Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

UpSampling vs MaxUnpooling #18

Open
jaxony opened this issue Oct 24, 2017 · 2 comments
Open

UpSampling vs MaxUnpooling #18

jaxony opened this issue Oct 24, 2017 · 2 comments

Comments

@jaxony
Copy link

jaxony commented Oct 24, 2017

Thanks for your work on getting ENet in Keras! Have you found any increases in accuracy from using MaxUnpooling instead of just naive UpSampling?

@PavlosMelissinos
Copy link
Owner

Hey, thanks for the interest!

I haven't seen any noticeable improvements to be honest but I haven't run any thorough tests so I've been getting weird results with my implementation anyway.

@PavlosMelissinos
Copy link
Owner

PavlosMelissinos commented Nov 23, 2017

Minor update on this question:

I've compared the qualitative results of the two networks and it seems like MaxUnpooling gives slightly smoother segments with fewer holes.

You can reproduce this by running the code using overfit mode python run.py --mode overfit, using 200 epochs on 4 or 8 samples. In order to do that you have to change these lines to

data['sample_size'] = 8
experiment['epochs'] = 200

and add a random seed here to ensure that the samples will be the same in the two experiments. So change it to something like:

image_ids = self._coco.getImgIds()
np.random.seed(1024)
self._image_ids = np.random.choice(image_ids, size=min(len(image_ids), self._sample_size), replace=False)

After you run it, for each sample you'll get a plot with the original image, the detections and the ground truth, which should help you visualize the results.

EDIT: The next version of master will plot a binary mask for each object instead of a single mask for the whole image.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants