-
Notifications
You must be signed in to change notification settings - Fork 190
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Example] Add yinglong #975
base: develop
Are you sure you want to change the base?
Conversation
Thanks for your contribution! |
|
||
## Example Usage | ||
|
||
### 1. Download the data and model weights |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
此次PR下包含模型训练、推理的代码,不包含通过静态图模型推理的代码,因此在Usage这一部分建议按照类似以下的方式进行组织:
- model pretrain
相关的预训练命令 xxx - model finetune
相关的微调命令 xxx - model inference
相关的推理命令 xxx
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
此文件与模型训练推理无关,可以删除
# num_timestamps=NUM_TIMESTAMPS, | ||
# prefix="wind", | ||
# ) | ||
# } |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
无用的注释可以删除
) | ||
solver.eval() | ||
# visualize prediction from pretrained_model_path | ||
# solver.visualize() |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
同上
# ) | ||
# PRETRAINED_MODEL_PATH = ( | ||
# f"../output/hrrr_time_embedding_merge_train_finetune_{NUM_TIMESTAMPS-1}/checkpoints/best_model" | ||
# ) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
同上
# metric=metric, | ||
# name="Sup_Validator", | ||
# ) | ||
# validator = {sup_validator.name: sup_validator} |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
同上
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
没有用到的代码可以直接删除,例如autodiff、geometry等;部分用到的,例如loss、metric等只用到了其中的某几个类,没有用到的类也可以直接删除。可以全局搜索一下。尽量保持此PR是yinglong代码的最小实现,无关的代码可以删除下。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
可以删除fourcastnet_hrrr文件夹,将其中的文件直接放到examples下即可
已经将冗余的代码和注释删除,并调整了文件目录 |
@robotLiberator 目前的代码训练、推理过程中好像没有用到地理数据?而之前release的代码中用到了这种数据, geo_data
|
|
ppsci冲突太多,将简化的代码放到了jointContribution/yinglong下