add ci for paddleocr test

.github/workflows/pre-commit.yml → .github/workflows/codestyle.yml

@@ -1,4 +1,4 @@
-name: pre-commit
+name: PaddleOCR Code Style Check
 
 on:
   pull_request:

.github/workflows/tests.yaml

@@ -0,0 +1,36 @@
+name: PaddleOCR PR Tests
+
+on:
+  push:
+  pull_request:
+    branches: ["main", "release/*"]
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.10"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install flake8 pytest
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+        pip install paddlepaddle requests
+        pip install -e .
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 ppocr/ --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 ppocr/ --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with pytest
+      run: |
+        pytest tests/

ppocr/data/imaug/label_ops.py

@@ -841,11 +841,11 @@ def __call__(self, data):
         return data
 
     def xyxyxyxy2xywh(self, boxes):
-        new_bboxes = np.zeros([len(bboxes), 4])
-        new_bboxes[:, 0] = bboxes[:, 0::2].min()  # x1
-        new_bboxes[:, 1] = bboxes[:, 1::2].min()  # y1
-        new_bboxes[:, 2] = bboxes[:, 0::2].max() - new_bboxes[:, 0]  # w
-        new_bboxes[:, 3] = bboxes[:, 1::2].max() - new_bboxes[:, 1]  # h
+        new_bboxes = np.zeros([len(boxes), 4])
+        new_bboxes[:, 0] = boxes[:, 0::2].min()  # x1
+        new_bboxes[:, 1] = boxes[:, 1::2].min()  # y1
+        new_bboxes[:, 2] = boxes[:, 0::2].max() - new_bboxes[:, 0]  # w
+        new_bboxes[:, 3] = boxes[:, 1::2].max() - new_bboxes[:, 1]  # h
         return new_bboxes
 
     def xyxy2xywh(self, bboxes):

ppocr/losses/distillation_loss.py

@@ -1184,7 +1184,9 @@ def forward(self, predicts, batch):
             loss = super().forward(out1, out2, ctc_label)
             if isinstance(loss, dict):
                 for key in loss:
-                    loss_dict["{}_{}_{}".format(self.name, model_name, idx)] = loss[key]
+                    loss_dict[
+                        "{}_{}_{}".format(self.name, self.model_name_pairs, idx)
+                    ] = loss[key]
             else:
                 loss_dict["{}_{}".format(self.name, idx)] = loss
         return loss_dict

ppocr/metrics/vqa_token_re_metric.py

@@ -19,7 +19,7 @@
 import numpy as np
 import paddle
 
-__all__ = ["KIEMetric"]
+__all__ = ["VQAReTokenMetric"]
 
 
 class VQAReTokenMetric(object):

ppocr/metrics/vqa_token_ser_metric.py

@@ -19,7 +19,7 @@
 import numpy as np
 import paddle
 
-__all__ = ["KIEMetric"]
+__all__ = ["VQASerTokenMetric"]
 
 
 class VQASerTokenMetric(object):

ppocr/modeling/backbones/rec_efficientb3_pren.py

@@ -27,7 +27,7 @@
 import paddle.nn as nn
 import paddle.nn.functional as F
 
-__all__ = ["EfficientNetb3"]
+__all__ = ["EfficientNetb3_PREN"]
 
 GlobalParams = collections.namedtuple(
     "GlobalParams",

ppocr/modeling/heads/rec_aster_head.py

@@ -132,7 +132,7 @@ def sample(self, x):
         # Decoder
         state = paddle.zeros([1, batch_size, self.sDim])
 
-        predicted_ids, predicted_scores = [], []
+        predicted_ids, predicted_scores, predicted = [], [], None
         for i in range(self.max_len_labels):
             if i == 0:
                 y_prev = paddle.full(shape=[batch_size], fill_value=self.num_classes)

ppocr/utils/loggers/wandb_logger.py

@@ -1,5 +1,8 @@
 import os
 from .base_logger import BaseLogger
+from ppocr.utils.logging import get_logger
+
+logger = get_logger()
 
 
 class WandbLogger(BaseLogger):
@@ -11,7 +14,7 @@ def __init__(
         entity=None,
         save_dir=None,
         config=None,
-        **kwargs
+        **kwargs,
     ):
         try:
             import wandb

tests/test_paddleocr_api.py

@@ -0,0 +1,37 @@
+import pytest
+import cv2
+from paddleocr import PaddleOCR
+
+
+@pytest.fixture
+def ocr():
+    return PaddleOCR(lang="en")
+
+
+@pytest.fixture
+def img():
+    return cv2.imread("doc/imgs/1.jpg")
+
+
+def test_ocr_with_detection_and_recognition(ocr, img):
+    result = ocr.ocr(img, det=True, rec=True)
+    assert result is not None
+    assert isinstance(result, list)
+
+
+def test_ocr_with_detection_only(ocr, img):
+    result = ocr.ocr(img, det=True, rec=False)
+    assert result is not None
+    assert isinstance(result, list)
+
+
+def test_ocr_with_recognition_only(ocr, img):
+    result = ocr.ocr(img, det=False, rec=True)
+    assert result is not None
+    assert isinstance(result, list)
+
+
+def test_ocr_without_detection_and_recognition(ocr, img):
+    result = ocr.ocr(img, det=False, rec=False)
+    assert result is not None
+    assert isinstance(result, list)