Top-level exports
simpledet.__version__
simpledet.train, simpledet.detect, simpledet.evaluate
simpledet.run_training, simpledet.run_inference, simpledet.run_evaluation
simpledet.native
simpledet.ProjectLayout
simpledet.DatasetConfig, simpledet.RuntimeConfig, simpledet.OptimizationConfig
simpledet.ProjectConfig, load_project_config, init_project_config, run_project
simpledet.detectors
simpledet.suite
simpledet.suite
EncoderSpec
NeckSpec
HeadSpec
DecoderSpec
DetectorSpec
build_encoder(...)
build_custom_encoder(...)
build_neck(...)
build_custom_neck(...)
build_head(...)
build_custom_head(...)
build_decoder(...)
build_custom_decoder(...)
build_detector(...)
compile_native_detector_plan(spec)
The build_custom_* helpers are the public mechanism for registry-backed custom components. They pair a component type, explicit imports, and the config fields needed by the planner and runtime registry loader.
compile_native_detector_plan(...) produces the structured build plan consumed by the native runtime.
Project config helpers
ProjectLayout(...)
DatasetConfig(...)
RuntimeConfig(...)
OptimizationConfig(...)
ProjectConfig(...)
project_config_template(...)
init_project_config(...)
load_project_config(...)
validate_project_config(...)
run_project(...)
Use the structured config objects when you want a repeatable project file and a single native entrypoint for build, train, inference, and evaluation stages.
Direct execution helpers
run_training(...)
run_inference(...)
run_evaluation(...)
Use these when you want native execution without creating a config file. They wrap the project-layout helpers and execute the relevant stages directly.
simpledet.native
NativeProjectConfig(...)
run_native_training(...)
run_native_inference(...)
run_native_evaluation(...)
build_native_components(...)
This is the native Lightning-backed backend. The current native catalog supports retinanet, retina, fcos, atss, gfl, vfnet, fovea, foveabox, reppoints, yolof, centernet, faster_rcnn, mask_rcnn, grid_rcnn, and cascade_rcnn.
Custom native detectors now grow through a detector-assembler layer. Register an assembler in simpledet.extensions.DETECTORS, create a spec with build_custom_detector(...), then call build_native_model(...) on that spec.
simpledet.api
The public API now centers on ProjectConfig, run_project(...), and the direct helpers run_training(...), run_inference(...), and run_evaluation(...). Legacy pipeline/config-compilation helpers are no longer part of the public contract.
simpledet._model_resolution
list_available_encoders()
list_available_heads()
list_available_necks()
apply_runtime_model_overrides()
patch_backbone_input_channels()
patch_model_num_classes()