File size: 7,043 Bytes
2999792 096602f 2999792 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | # Copyright 2024 The SSL4EO-S12 Authors and The HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Image processor for SSL4EO ViT models."""
from typing import Optional, Union
import numpy as np
from transformers.image_processing_utils import BaseImageProcessor, BatchFeature, get_size_dict
from transformers.image_transforms import resize, to_channel_dimension_format
from transformers.image_utils import (
ChannelDimension,
ImageInput,
PILImageResampling,
infer_channel_dimension_format,
make_flat_list_of_images,
to_numpy_array,
valid_images,
validate_preprocess_arguments,
)
from transformers.utils import TensorType, filter_out_non_signature_kwargs, logging
logger = logging.get_logger(__name__)
def _resize_multispectral(image: np.ndarray, size: dict[str, int], input_data_format: ChannelDimension) -> np.ndarray:
target_height, target_width = size["height"], size["width"]
if input_data_format == ChannelDimension.FIRST:
image = np.transpose(image, (1, 2, 0))
height, width, _ = image.shape
if height == target_height and width == target_width:
resized = image
else:
try:
import cv2
except ImportError as exc:
raise ImportError(
"Multispectral resize requires OpenCV (`opencv-python`) when input has more than 4 channels."
) from exc
resized = cv2.resize(image, (target_width, target_height), interpolation=cv2.INTER_LINEAR)
if input_data_format == ChannelDimension.FIRST:
return np.transpose(resized, (2, 0, 1))
return resized
class SSL4EOViTImageProcessor(BaseImageProcessor):
"""
Image processor for SSL4EO ViT models.
SSL4EO models are trained on uint8 Sentinel imagery rescaled to `[0, 1]` by dividing by 255.
No per-channel normalization is applied by default, matching the original SSL4EO-S12 benchmark code.
"""
model_input_names = ["pixel_values"]
def __init__(
self,
do_resize: bool = False,
size: Optional[dict[str, int]] = None,
resample: PILImageResampling = PILImageResampling.BILINEAR,
do_rescale: bool = True,
rescale_factor: float = 1 / 255.0,
do_normalize: bool = False,
image_mean: Optional[Union[float, list[float]]] = None,
image_std: Optional[Union[float, list[float]]] = None,
do_convert_rgb: bool = False,
**kwargs,
):
super().__init__(**kwargs)
size = size if size is not None else {"height": 224, "width": 224}
self.do_resize = do_resize
self.size = size
self.resample = resample
self.do_rescale = do_rescale
self.rescale_factor = rescale_factor
self.do_normalize = do_normalize
self.image_mean = image_mean
self.image_std = image_std
self.do_convert_rgb = do_convert_rgb
@filter_out_non_signature_kwargs()
def preprocess(
self,
images: ImageInput,
do_resize: Optional[bool] = None,
size: Optional[dict[str, int]] = None,
resample: Optional[PILImageResampling] = None,
do_rescale: Optional[bool] = None,
rescale_factor: Optional[float] = None,
do_normalize: Optional[bool] = None,
image_mean: Optional[Union[float, list[float]]] = None,
image_std: Optional[Union[float, list[float]]] = None,
return_tensors: Optional[Union[str, TensorType]] = None,
data_format: Union[str, ChannelDimension] = ChannelDimension.FIRST,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
do_convert_rgb: Optional[bool] = None,
):
do_resize = do_resize if do_resize is not None else self.do_resize
size = size if size is not None else self.size
size = get_size_dict(size, default_to_square=True)
resample = resample if resample is not None else self.resample
do_rescale = do_rescale if do_rescale is not None else self.do_rescale
rescale_factor = rescale_factor if rescale_factor is not None else self.rescale_factor
do_normalize = do_normalize if do_normalize is not None else self.do_normalize
image_mean = image_mean if image_mean is not None else self.image_mean
image_std = image_std if image_std is not None else self.image_std
do_convert_rgb = do_convert_rgb if do_convert_rgb is not None else self.do_convert_rgb
if do_normalize and (image_mean is None or image_std is None):
raise ValueError(
"Normalization requires `image_mean` and `image_std` with one value per channel."
)
images = make_flat_list_of_images(images)
if not valid_images(images):
raise ValueError("Invalid image type. Must be PIL, numpy, or torch tensor.")
validate_preprocess_arguments(
do_rescale=do_rescale,
rescale_factor=rescale_factor,
do_normalize=do_normalize,
image_mean=image_mean,
image_std=image_std,
do_resize=do_resize,
size=size,
resample=resample,
)
processed_images = []
for image in images:
image = to_numpy_array(image)
if do_convert_rgb:
image = self._convert_image_to_rgb(image)
if input_data_format is None:
try:
input_data_format = infer_channel_dimension_format(image)
except ValueError:
input_data_format = ChannelDimension.LAST
num_channels = image.shape[-1] if input_data_format == ChannelDimension.LAST else image.shape[0]
if do_resize:
if num_channels > 4:
image = _resize_multispectral(image, size=size, input_data_format=input_data_format)
else:
image = resize(image, size=size, resample=resample, input_data_format=input_data_format)
if do_rescale:
image = image * rescale_factor
if do_normalize:
image = self.normalize(image=image, mean=image_mean, std=image_std, input_data_format=input_data_format)
image = to_channel_dimension_format(image, data_format, input_channel_dim=input_data_format)
processed_images.append(image)
data = {"pixel_values": processed_images}
return BatchFeature(data=data, tensor_type=return_tensors)
__all__ = ["SSL4EOViTImageProcessor"]
|