[BugFix][ARM][OP] Fix arm op: reduce_mean & sequence_expand_as #4492
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
zhaoyang-star
added a commit
to zhaoyang-star/Paddle-Lite
that referenced
this pull request
Oct 13, 2020
…ePaddle#4492) * fix op for gcn model: reduce_mean, sequence_expand_as_compute. test=develop
zhaoyang-star
added a commit
that referenced
this pull request
Oct 13, 2020
#4523) * fix op for gcn model: reduce_mean, sequence_expand_as_compute. test=develop
juncaipeng
pushed a commit
to juncaipeng/Paddle-Lite
that referenced
this pull request
Oct 27, 2020
…ePaddle#4492) * fix op for gcn model: reduce_mean, sequence_expand_as_compute. test=develop
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Outdated suggestions cannot be applied.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.
【问题】在运行页面理解GCN模型时，定位到在执行如上两个op时会报段错误，原因为：
reduce_meanop实现时假定了输入tensor的dims是4，然而GCN模型中该op的输入dims是2，因此直接运行会出现段错误；sequence_expand_asop实现时假定了输入Y的LoD数据是按长度保存，然而实际上是按偏移量的形式保存的。如下是Paddle官网对LoD的描述：【解决方法】修复对应 op 实现；可正确运行GCN模型。
【性能】本PR不改变原有kernel的运行性能。
【备注】GCN模型中同时涉及到
elementwise_mulop的修改，比如在该模型中的elementwise_mulop 输入数据 X{31535,4,64}, 输入数据 Y{1,4,64}，需要忽略 Y 的大小为1的头部维度），PR #4485 已对elementwise_mul进行了修复。