srproj_reader

data.dataset.srproj_reader

path_interpreter

path_interpreter(code: str) -> Tuple[str, str, str, str]

data path interpreter

Parameters:

• code (str) –

  dataset code (rule: {domain}-{source}-{category}) (ex) sample dataset for cls: "test_directory-sample-cls")

Raises:

• RuntimeError –

  invalid classifier keys (code) for srproj code.

• Exception –

  wrong type of input code

Returns:

• Tuple[str, str, str, str] –

  Tuple[str, str, str, str]: absolute path for dataset, domain, source, category

Source code in SaigeToolkit/data/dataset/srproj_reader.py

def path_interpreter(code: str) -> Tuple[str, str, str, str]:
    """data path interpreter

    Args:
        code (str): dataset code (rule: {domain}-{source}-{category})
            (ex) sample dataset for cls: "test_directory-sample-cls")

    Raises:
        RuntimeError: invalid classifier keys (code) for srproj code.
        Exception: wrong type of input code

    Returns:
        Tuple[str, str, str, str]: absolute path for dataset, domain, source, category
    """

    if os.path.isdir(code) or os.path.isfile(code):
        # correct directory/file
        path = code
        keys = os.path.dirname(os.path.dirname(path)).split(os.sep)
        keys = keys + ["dummy" for _ in range(3 - len(keys))]
        domain, source, category = keys[-3:]
    else:
        # wrong directory/file/code
        raise Exception(f"Wrong Directory / File / Code: {code}")

    return path, domain, source, category

read_srproj

read_srproj(code: str, split: str, two_class: bool = False, mode: Optional[str] = None, use_absolute_path: bool = False, srproj_image_directory: Optional[str] = None, system_image_directory: Optional[str] = None, get_class_colors: bool = False, skip_problematic_files: bool = False) -> Tuple[List[Dict], int, Union[List[str], List[Dict]]]

read srproj dataset from file-system.

Parameters:

• code (str) –

  dataset code.

• split (str) –

  split dataset, "Training" or "Validation".

• two_class (bool, default: False ) –

  load data as two class mode (ex) normal <-> abnormal)

• mode (Optional[str], default: None ) –

  select data label type.

• use_absolute_path (bool, default: False ) –

  use the image path in srproj as is.

• srproj_image_directory (Optional[str], default: None ) –

  srproj 파일에 작성된 이미지 경로를 현재 시스템 상의 이미지 경로로 변환하기 위해 치환해야 하는 이미지 폴더 경로. None이면 SaigeDatabase 규칙 사용.

• system_image_directory (Optional[str], default: None ) –

  코드가 구동되는 시스템 상의 이미지 폴더 경로. None이면 SaigeDatabase 규칙 사용.

• get_class_colors(bool) –

  srproj에 정의된 각 클래스의 color를 받을지 여부. True이면

• skip_problematic_files(bool) –

  srproj 파일에 작성된 이미지 경로로부터 이미지들을 읽을 때, 해당 파라미터가 True 라면, 파일이 실제 존재하지 않거나, 읽다가 문제가 발생할 경우 해당 파일을 제외하고 나머지 파일을 계속 읽음. 만약, False라면 Error를 raise 함.

Returns:

• Tuple[List[Dict], int, Union[List[str], List[Dict]]] –

  Tuple[List[Dict], int, Union[List[str], List[Dict]]]: list of meta data dicts, number of classes, and list of class names or dict

Note

.sproj 파일에는 각 이미지들의 경로와 라벨 정보 등이 포함되어 있습니다. 이때 이미지 경로는 해당 파일을 생성한 PC 기준의 절대 경로로 작성되어 있기 때문에, 현재 이 코드가 실행되는 시스템에서의 경로로 변환해 주어야 합니다. 현재 이미지 경로 변환 옵션은 3가지가 존재합니다. 1. sproj를 생성한 PC에서 코드를 실행하는 경우, use_absolute_path= True로 세팅하면 srproj에 작성된 이미지 경로를 그대로 사용합니다. 2. 이미지와 srproj가 SaigeDatabase 룰에 맞게 구성된 경우, 이미지는 images 폴더에 하위에 있고 (root/images/.../xxx.png) srproj는 images 폴더보다 한 단계 아래 경로에 있어야 합니다 (root/projects/xxx.srproj) 이때는srproj_image_directory= None,system_image_directory= None 으로 설정합니다. 3. 이미지와 srproj가 SaigeDatabase 룰을 따르지 않는 경우,srproj_image_directory와system_image_directory`를 설정하면 srproj에 작성된 이미지 경로를 다음 규칙으로 변환합니다: {srproj_image_directory}/.../xxx.png -> {system_image_directory}/.../xxx.png

