mirror of
https://github.com/PaddlePaddle/PaddleOCR.git
synced 2025-06-03 21:53:39 +08:00
3d03ca5500
* Init new paddleocr * Remove unused dependency * Fix typos * Fix * Add doc understanding modules * Fix package finding * Normalize name * Fix setting bugs * Fix setting bug * Support single model inference * Add PP-ChatOCRv4-doc * Add pp_chatocrv4_doc tests * Enable MKL-DNN when available * add seal_text_detection modules * add layout_detection and table_cells_detection modules * add testing scripts * Fix desc * add text_image_unwarping and table_structure_recognition modules * add formula_recognition and doc_vlm modules * update formula_recognition default_model_name * add MKLDNN_BLOCKLIST * update MKLDNN log * add seal rec pipeline * fix sth * fix sth * add doc preprocessor pipeline * fix sth * add doc understanding * add table_rec_v2, ppstructurev3, formula_rec pipelines * move test files * forward kwargs to pipeline.predict * clean test files * Add missing kwargs * Fix typo * Fix typo * rerun CI * update mkldnn BLOCKLIST * update * update warning message * fix cli args * update PIPELINE_MKLDNN_BLOCKLIST * update of workflow * skip resource_intensive tests * update config * skip ppdocbee test_predict_params --------- Co-authored-by: zhangyue66 <zhangyue66@baidu.com> Co-authored-by: zhangzelun <zhangzelun@baidu.com>
106 lines
3.3 KiB
Python
106 lines
3.3 KiB
Python
# Copyright (c) 2025 PaddlePaddle Authors. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
from ..utils.cli import (
|
|
add_simple_inference_args,
|
|
get_subcommand_args,
|
|
perform_simple_inference,
|
|
str2bool,
|
|
)
|
|
from .base import PaddleXPipelineWrapper, PipelineCLISubcommandExecutor
|
|
from .utils import create_config_from_structure
|
|
from paddlex.utils.pipeline_arguments import custom_type
|
|
|
|
|
|
class DocUnderstanding(PaddleXPipelineWrapper):
|
|
def __init__(
|
|
self,
|
|
doc_understanding_model_name=None,
|
|
doc_understanding_model_dir=None,
|
|
doc_understanding_batch_size=None,
|
|
**kwargs,
|
|
):
|
|
|
|
self._params = {
|
|
"doc_understanding_model_name": doc_understanding_model_name,
|
|
"doc_understanding_model_dir": doc_understanding_model_dir,
|
|
"doc_understanding_batch_size": doc_understanding_batch_size,
|
|
}
|
|
super().__init__(**kwargs)
|
|
|
|
@property
|
|
def _paddlex_pipeline_name(self):
|
|
return "doc_understanding"
|
|
|
|
def predict(
|
|
self,
|
|
input,
|
|
**kwargs,
|
|
):
|
|
result = []
|
|
for res in self.paddlex_pipeline.predict(input, **kwargs):
|
|
result.append(res)
|
|
return result
|
|
|
|
@classmethod
|
|
def get_cli_subcommand_executor(cls):
|
|
return DocUnderstandingCLISubcommandExecutor()
|
|
|
|
def _get_paddlex_config_overrides(self):
|
|
STRUCTURE = {
|
|
"SubModules.DocUnderstanding.model_name": self._params[
|
|
"doc_understanding_model_name"
|
|
],
|
|
"SubModules.DocUnderstanding.model_dir": self._params[
|
|
"doc_understanding_model_dir"
|
|
],
|
|
"SubModules.DocUnderstanding.batch_size": self._params[
|
|
"doc_understanding_batch_size"
|
|
],
|
|
}
|
|
return create_config_from_structure(STRUCTURE)
|
|
|
|
|
|
class DocUnderstandingCLISubcommandExecutor(PipelineCLISubcommandExecutor):
|
|
|
|
input_validator = staticmethod(custom_type(dict))
|
|
|
|
@property
|
|
def subparser_name(self):
|
|
return "doc_understanding"
|
|
|
|
def _update_subparser(self, subparser):
|
|
add_simple_inference_args(subparser)
|
|
|
|
subparser.add_argument(
|
|
"--doc_understanding_model_name",
|
|
type=str,
|
|
help="Name of the document understanding model.",
|
|
)
|
|
subparser.add_argument(
|
|
"--doc_understanding_model_dir",
|
|
type=str,
|
|
help="Path to the document understanding model directory.",
|
|
)
|
|
subparser.add_argument(
|
|
"--doc_understanding_batch_size",
|
|
type=str,
|
|
help="Batch size for the document understanding model.",
|
|
)
|
|
|
|
def execute_with_args(self, args):
|
|
params = get_subcommand_args(args)
|
|
params["input"] = self.input_validator(params["input"])
|
|
perform_simple_inference(DocUnderstanding, params)
|