mmdeploy/configs/mmocr/text-detection/text-detection_sdk_dynamic.py

_base_ = ['./text-detection_dynamic.py', '../../_base_/backends/sdk.py']

codebase_config = dict(model_type='sdk')

backend_config = dict(pipeline=[
    dict(type='LoadImageFromFile'),
    dict(type='Collect', keys=['img'], meta_keys=['filename', 'ori_shape'])
])
Add Python wrapper for SDK (#27) * add python API for detector * integrate detection * add python segmentor * add segmentation support * add classifier, text-detector, text-recognizer and restorer * integrate classifier * integrate textdet, textrecog and restorer * simplify * add inst-seg * fix inst-seg * integrate inst-seg * Moidfy _build_wrapper * better pipeline substitution * use registry for backend model creation * build Python module according to C API targets * minor fix * move sdk data pipeline to backend_config * remove debugging lines * add docstring for SDKEnd2EndModel * fix type hint * fix lint * fix lint * insert build/lib to sys.path Co-authored-by: SingleZombie <singlezombie@163.com> 2022-01-13 11:31:51 +08:00			`_base_ = ['./text-detection_dynamic.py', '../../_base_/backends/sdk.py']`

			`codebase_config = dict(model_type='sdk')`

			`backend_config = dict(pipeline=[`
			`dict(type='LoadImageFromFile'),`
			`dict(type='Collect', keys=['img'], meta_keys=['filename', 'ori_shape'])`
			`])`