Skip to content

Conversation

@qingqing01
Copy link
Contributor

Fix #11403

@qingqing01 qingqing01 changed the title Implement a bilinear initializer for transposed convolution. Implement a bilinear initializer for transposed convolution to do upsampling. Jun 12, 2018
'Constant', 'Uniform', 'Normal', 'Xavier', 'Bilinear', 'force_init_on_cpu',
'init_on_cpu', 'ConstantInitializer', 'UniformInitializer',
'NormalInitializer', 'XavierInitializer'
'NormalInitializer', 'XavierInitializer', 'BilinearInitializer'
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这里的排版用改成一列么?

Raises:
ValueError: If type of `var` and `block` is not right.
If the shape of `var` size is not 4 and
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

and -> or ?

class BilinearInitializer(Initializer):
"""Implements the bilinear initializer.
This initializer can be used in transposed convolution operator to
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

BilinearInitializer强绑定到“用conv_transpose做upsampling”的场景了?
如果我想对普通的parameter做bilinear initializatoin怎么办?

@qingqing01 qingqing01 merged commit 566a940 into PaddlePaddle:develop Jun 15, 2018
@qingqing01 qingqing01 deleted the bilinear_init branch November 14, 2019 05:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

2 participants