【Hackathon 8th No.14】CoNFiLD 论文复现 #1110
Open
Conversation
This file contains hidden or 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! |
|
|
如果有可复现的精度结果，可以日志截图到github+上传log，这边可以开始测试 |
有的有的 |
|
2、3、4的太大了，我的batch_size是一个一个跑的，看的是他们的前几个的loss |
|
链接的是按照原论文那种，没有改动的 |
可视化代码尚未补上 |
| @@ -0,0 +1,369 @@ | |||
| # AI辅助的时空湍流生成：条件神经场潜在扩散模型（CoNFILD） | |||
|
|
|||
| Distributed under a Creative Commons Attribution license 4.0 (CC BY). | |||
There was a problem hiding this comment.
文档过于简单，需要进行更详细的背景解释，论文的重要结论和精度需要补充上去
| batch_size: 100 | ||
|
|
||
| Data: | ||
| data_path: /home/xinyang/store/projects/nfdiff/algo/elbow/uvp.npy |
| batch_size: 40 | ||
|
|
||
| Data: | ||
| data_path: /home/xinyang/store/projects/nfdiff/algo/elbow/uvp.npy |
| batch_size: 64 | ||
|
|
||
| Data: | ||
| data_path: /home/xinyang/store/projects/nfdiff/algo/elbow/uvp.npy |
| 2. **潜在扩散**：在潜在空间进行概率扩散过程，学习湍流统计分布。 | ||
| 3. **零样本条件生成**：结合贝叶斯推理，无需重新训练即可实现传感器重建、超分辨率等任务。 | ||
|
|
||
|  |
There was a problem hiding this comment.
图片需要改为链接，删除conflid.png文件
|
|
||
| ## 2. 问题定义 | ||
| ### 2.1 研究背景 | ||
| 湍流模拟在航空航天、海洋工程等领域至关重要，但传统方法如直接数值模拟（DNS）和大涡模拟（LES）计算成本高昂，难以应用于高雷诺数或实时场景。现有深度学习模型多基于确定性框架，难以捕捉湍流的混沌特性，且在复杂几何域中表现受限。 |
| paddle.save(latents_model.state_dict(), f"latents_model_{i}.pdparams") | ||
| ``` | ||
|
|
||
| ## 5. 实验结果 |
| DEFAULT_W0 = 30.0 | ||
|
|
||
|
|
||
| class Swish(paddle.nn.Layer): |
There was a problem hiding this comment.
请判断下是否可以复用：ppsci/arc/activation.py的swish？
|
|
||
|
|
||
| NLS_AND_INITS = { | ||
| "sine": (Sine(), sine_init, first_layer_sine_init), |
| x = self.net1[-1](x) | ||
| return {self.output_keys[0]: x} | ||
|
|
||
| def disable_gradient(self): |
There was a problem hiding this comment.
请看下是否用到？如果用到是否可以用no_grad代替？
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
Others
PR changes
Others
Describe
PaddlePaddle/community#1080