Source code in SaigeToolkit/data/dataset/srproj_reader.py

def read_srproj(
    code: str,
    split: str,
    two_class: bool = False,
    mode: Optional[str] = None,
    use_absolute_path: bool = False,
    srproj_image_directory: Optional[str] = None,
    system_image_directory: Optional[str] = None,
    get_class_colors: bool = False,
    skip_problematic_files: bool = False,
) -> Tuple[List[Dict], int, Union[List[str], List[Dict]]]:
    """read srproj dataset from file-system.

    Args:
        code (str): dataset code.
        split (str): split dataset, "Training" or "Validation".
        two_class (bool): load data as two class mode (ex) normal <-> abnormal)
        mode (Optional[str]): select data label type.
        use_absolute_path (bool): use the image path in srproj as is.
        srproj_image_directory (Optional[str]): srproj 파일에 작성된 이미지 경로를 현재 시스템 상의 이미지 경로로 변환하기 위해
                                                치환해야 하는 이미지 폴더 경로. None이면 SaigeDatabase 규칙 사용.
        system_image_directory (Optional[str]): 코드가 구동되는 시스템 상의 이미지 폴더 경로. None이면 SaigeDatabase 규칙 사용.
        get_class_colors(bool): srproj에 정의된 각 클래스의 color를 받을지 여부. True이면
        skip_problematic_files(bool): srproj 파일에 작성된 이미지 경로로부터 이미지들을 읽을 때, 해당 파라미터가 True 라면,
                                      파일이 실제 존재하지 않거나, 읽다가 문제가 발생할 경우 해당 파일을 제외하고 나머지 파일을 계속 읽음.
                                      만약, False라면 Error를 raise 함.

    Returns:
        Tuple[List[Dict], int, Union[List[str], List[Dict]]]:
            list of meta data dicts, number of classes, and list of class names or dict

    Note:
        .sproj 파일에는 각 이미지들의 경로와 라벨 정보 등이 포함되어 있습니다.
        이때 이미지 경로는 해당 파일을 생성한 PC 기준의 절대 경로로 작성되어 있기 때문에, 현재 이 코드가 실행되는 시스템에서의 경로로 변환해 주어야 합니다.
        현재 이미지 경로 변환 옵션은 3가지가 존재합니다.
        1. sproj를 생성한 PC에서 코드를 실행하는 경우,
            use_absolute_path` = True로 세팅하면 srproj에 작성된 이미지 경로를 그대로 사용합니다.
        2. 이미지와 srproj가 SaigeDatabase 룰에 맞게 구성된 경우,
            이미지는 images 폴더에 하위에 있고 (root/images/.../xxx.png)
            srproj는 images 폴더보다 한 단계 아래 경로에 있어야 합니다 (root/projects/xxx.srproj)
            이때는 `srproj_image_directory` = None, `system_image_directory` = None 으로 설정합니다.
        3. 이미지와 srproj가 SaigeDatabase 룰을 따르지 않는 경우,
            `srproj_image_directory`와 `system_image_directory`를 설정하면
            srproj에 작성된 이미지 경로를 다음 규칙으로 변환합니다:
            {srproj_image_directory}/.../xxx.png -> {system_image_directory}/.../xxx.png

    """

    path, domain, source, category = path_interpreter(code)

    # Check if "path" is directory
    if os.path.isdir(path):
        srproj_list = [os.path.join(path, f) for f in os.listdir(path) if f.endswith(".srproj")]
        path = np.random.choice(srproj_list)

    # Read srproj
    with open(path, encoding="utf-8") as file:
        txt = file.read()
    srproj = xmltodict.parse(txt, dict_constructor=dict)["Project"]

