reimplement paddle.nn.functional.sigmoid_focal_loss #27748
Merged
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
|
Thanks for your contribution! |
FlyingQianMM
force-pushed
the
remove_focal_loss
branch
from
4d95fa0
to
3f9512d
Compare
FlyingQianMM
force-pushed
the
remove_focal_loss
branch
from
3f9512d
to
5772671
Compare
FlyingQianMM
force-pushed
the
remove_focal_loss
branch
3 times, most recently
from
026bfe3
to
f375ef1
Compare
FlyingQianMM
force-pushed
the
remove_focal_loss
branch
from
f375ef1
to
317ee0a
Compare
FlyingQianMM
force-pushed
the
remove_focal_loss
branch
3 times, most recently
from
a26da0e
to
b8d7639
Compare
FlyingQianMM
force-pushed
the
remove_focal_loss
branch
from
b8d7639
to
94100a4
Compare
wawltor
reviewed
Oct 6, 2020
python/paddle/nn/functional/loss.py
Outdated
| Args: | ||
| logit (Tensor): The input prediction tensor. 2-D tensor with shape: [N, *], | ||
| N is batch_size, `*` means number of additional dimensions. The ``logit`` | ||
| is usually the output of a convolution layer. Available dtype is float32, float64. |
There was a problem hiding this comment.
是否支持多维的tensor的输入了？* 表示额外的维度，* 有可能是一维或者多维的信息
There was a problem hiding this comment.
已经去掉2-D tensor的描述。谢谢～
python/paddle/nn/functional/loss.py
Outdated
| a 1-D Tensor whose shape is `[1, ]`. The data type is float32, float64. | ||
| For object detection task, it is the the number of positive samples. | ||
| If set to None, the focal loss will not be normalized. | ||
| alpha(int|float): Hyper-parameter to balance the positive and negative example, |
There was a problem hiding this comment.
已加上optional。谢谢～
python/paddle/nn/functional/loss.py
Outdated
| If set to None, the focal loss will not be normalized. | ||
| alpha(int|float): Hyper-parameter to balance the positive and negative example, | ||
| it should be between 0 and 1. Default value is set to 0.25. | ||
| gamma(int|float): Hyper-parameter to modulate the easy and hard examples. |
python/paddle/nn/functional/loss.py
Outdated
|
|
||
| import paddle | ||
|
|
||
| paddle.disable_static() |
There was a problem hiding this comment.
尝试一下是否可以去掉disable_static，现在默认打开的是动态图
There was a problem hiding this comment.
已经去掉，可以正常运行。谢谢～
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
PR types
New features
PR changes
OPs
Describe
The paddle.nn.functional.sigmoid_focal_loss is implemented by alias of paddle.fluid.layers.sigmod_focal_loss before, now it is reimplement by composing the sigmoid and binary_cross_entropy_with_logits ops.
chinese pr: PaddlePaddle/docs#2751
