mirror of
https://github.com/PaddlePaddle/PaddleOCR.git
synced 2025-06-03 21:53:39 +08:00
* 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>
65 lines
1.7 KiB
Python
65 lines
1.7 KiB
Python
import pytest
|
|
|
|
from paddleocr import TableRecognitionPipelineV2
|
|
from ..testing_utils import (
|
|
TEST_DATA_DIR,
|
|
check_simple_inference_result,
|
|
check_wrapper_simple_inference_param_forwarding,
|
|
)
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def table_recognition_v2_pipeline():
|
|
return TableRecognitionPipelineV2()
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"image_path",
|
|
[
|
|
TEST_DATA_DIR / "table.jpg",
|
|
],
|
|
)
|
|
def test_visual_predict(table_recognition_v2_pipeline, image_path):
|
|
result = table_recognition_v2_pipeline.predict(
|
|
str(image_path), use_doc_orientation_classify=False, use_doc_unwarping=False
|
|
)
|
|
|
|
check_simple_inference_result(result)
|
|
res = result[0]
|
|
assert len(res["table_res_list"]) > 0
|
|
assert isinstance(res["table_res_list"][0], dict)
|
|
assert len(res["table_res_list"][0]["cell_box_list"]) > 0
|
|
assert isinstance(res["table_res_list"][0]["pred_html"], str)
|
|
assert isinstance(res["table_res_list"][0]["table_ocr_pred"], dict)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"params",
|
|
[
|
|
{"use_doc_orientation_classify": False},
|
|
{"use_doc_unwarping": False},
|
|
{"use_layout_detection": False},
|
|
{"use_ocr_model": False},
|
|
{"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,
|
|
table_recognition_v2_pipeline,
|
|
params,
|
|
):
|
|
check_wrapper_simple_inference_param_forwarding(
|
|
monkeypatch,
|
|
table_recognition_v2_pipeline,
|
|
"paddlex_pipeline",
|
|
"dummy_path",
|
|
params,
|
|
)
|
|
|
|
|
|
# TODO: Test constructor and other methods
|