refactor(data preprocess): remove the cut off options from info.json #200
Conversation
This file contains 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
…and collect the values from input.json
Previous the ase data will be transferred into text file and then loaded by the _TrajData. now i refactor the function. both text and ase data are treated equally. will works as a class funtion to initial the _TrajData class.
…om_model_options .
…g96. For powerlaw and varTang96, the rs is not exactly the hard cutoff. so when extract the r_max for data. we have to use rs + 5 * w; but for other method just use rs.
…s instance and add from_model class function. note, compared to the previous build_dataset, this one is more flexible. previous build_dataset is a function. now i define a class DataBuilder and re-defined __call__ function. then build_dataset is an instance of DataBuilder class. so i can use build_dataset.from_model() to build dataset from model. at the same time the previous way to use build_dataset is still available. like build_dataset(...).
| @@ -500,7 +500,7 @@ def from_points( | |||
| def from_ase( | |||
| cls, | |||
| atoms, | |||
| r_max, | |||
| r_max: Union[float, int, dict], | |||
| er_max: Optional[float] = None, | |||
| # same cell size, then copy it to all frames. | ||
| cell = np.expand_dims(cell, axis=0) | ||
| data["cell"] = np.broadcast_to(cell, (info["nframes"], 3, 3)) | ||
| elif cell.shape[0] == info["nframes"] * 3: |
| pos = np.loadtxt(os.path.join(root, "positions.dat")) | ||
| if len(pos.shape) == 1: | ||
| pos = pos.reshape(1,3) | ||
| natoms = info["natoms"] |
There was a problem hiding this comment.
ok看起来nframes和natoms的逻辑是没动的
There was a problem hiding this comment.
nframes natoms 如果想去掉。就必须修改文本数据的存储格式。比如一帧结构存为一行这样。不然没办法从数据中提取这个信息。因此我没办法去掉。
| @@ -170,7 +170,7 @@ def __init__(self, model:torch.nn.Module, results_path: str=None, use_gui: bool= | |||
| self.results_path = results_path | |||
| self.use_gui = use_gui | |||
|
|
|||
| def get_bands(self, data: Union[AtomicData, ase.Atoms, str], kpath_kwargs: dict, AtomicData_options: dict={}): | |||
| def get_bands(self, data: Union[AtomicData, ase.Atoms, str], kpath_kwargs: dict, pbc:Union[bool,list]=None, AtomicData_options:dict=None): | |||
There was a problem hiding this comment.
这里为啥单加pbc，以及，前面数据部分AtomicData_options 被info取代掉了，这里为啥保留？
There was a problem hiding this comment.
单加pbc 是因为这信息不一定能从给的结构文件中提取到。需要支持外部的指定。 这里支持AtomicData_options 是为了兼容以前的一些存档。这个后续使用是可以不提供。但是对于一些旧存档，就必须加上，不然存档不能用。
There was a problem hiding this comment.
而数据部分取消，是因为以后做训练任务，我们就不需要这个了。以后新训练下来的模型，后处理算能带的时候，也可以不提供这个。这个参数现在是 optional的。
这一切都是为了软件的兼容性，所不得不做的设置。
floatingCatty
approved these changes
Aug 13, 2024
# for free
to join this conversation on GitHub.
Already have an account?
# 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.
refactor(data preprocess): remove the cut off options from info.json and collect the values from input.json. when run model no need to supply the atomicdata options.
Fix: #155