Files
modelscope/maas_lib/preprocessors/image.py
wenmeng.zwm db4a8be9c5 [to #41669377] docs and tools refinement and release
1. add build_doc linter script
2. add sphinx-docs support
3. add development doc and api doc
4. change version to 0.1.0 for the first internal release version

Link: https://code.aone.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/8775307
2022-05-20 16:51:34 +08:00

71 lines
2.3 KiB
Python

# Copyright (c) Alibaba, Inc. and its affiliates.
import io
from typing import Dict, Union
from PIL import Image, ImageOps
from maas_lib.fileio import File
from maas_lib.utils.constant import Fields
from .builder import PREPROCESSORS
@PREPROCESSORS.register_module(Fields.image)
class LoadImage:
"""Load an image from file or url.
Added or updated keys are "filename", "img", "img_shape",
"ori_shape" (same as `img_shape`), "pad_shape" (same as `img_shape`),
"scale_factor" (1.0) and "img_norm_cfg" (means=0 and stds=1).
Args:
mode (str): See :ref:`PIL.Mode<https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes>`.
to_float32 (bool): Whether to convert the loaded image to a float32
numpy array. If set to False, the loaded image is an uint8 array.
Defaults to False.
"""
def __init__(self, mode='rgb'):
self.mode = mode.upper()
def __call__(self, input: Union[str, Dict[str, str]]):
"""Call functions to load image and get image meta information.
Args:
input (str or dict): input image path or input dict with
a key `filename`.
Returns:
dict: The dict contains loaded image.
"""
if isinstance(input, dict):
image_path_or_url = input['filename']
else:
image_path_or_url = input
bytes = File.read(image_path_or_url)
# TODO @wenmeng.zwm add opencv decode as optional
# we should also look at the input format which is the most commonly
# used in Mind' image related models
with io.BytesIO(bytes) as infile:
img = Image.open(infile)
img = ImageOps.exif_transpose(img)
img = img.convert(self.mode)
results = {
'filename': image_path_or_url,
'img': img,
'img_shape': (img.size[1], img.size[0], 3),
'img_field': 'img',
}
return results
def __repr__(self):
repr_str = (f'{self.__class__.__name__}(' f'mode={self.mode})')
return repr_str
def load_image(image_path_or_url: str) -> Image.Image:
""" simple interface to load an image from file or url
Args:
image_path_or_url (str): image file path or http url
"""
loader = LoadImage()
return loader(image_path_or_url)['img']