    # Config mode
    if mode is None:
        mode = srproj["Type"]

    # Return empty list when dummy.srproj
    if srproj["ImageGroup"]["Image"] is None:
        return [], 0, []

    # Config files
    image_list = (
        srproj["ImageGroup"]["Image"]
        if isinstance(srproj["ImageGroup"]["Image"], list)
        else [srproj["ImageGroup"]["Image"]]
    )
    assert split in [
        "Training",
        "Validation",
        "All",
    ], "Split for *.srproj Should be 'Training' or 'Validation'"
    if split == "All":
        files = [l for l in image_list]
    else:
        files = [l for l in image_list if l["SplitState"] == split]
    files = check_label(files, mode)

    n_classes = 0

    image_path_converter = lambda srproj_image_path: srproj_image_path
    if not use_absolute_path:
        if srproj_image_directory is None:
            srproj_image_path = (
                files[0]["Path"] if "Path" in files[0] else files[0]["PathGroup"]["Path"][0]
            )
            srproj_image_path = srproj_image_path.replace("\\", os.sep)
            srproj_image_directory = srproj_image_path.split(os.sep + "images" + os.sep)[0]
        srproj_image_directory = srproj_image_directory.replace("\\", os.sep)

        if system_image_directory is None:
            system_image_directory = os.path.dirname(os.path.dirname(path))

        assert os.path.isdir(
            system_image_directory
        ), f"Image data should be in following directory: {system_image_directory}"

        image_path_converter = lambda srproj_image_path: os.path.join(
            system_image_directory,
            os.path.relpath(srproj_image_path.replace("\\", os.sep), srproj_image_directory),
        )

    def _update_file_information(file: Dict) -> bool:
        image_path = file["image_path"]
        if isinstance(image_path, List):
            image_path = image_path[0]

        if os.path.isfile(image_path):
            try:
                with Image.open(image_path) as image_file:
                    # NOTE: https://github.com/python-pillow/Pillow/blob/main/src/PIL/ImageOps.py#LL579C2-L579C2
                    orientation = image_file.getexif().get(0x0112)
                    if orientation in range(2, 9):
                        img_size = list(ImageOps.exif_transpose(image_file).size)
                    else:
                        img_size = list(image_file.size)
            except (IOError, OSError):
                if skip_problematic_files:
                    return False
                raise error.InvalidImageFileError
        else:
            if skip_problematic_files:
                print(f"image not found: {file['image_path']}")
                return False
            raise error.FileNotFoundError

        file.update(
            {
                "domain": domain,
                "source": source,
                "category": category,
                "image_size": img_size,
                "label_extension": "srproj",
                "mode": mode,
            }
        )

        if mode == "Classification":
            lbl = int(file["ClassIndexOfLabel"])
            if two_class:
                lbl = 1 if (lbl > 0) else lbl

            file["ClassIndexOfLabel"] = lbl + n_classes

        elif mode == "MultiLabelClassification":
            lbl = list(file["ClassIndexOfLabel"])
            file["ClassIndexOfLabel"] = [int(l) + n_classes for l in lbl]

        elif mode == "Segmentation":
            if str(file["LabelGroup"]["IsNormal"]) in ["False", "false", "FALSE"]:
                lbl_list = (
                    file["LabelGroup"]["Label"]
                    if isinstance(file["LabelGroup"]["Label"], list)
                    else [file["LabelGroup"]["Label"]]
                )
                for l in lbl_list:
                    lbl = 1 if two_class else int(l["ClassIndex"]) + 1
                    l["ClassIndex"] = lbl + n_classes

        return True

    cleaned_files = []
    for f in files:
        if "Path" in f:
            f["image_path"] = image_path_converter(f["Path"])
        else:
            f["image_path"] = [image_path_converter(_path) for _path in f["PathGroup"]["Path"]]

        is_updated = _update_file_information(f)
        if is_updated:
            cleaned_files.append(f)

