,
validation and testing respectively.

—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
#2 (comment),
or mute the thread
https://github.com/notifications/unsubscribe-auth/AEbvNLAiJqFAdKbUqGLOTbwn2G1qy0Sfks5q7XgegaJpZM4Kqe0t
.

from machine-learning-for-image-colorization.