cellmap_flow.models.cellmap_models

Attributes

ort

torch

Classes

ModelMetadata

!!! abstract "Usage Documentation"

CellmapModel

Represents a single model directory.

CellmapModels

A container that discovers all subfolders in the given directory

Module Contents

cellmap_flow.models.cellmap_models.ort = None
cellmap_flow.models.cellmap_models.torch = None
class cellmap_flow.models.cellmap_models.ModelMetadata(/, **data: Any)
!!! abstract “Usage Documentation”

[Models](../concepts/models.md)

A base class for creating Pydantic models.

__class_vars__

The names of the class variables defined on the model.

__private_attributes__

Metadata about the private attributes of the model.

__signature__

The synthesized __init__ [Signature][inspect.Signature] of the model.

__pydantic_complete__

Whether model building is completed, or if there are still undefined fields.

__pydantic_core_schema__

The core schema of the model.

__pydantic_custom_init__

Whether the model has a custom __init__ function.

__pydantic_decorators__

Metadata containing the decorators defined on the model. This replaces Model.__validators__ and Model.__root_validators__ from Pydantic V1.

__pydantic_generic_metadata__

Metadata for generic models; contains data used for a similar purpose to __args__, __origin__, __parameters__ in typing-module generics. May eventually be replaced by these.

__pydantic_parent_namespace__

Parent namespace of the model, used for automatic rebuilding of models.

__pydantic_post_init__

The name of the post-init method for the model, if defined.

__pydantic_root_model__

Whether the model is a [RootModel][pydantic.root_model.RootModel].

__pydantic_serializer__

The pydantic-core SchemaSerializer used to dump instances of the model.

__pydantic_validator__

The pydantic-core SchemaValidator used to validate instances of the model.

__pydantic_fields__

A dictionary of field names and their corresponding [FieldInfo][pydantic.fields.FieldInfo] objects.

__pydantic_computed_fields__

A dictionary of computed field names and their corresponding [ComputedFieldInfo][pydantic.fields.ComputedFieldInfo] objects.

__pydantic_extra__

A dictionary containing extra values, if [extra][pydantic.config.ConfigDict.extra] is set to ‘allow’.

__pydantic_fields_set__

The names of fields explicitly set during instantiation.

__pydantic_private__

Values of private attributes set on the model instance.

model_name: str | None = None
model_type: str | None = None
framework: str | None = None
spatial_dims: int | None = None
in_channels: int | None = None
out_channels: int | None = None
iteration: int | None = None
input_voxel_size: List[int] | None = None
output_voxel_size: List[int] | None = None
channels_names: List[str] | None = None
input_shape: List[int] | None = None
output_shape: List[int] | None = None
inference_input_shape: List[int] | None = None
inference_output_shape: List[int] | None = None
author: str | None = None
description: str | None = None
version: str | None = None
class cellmap_flow.models.cellmap_models.CellmapModel(folder_path: str)

Represents a single model directory. Lazily loads:

  • metadata.json –> pydantic ModelMetadata

  • model.onnx –> ONNX model session (if onnxruntime is available)

  • model.pt –> PyTorch model (if torch is available)

  • model.ts –> TorchScript model (if torch is available)

  • README.md –> str

folder_path
property metadata: ModelMetadata

Lazy load the metadata.json file and parse it into a ModelMetadata object.

property onnx_model

If ‘model.onnx’ exists, lazily load it as an ONNX Runtime InferenceSession. Use GPU if available (requires onnxruntime-gpu installed), otherwise CPU. Returns None if the file doesn’t exist or onnxruntime isn’t installed.

property pytorch_model

If ‘model.pt’ exists, lazily load it using torch.load(). Returns None if the file doesn’t exist or PyTorch isn’t installed.

NOTE: Adjust this for how your .pt was saved (entire model vs state_dict).

property ts_model

If ‘model.ts’ exists, lazily load it using torch.jit.load(). Returns None if the file doesn’t exist or PyTorch isn’t installed.

property readme: str | None

Lazy load the README.md content if it exists, else None.

class cellmap_flow.models.cellmap_models.CellmapModels(root_dir: str)

A container that discovers all subfolders in the given directory and provides them as model attributes.

root_dir
list_models() List[str]

Returns the list of detected model names (subfolder names that contain ‘metadata.json’).