    # Config n_classes
    classes = []
    if "ClassGroup" in srproj:
        n_classes = int(srproj["ClassGroup"]["NumberOfClasses"])
        class_list = (
            srproj["ClassGroup"]["Class"]
            if isinstance(srproj["ClassGroup"]["Class"], list)
            else [srproj["ClassGroup"]["Class"]]
        )
        if get_class_colors:
            classes = [
                {
                    "name": class_["Name"],
                    "color": convert_srproj_class_color_to_rgb(int(class_["Color"])),
                }
                for class_ in class_list
            ]
        else:
            classes = [class_["Name"] for class_ in class_list]
    elif "CharacterGroup" in srproj:
        classes = srproj["CharacterGroup"]["Included"]["@xmlns"]
        n_classes = len(classes) + 1

    if mode in ["Segmentation"]:
        if isinstance(classes[0], dict):
            classes.insert(0, {"name": "background", "color": (0, 0, 0)})
        else:
            classes.insert(0, "background")
        n_classes = len(classes)

    if two_class:
        classes = ["Normal", "Defect"]
        n_classes = len(classes)

    return cleaned_files, n_classes, classes

check_label

check_label(files: List[Dict], mode: str) -> List[Dict]

check all data label is valid. If any data is corrupted, pop out from meta data list.

Parameters:

• files (List[Dict]) –

  meta data list to be checked

• mode (str) –

  label data type

Returns:

• List[Dict] –

  List[Dict]: cleaned meta data list

Source code in SaigeToolkit/data/dataset/srproj_reader.py

def check_label(files: List[Dict], mode: str) -> List[Dict]:
    """check all data label is valid.
    If any data is corrupted, pop out from meta data list.

    Args:
        files (List[Dict]): meta data list to be checked
        mode (str): label data type

    Returns:
        List[Dict]: cleaned meta data list
    """
    for i in range(len(files) - 1, -1, -1):
        if mode == "Classification":
            if int(files[i]["ClassIndexOfLabel"]) == -1:
                files.pop(i)
        elif mode == "MultiLabelClassification":
            if not isinstance(files[i]["ClassIndexOfLabel"], list):
                files[i]["ClassIndexOfLabel"] = [files[i]["ClassIndexOfLabel"]]

        elif mode == "OpticalCharacterRecognition":
            if int(files[i]["LabelGroup"].get("NumberOfLabels", 0)) == 0:
                continue
            labels = (
                files[i]["LabelGroup"]["Label"]
                if isinstance(files[i]["LabelGroup"]["Label"], list)
                else [files[i]["LabelGroup"]["Label"]]
            )
            for idx in range(len(labels) - 1, -1, -1):
                # XXX: Temporary implementation for memory issue
                for key, value in labels[idx]["Coordinate"].items():
                    labels[idx]["Coordinate"][key] = float(value)

                if labels[idx]["Characters"] == '"value4"':
                    labels.pop(idx)
                elif not labels[idx]["Characters"]:
                    labels.pop(idx)
                else:
                    continue

                files[i]["LabelGroup"]["Label"] = labels
                files[i]["LabelGroup"]["NumberOfLabels"] = len(labels)

        else:
            if str(files[i]["LabelGroup"]["IsNormal"]) in [
                "False",
                "false",
                "FALSE",
            ]:
                if int(files[i]["LabelGroup"].get("NumberOfLabels", 0)) == 0:
                    files.pop(i)
    return files

load_srproj_label

load_srproj_label(file: Dict, use_crop_fn: Optional[bool] = False, **kwargs) -> Dict

load single data dict from srproj meta data.

Parameters:

• file (Dict) –

  single meta data dict

• use_crop_fn (bool, default: False ) –

  Whether to use the crop function. Defaults to False.

Raises:

• NotImplementedError –

  only four modes are available. ["Classification", "Detection", "Segmentation", "OpticalCharacterRecognition"]

Returns:

• Dict ( Dict ) –

  label data as dict

Source code in SaigeToolkit/data/dataset/srproj_reader.py

def load_srproj_label(file: Dict, use_crop_fn: Optional[bool] = False, **kwargs) -> Dict:
    """load single data dict from srproj meta data.

    Args:
        file (Dict): single meta data dict
        use_crop_fn (bool, optional): Whether to use the crop function.
            Defaults to False.

