【Hackathon 7th PPSCI No.7】No.7 AI-aided geometric design of anti-infection catheters 论文复现

[ADream-ki]

PR types

PR changes

Describe

[paddle-bot[bot]]

Thanks for your contribution!

[ADream-ki]

这两个好像还没做，注意下 3. catheter_design.ipynb: Real-time design optimization by using Geo-FNO model and BFGS algorithm.

4. catheter_analysis.ipynb: Compassion with linear regression model; Visualization of the landscape of the loss function around the optimal design.

加在aistudio那里了

[CLAassistant]

All committers have signed the CLA.

[wangguan1995]

数据集没有公开，另外需要【挂载】到aistudio项目上

[ADream-ki]

抱歉抱歉，忘了公开数据集了，现在已经可以了，请review @wangguan1995

[wangguan1995]

AIStudio需要修复以下内容，最终做到用户【一键跑通训练推理】:

1. 补充数据解压脚本，到3个ipynb文件内

!unzip ./data/data291940/data.zip -d .
!mkdir MyData
!mv ./data/test/ MyData
!mv ./data/training/ MyData

2. 修复 geofno_analysis.ipynb bug：

3. 修复 main.ipynb bug：

[ADream-ki]

已经修改了，但是有个问题，这个是怎么回事吗 @wangguan1995

[ADream-ki]

好的好的，我现在试试

[ADream-ki]

已经好了，请您review一下

[ADream-ki]

@HydrogenSulfate

[ADream-ki]

已经加上去了 @HydrogenSulfate

[ADream-ki]

请问我的code_style为什么一直都是错误的？我在本地已经跑过一遍了 @HydrogenSulfate

[ADream-ki]

论文里面并没有给出明确的评价指标 ，那个codestyle我晚上再调一下，将那些没用的引用删掉@HydrogenSulfate

[wangguan1995]

实在跑不通，要不加下微信聊下？

[wangguan1995]

input <class 'paddle.Tensor'>
Error executing job with overrides: []
Traceback (most recent call last):
  File "/workspace/PaddleScience_test/examples/catheter/catheter.py", line 283, in main
    train(cfg)
  File "/workspace/PaddleScience_test/examples/catheter/catheter.py", line 176, in train
    solver.train()
  File "/workspace/PaddleScience_test/ppsci/solver/solver.py", line 560, in train
    self.train_epoch_func(self, epoch_id, self.log_freq)
  File "/workspace/PaddleScience_test/ppsci/solver/train.py", line 177, in train_epoch_func
    solver.optimizer.step()
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/decorator.py", line 232, in fun
    return caller(func, *(extras + args), **kw)
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/base/dygraph/base.py", line 383, in __impl__
    return func(*args, **kwargs)
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/decorator.py", line 232, in fun
    return caller(func, *(extras + args), **kw)
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/base/wrapped_decorator.py", line 40, in __impl__
    return wrapped_func(*args, **kwargs)
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/base/framework.py", line 718, in __impl__
    return func(*args, **kwargs)
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/optimizer/adam.py", line 526, in step
    optimize_ops = self._apply_optimize(
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/optimizer/optimizer.py", line 1614, in _apply_optimize
    optimize_ops = self._create_optimization_pass(
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/optimizer/optimizer.py", line 1292, in _create_optimization_pass
    self._append_optimize_op(
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/optimizer/adam.py", line 387, in _append_optimize_op
    _, _, _, _, _, _, _ = _C_ops.adam_(
RuntimeError: (NotFound) The kernel with key (GPU, Undefined(AnyLayout), complex64) of kernel `adam` is not registered and fail to fallback to CPU one. Selected wrong DataType `complex64`. Paddle support following DataTypes: float64, float16, float32, bfloat16.
  [Hint: Expected kernel_iter != iter->second.end(), but received kernel_iter == iter->second.end().] (at /workspace/Paddle/paddle/phi/core/kernel_factory.cc:379)

[ADream-ki]

实在跑不通，要不加下微信聊下？

好的好的，我该如何联系您

[ADream-ki]

input <class 'paddle.Tensor'>
Error executing job with overrides: []
Traceback (most recent call last):
  File "/workspace/PaddleScience_test/examples/catheter/catheter.py", line 283, in main
    train(cfg)
  File "/workspace/PaddleScience_test/examples/catheter/catheter.py", line 176, in train
    solver.train()
  File "/workspace/PaddleScience_test/ppsci/solver/solver.py", line 560, in train
    self.train_epoch_func(self, epoch_id, self.log_freq)
  File "/workspace/PaddleScience_test/ppsci/solver/train.py", line 177, in train_epoch_func
    solver.optimizer.step()
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/decorator.py", line 232, in fun
    return caller(func, *(extras + args), **kw)
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/base/dygraph/base.py", line 383, in __impl__
    return func(*args, **kwargs)
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/decorator.py", line 232, in fun
    return caller(func, *(extras + args), **kw)
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/base/wrapped_decorator.py", line 40, in __impl__
    return wrapped_func(*args, **kwargs)
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/base/framework.py", line 718, in __impl__
    return func(*args, **kwargs)
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/optimizer/adam.py", line 526, in step
    optimize_ops = self._apply_optimize(
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/optimizer/optimizer.py", line 1614, in _apply_optimize
    optimize_ops = self._create_optimization_pass(
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/optimizer/optimizer.py", line 1292, in _create_optimization_pass
    self._append_optimize_op(
  File "/root/miniconda3/envs/test/lib/python3.10/site-packages/paddle/optimizer/adam.py", line 387, in _append_optimize_op
    _, _, _, _, _, _, _ = _C_ops.adam_(
RuntimeError: (NotFound) The kernel with key (GPU, Undefined(AnyLayout), complex64) of kernel `adam` is not registered and fail to fallback to CPU one. Selected wrong DataType `complex64`. Paddle support following DataTypes: float64, float16, float32, bfloat16.
  [Hint: Expected kernel_iter != iter->second.end(), but received kernel_iter == iter->second.end().] (at /workspace/Paddle/paddle/phi/core/kernel_factory.cc:379)

这个我不是改掉了吗，我看看

[luotao1]

⚠️ 重要通知：个人挑战赛赛题即将锁定 各位参与黑客松「个人挑战赛」的开发者请注意：个人挑战赛的赛题将于 12 月 18 日正式锁定。

锁定后，除完成度较高的 PR 外，其余 PR 将不再进行审核和合入。请已报名的开发者务必抓紧时间推进赛题进度，确保在截止日期前提交高质量的成果。

感谢大家的积极参与！ 🚀

[wangguan1995]

开发者你好，感谢你的参与！由于你的黑客松赛题完成度较高，其PR已被锁定，请尽快完善锁定的PR，并确保在2025年1月3日前完成合入。逾期未合入PR将无法获得奖金发放。

[wangguan1995]

LGTM

[ADream-ki]

你好，请问还有哪里需要修改的吗？ @HydrogenSulfate