【Hackathon 4th No.83】为神经网络编译器 CINN 增加 resize 算子 #384
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
Contributor
MayYouBeProsperous
commented
Feb 26, 2023
•
MayYouBeProsperous
commented
- 【PaddlePaddle Hackathon 4】核心框架开源贡献 CINN 开发任务合集 Paddle#50661 (comment)
MayYouBeProsperous
changed the title
thisjiang
reviewed
Feb 27, 2023
| | :-------: | :---------: | :-------: | :------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------: | | ||
| | Input | Tensor\<T\> | x | [N, C, in_H, in_W] | 输入张量 | | ||
| | Attribute | vector<int> | out_shape | [out_H, out_W] | 调整后的张量大小，只需指定H、W两个维度上的值 | | ||
| | Attribute | string | mode | - | 指定插值方法，可选项包括：<br>**NEAREST**(最近邻插值，选取H和W维上最近的值);<br>**BILINEAR**(双线性插值，选取H和W维上相邻四个点做线性插值).<br>默认值BILINEAR | |
There was a problem hiding this comment.
bicubic也是很常见的插值方法，麻烦也实现下吧~
|
|
||
|
|
||
| # 四、对比分析 | ||
| TVM 的 `resize2d` 算子实现详细，可作为参考。本次任务计划使用 custom call 实现 `resize` 算子，参考 [cholesky 算子的实现](https://github.com/PaddlePaddle/CINN/pull/1133)。 |
There was a problem hiding this comment.
te对应的是CINN里的cinn ir。如果没有像cublas、cudnn、cusolver这种第三方库提供类似函数的话，那就不能通过custom call的方式实现，而是得通过extern call的方式实现，参考PaddlePaddle/CINN#1018 。
There was a problem hiding this comment.
好的明白，修改为extern call的方式实现
|
|
||
| **支持的数据类型:** | ||
|
|
||
| `int32`、`float32` |
There was a problem hiding this comment.
图片应该大部分是uint8、int32这种类型吧。。。
|
|
||
|
|
||
| # 六、测试和验收的考量。 | ||
| 在 `python/tests/ops/test_example_op.py` 中添加 `resize` 算子的测试。测试内容覆盖所有 resize 模式，数据类型。 |
There was a problem hiding this comment.
添加python/tests/ops/test_resize_op.py测试而非test_example_op.py，覆盖支持的所有模式和数据类型，以及几个常见shape
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.