    Raises:
        NotImplementedError: only four modes are available.
            ["Classification", "Detection", "Segmentation", "OpticalCharacterRecognition"]

    Returns:
        Dict: label data as dict
    """
    mode = file["mode"]

    # make label for the right mode
    if mode == "Classification":
        label = load_label_cls(file, **kwargs)

    elif mode == "Detection":
        label = load_label_det(file, **kwargs)

    elif mode == "Segmentation":
        # In Segmentation task, need polygon data to use the crop function.
        label = load_label_seg(file, return_polygon=use_crop_fn, **kwargs)

    elif mode == "OpticalCharacterRecognition":
        label = load_label_ocr(file, **kwargs)

    else:
        raise NotImplementedError(f"Mode {mode} not implemented")

    return label

load_label_cls

load_label_cls(file: Dict) -> Dict

Source code in SaigeToolkit/data/dataset/srproj_reader.py

def load_label_cls(file: Dict) -> Dict:
    return {"class": file["ClassIndexOfLabel"]}

load_label_det

load_label_det(file: Dict) -> Dict

load detection label

Parameters:

• file (Dict) –

  meta data for detection label

Returns:

• Dict ( Dict ) –

  detection label data dict

  {
      "bboxes": [
          [x, y, w, h],
          ...,
      ],
      "labels": List[int],
  }
  

Source code in SaigeToolkit/data/dataset/srproj_reader.py

def load_label_det(file: Dict) -> Dict:
    """load detection label

    Args:
        file (Dict): meta data for detection label

    Returns:
        Dict: detection label data dict
            ```python
            {
                "bboxes": [
                    [x, y, w, h],
                    ...,
                ],
                "labels": List[int],
            }
            ```
    """
    srproj_label_group = file["LabelGroup"]
    label = {"bboxes": [], "labels": []}

    if str(srproj_label_group["IsNormal"]).lower() == "false":
        srproj_labels = srproj_label_group["Label"]
        if not isinstance(srproj_labels, list):
            srproj_labels = [srproj_labels]
        for srproj_label in srproj_labels:
            x = int(srproj_label["Coordinate"]["@X"])
            y = int(srproj_label["Coordinate"]["@Y"])
            w = int(srproj_label["Coordinate"]["@Width"])
            h = int(srproj_label["Coordinate"]["@Height"])
            label["bboxes"].append([x, y, w, h])
            label["labels"].append(int(srproj_label["ClassIndex"]))

    return label

load_label_seg

load_label_seg(file: Dict, return_polygon: bool = True, mask_to_pil: bool = False) -> Dict

load segmentation label

Parameters:

• file (Dict) –

  meta data for segmentation label

• return_polygon (bool, default: True ) –

  whether return polygon data. Defaults to True.

• mask_to_pil (bool, default: False ) –

  whether return mask as PIL.Image. Defaults to False.

Returns:

• Dict ( Dict ) –

  segmentation label data dict

Source code in SaigeToolkit/data/dataset/srproj_reader.py

def load_label_seg(file: Dict, return_polygon: bool = True, mask_to_pil: bool = False) -> Dict:
    """load segmentation label

    Args:
        file (Dict): meta data for segmentation label
        return_polygon (bool, optional): whether return polygon data. Defaults to True.
        mask_to_pil (bool, optional): whether return mask as PIL.Image. Defaults to False.

    Returns:
        Dict: segmentation label data dict
    """
    w, h = file["image_size"]
    lbl = np.zeros((h, w), dtype=np.uint8)

    lbl_list = file["LabelGroup"]

    if str(lbl_list["IsNormal"]) in ["False", "false", "FALSE"]:
        lbl_list = lbl_list["Label"] if isinstance(lbl_list["Label"], list) else [lbl_list["Label"]]
        contour = []
        for l in lbl_list:
            canvas = np.zeros((h, w), dtype=np.uint8)
            color = l["ClassIndex"]

            contour_list = (
                l["ContourGroup"]["Contour"]
                if isinstance(l["ContourGroup"]["Contour"], list)
                else [l["ContourGroup"]["Contour"]]
            )

            # Contour functions in cv2 gets list type contours
            contours = {"Outer": [], "Inner": []}
            for c_l in contour_list:
                contours[c_l["@Type"]].append(
                    np.array([[int(p["@X"]), int(p["@Y"])] for p in c_l["Point"]])
                )

