mmdeploy/configs/mmocr/text-detection/text-detection_mrcnn_torchscript.py
AllentDan ff95bf48ea
[Feature] Support more MMOCR models: DBNet++, TextSnake, ABINet, MRCNN (#1534)
* WIP ocr

* add mrcnn rewrite

* add any rewrite for abinet

* export abinet to onnx

* fix abinet onnx export

* support abinet to tensorrt static and modify mmocr.yml

* add textsnake and dbnetpp

* support mrcnn in ORT and TRT

* add a condition before update data_preprocessor scope

* update doc and mmocr.yml

* add ut

* markdown and simple config

* write build_pytorch_model in child class

* update any_default

* remove where in abi_language_decoder___get_length__default

* keep where

* fix UT

* fix UT

* fix UT

* update mmocr.yml and config description

* tensorrt-fp32 -> tensorrt

* update doc
2023-01-16 12:06:03 +08:00

19 lines
523 B
Python

_base_ = [
'../../_base_/torchscript_config.py',
'../../_base_/backends/torchscript.py'
]
ir_config = dict(input_shape=None, output_names=['dets', 'labels', 'masks'])
codebase_config = dict(
type='mmocr',
task='TextDetection',
post_processing=dict(
score_threshold=0.05,
confidence_threshold=0.005,
iou_threshold=0.5,
max_output_boxes_per_class=200,
pre_top_k=5000,
keep_top_k=100,
background_label_id=-1,
export_postprocess_mask=False))