cellmap_flow.models.configs.script

ScriptModelConfig: a model that a Python script defines.

load_safe_config checks the script, runs it and returns its globals as a Config: the model (or a predict) and its geometry. Sizes in voxels (input_size, output_size) and shapes in nm (read_shape, write_shape) are each derived from the other when only one is given.

A script that defines its own process_chunk or predict (a TensorFlow model’s) reads its input itself, and so runs only at its own voxel size (ModelConfig.run_voxel_size); script_reads_input_itself says so from its text, without running it.

Attributes

logger

Classes

ScriptModelConfig

Functions

`load_safe_config`(config_path[, force_safe])	Loads the configuration script at config_path after verifying its safety.
`script_reads_input_itself`(script_path) → bool	Whether the script at `script_path` defines a `process_chunk` or a

Module Contents

cellmap_flow.models.configs.script.logger

cellmap_flow.models.configs.script.load_safe_config(config_path, force_safe=None): Loads the configuration script at config_path after verifying its safety. If force_safe is True, raises an error if the script is deemed unsafe. When it is None, the FORCE_SAFE_CONFIG environment variable decides.

cellmap_flow.models.configs.script.script_reads_input_itself(script_path) → bool

Whether the script at script_path defines a process_chunk or a predict at its top level (a function, or a name assigned), read from its text without running it; False when it cannot be read.

For saying so before its server is started: the dashboard’s Submit refuses to run such a script at another voxel size, and cellmap_flow add -v gives it none. A name it imports is not seen here; its built config is checked too (ModelConfig.config).

class cellmap_flow.models.configs.script.ScriptModelConfig(script_path, name=None, scale=None)

cli_name = 'script'

finetunable = True

script_path

name = None

scale = None

reads_input_itself() → bool: Its built config’s answer, else its script’s (script_reads_input_itself).

to_dict(): This config as a model entry, which registry.build_model rebuilds.