Conversation
|
Thanks for your contribution! |
|
|
||
| ## Example Usage | ||
|
|
||
| ### 1. Download the data and model weights |
There was a problem hiding this comment.
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.
此文件与模型训练推理无关,可以删除
| # num_timestamps=NUM_TIMESTAMPS, | ||
| # prefix="wind", | ||
| # ) | ||
| # } |
| ) | ||
| solver.eval() | ||
| # visualize prediction from pretrained_model_path | ||
| # solver.visualize() |
| # ) | ||
| # PRETRAINED_MODEL_PATH = ( | ||
| # f"../output/hrrr_time_embedding_merge_train_finetune_{NUM_TIMESTAMPS-1}/checkpoints/best_model" | ||
| # ) |
| # metric=metric, | ||
| # name="Sup_Validator", | ||
| # ) | ||
| # validator = {sup_validator.name: sup_validator} |
There was a problem hiding this comment.
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.
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