            # One Outer per One Label
            cv2.fillPoly(canvas, pts=contours["Outer"], color=color)

            # Many Inner could exist in One Label
            if contours["Inner"]:
                cv2.fillPoly(canvas, pts=contours["Inner"], color=0)

            nonzeros = canvas > 0
            lbl[nonzeros] = canvas[nonzeros]
            contour.append(contours["Outer"][0])
    else:
        contour = []

    if mask_to_pil:
        lbl = Image.fromarray(lbl)

    lbl = {"mask": lbl}

    if return_polygon:
        lbl.update({"polygons": contour})

    return lbl

load_label_ocr

load_label_ocr(file: Dict) -> Dict

load ocr label

Parameters:

• file (Dict) –

  meta data for ocr label

Returns:

• Dict ( Dict ) –

  ocr label data dict

Source code in SaigeToolkit/data/dataset/srproj_reader.py

def load_label_ocr(file: Dict) -> Dict:
    """load ocr label

    Args:
        file (Dict): meta data for ocr label

    Returns:
        Dict: ocr label data dict
    """
    lbl_list = file["LabelGroup"]

    if int(lbl_list.get("NumberOfLabels", 0)) == 0:
        return {"polygons": [], "strings": [], "ignore": []}

    pols, strs = [], []

    lbl_list = lbl_list["Label"] if isinstance(lbl_list["Label"], list) else [lbl_list["Label"]]
    for l in lbl_list:
        if not l["Characters"]:
            continue
        # if self.ignore_whitespace:
        #     l["Characters"] = l["Characters"].replace(" ", "")
        strs.append(l["Characters"])
        n_point = max(
            [
                int(key.replace("@Vertex", "").replace("X", "").replace("Y", ""))
                for key in l["Coordinate"].keys()
                if "@Vertex" in key
            ]
        )
        pols.append(
            np.array(
                [
                    [
                        float(l["Coordinate"][f"@Vertex{idx + 1}X"]),
                        float(l["Coordinate"][f"@Vertex{idx + 1}Y"]),
                    ]
                    for idx in range(n_point)
                ]
            )
        )

    strings, kie_labels = [], []
    for string in strs:
        string, kie_label = _refine_kie_labels(string)
        strings.append(string)
        kie_labels.append(kie_label)

    ignore = [s is None for s in strs]

    lbl = {"polygons": pols, "strings": strings, "kie_labels": kie_labels, "ignore": ignore}

    return lbl

_refine_kie_labels

_refine_kie_labels(string)

Source code in SaigeToolkit/data/dataset/srproj_reader.py

def _refine_kie_labels(string):
    # split kie_label and string_label
    if string.startswith('"key'):
        index = string[1:].find('"') + 1

        kie_label = 2 * int(string[4:index]) + 1 if index > 4 else 0
        string = string[index + 1 :]

    elif string.startswith('"value'):
        index = string[1:].find('"') + 1

        kie_label = 2 * int(string[6:index]) + 2 if index > 6 else 0
        string = string[index + 1 :]

    else:
        kie_label = 0

    if kie_label < 0:
        kie_label = 0

    return string, kie_label

merge_srproj_classes

merge_srproj_classes(classes1, classes2)

Source code in SaigeToolkit/data/dataset/srproj_reader.py

def merge_srproj_classes(classes1, classes2):
    if classes1 == classes2:
        return classes1

    if len(classes1) > len(classes2):
        classes1, classes2 = classes2, classes1

    if classes2[: len(classes1)] != classes1:
        raise RuntimeError("two srproj cannot be mixed")

    return classes2

convert_srproj_class_color_to_rgb

convert_srproj_class_color_to_rgb(argb: int) -> Tuple[int, int, int]

srproj의 각 클래스 색 코드를 rgb 값으로 변환합니다.

Source code in SaigeToolkit/data/dataset/srproj_reader.py

def convert_srproj_class_color_to_rgb(argb: int) -> Tuple[int, int, int]:
    """srproj의 각 클래스 색 코드를 rgb 값으로 변환합니다."""
    a = (argb >> 24) & 255
    r = (argb >> 16) & 255
    g = (argb >> 8) & 255
    b = argb & 255
    return (r, g, b)