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Outdated suggestions cannot be applied.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
Bug fixes
PR changes
Others
Describe
This pull request introduces several improvements and fixes across documentation, dependency management, and code compatibility for the Transolver example and the CViT architecture. The most important changes include enhanced documentation for setup and data preprocessing, added missing dependencies, improved error handling for optional imports, and a correction in the CViT architecture's MLP block initialization.
Documentation improvements:
docs/zh/examples/transolver.mdto include installation instructions for required dependencies and moved the note about initial data preprocessing to relevant sections for better clarity. [1] [2] [3] [4]Dependency management:
paddle_geometricandvtktoexamples/transolver/requirements.txtto ensure all required packages are installed before running the example.Code compatibility and robustness:
examples/transolver/shapenet_car.pyby usingtry/exceptblocks for optional imports frompaddle_geometric, preventing crashes if dependencies are missing.examples/transolver/shapenet_car.pyto use PaddlePaddle types directly, improving compatibility and simplifying data handling. [1] [2]Architecture correction:
ppsci/arch/cvit.pyby usingself.coords_diminstead ofself.latent_dimfor the input dimension, ensuring correct model behavior for the "mlp" embedding type. [1] [2]