mirror of
https://github.com/PaddlePaddle/PaddleOCR.git
synced 2025-08-01 13:18:26 +00:00
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>
82 lines
2.2 KiB
Python
82 lines
2.2 KiB
Python
import pytest
|
|
|
|
from paddleocr import PPChatOCRv4Doc
|
|
from ..testing_utils import TEST_DATA_DIR
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def pp_chatocrv4_doc_pipeline():
|
|
return PPChatOCRv4Doc()
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"image_path",
|
|
[
|
|
TEST_DATA_DIR / "doc_with_formula.png",
|
|
],
|
|
)
|
|
def test_visual_predict(pp_chatocrv4_doc_pipeline, image_path):
|
|
result = pp_chatocrv4_doc_pipeline.visual_predict(str(image_path))
|
|
|
|
assert result is not None
|
|
assert isinstance(result, list)
|
|
assert len(result) == 1
|
|
res = result[0]
|
|
assert isinstance(res, dict)
|
|
assert res.keys() == {"visual_info", "layout_parsing_result"}
|
|
assert isinstance(res["visual_info"], dict)
|
|
assert isinstance(res["layout_parsing_result"], dict)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"params",
|
|
[
|
|
{"use_doc_orientation_classify": False},
|
|
{"use_doc_unwarping": False},
|
|
{"use_general_ocr": False},
|
|
{"use_table_recognition": False},
|
|
{"layout_threshold": 0.88},
|
|
{"layout_threshold": [0.45, 0.4]},
|
|
{"layout_threshold": {0: 0.45, 2: 0.48, 7: 0.4}},
|
|
{"layout_nms": False},
|
|
{"layout_unclip_ratio": 1.1},
|
|
{"layout_unclip_ratio": [1.2, 1.5]},
|
|
{"layout_unclip_ratio": {0: 1.2, 2: 1.5, 7: 1.8}},
|
|
{"layout_merge_bboxes_mode": "large"},
|
|
{"layout_merge_bboxes_mode": {0: "large", 2: "small", 7: "union"}},
|
|
{"text_det_limit_side_len": 640, "text_det_limit_type": "min"},
|
|
{"text_det_thresh": 0.5},
|
|
{"text_det_box_thresh": 0.3},
|
|
{"text_det_unclip_ratio": 3.0},
|
|
{"text_rec_score_thresh": 0.5},
|
|
],
|
|
)
|
|
def test_predict_params(
|
|
monkeypatch,
|
|
pp_chatocrv4_doc_pipeline,
|
|
params,
|
|
):
|
|
def _dummy_visual_predict(input, **params):
|
|
yield {"visual_info": {}, "layout_parsing_result": params}
|
|
|
|
monkeypatch.setattr(
|
|
pp_chatocrv4_doc_pipeline.paddlex_pipeline,
|
|
"visual_predict",
|
|
_dummy_visual_predict,
|
|
)
|
|
|
|
result = pp_chatocrv4_doc_pipeline.visual_predict(
|
|
input,
|
|
**params,
|
|
)
|
|
|
|
assert isinstance(result, list)
|
|
assert len(result) == 1
|
|
res = result[0]
|
|
res = res["layout_parsing_result"]
|
|
for k, v in params.items():
|
|
assert res[k] == v
|
|
|
|
|
|
# TODO: Test constructor and other methods
|