This repository has been archived by the owner on Jul 2, 2021. It is now read-only.
use scales (tuple of floats) in region_proposal_network #729
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
yuyu2172
reviewed
Nov 6, 2018
| @@ -82,8 +82,8 @@ def __call__(self, x, img_size, scale=1.): | |||
| Its shape is :math:`(N, C, H, W)`. | |||
| img_size (tuple of ints): A tuple :obj:`height, width`, | |||
| which contains image size after scaling. | |||
| scale (float): The amount of scaling done to the input images after | |||
| reading them from files. | |||
| scales (tuple of float): The amount of scaling done to the input | |||
There was a problem hiding this comment.
I guess it is better to make the definition clear that scaling parameter can be different for each image.
Perhaps:
The amount of scaling done to each input image during preprocessing?
Similarly, please change the rest of the definition for scales (they are currently not consistent, but it would be better to use the same wording for all of them).
| @@ -132,7 +132,7 @@ def __call__(self, x, scale=1.): | |||
|
|
|||
| Args: | |||
| x (~chainer.Variable): 4D image variable. | |||
| scale (float): Amount of scaling applied to the raw image | |||
| scales (tuple of float): Amount of scaling applied to the raw image | |||
| @@ -79,7 +79,7 @@ def __call__(self, imgs, bboxes, labels, scale): | |||
| the definition, which means that the range of the value | |||
| is :math:`[0, L - 1]`. :math:`L` is the number of foreground | |||
| classes. | |||
| scale (float or ~chainer.Variable): Amount of scaling applied to | |||
| scale (~chainer.Variable): Amount of scaling applied to | |||
|
Thx for the review. I updated. |
yuyu2172
reviewed
Nov 7, 2018
| @@ -112,10 +112,10 @@ def n_class(self): | |||
| # Total number of classes including the background. | |||
| return self.head.n_class | |||
|
|
|||
| def __call__(self, x, scale=1.): | |||
| def __call__(self, x, scales): | |||
There was a problem hiding this comment.
The default value should be set in order to prevent this from becoming no-compat
yuyu2172
reviewed
Nov 7, 2018
| @@ -67,7 +67,7 @@ def __init__( | |||
| self.loc = L.Convolution2D( | |||
| mid_channels, n_anchor * 4, 1, 1, 0, initialW=initialW) | |||
|
|
|||
| def __call__(self, x, img_size, scale=1.): | |||
| def __call__(self, x, img_size, scales): | |||
|
Thanks, updated :) |
knorth55
changed the title
yuyu2172
approved these changes
Nov 7, 2018
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
xis(N, C, H, W)andscaleis scalar value.I modify to use
scales: (N, ).