|
|
""" |
|
|
Pydantic models for request/response validation. |
|
|
""" |
|
|
import enum |
|
|
from typing import Optional |
|
|
|
|
|
import pydantic |
|
|
|
|
|
|
|
|
class ImageData(pydantic.BaseModel): |
|
|
"""Image data model for base64 encoded images.""" |
|
|
mediaType: str |
|
|
data: str |
|
|
|
|
|
|
|
|
class ImageRequest(pydantic.BaseModel): |
|
|
"""Request model for image classification.""" |
|
|
image: ImageData |
|
|
|
|
|
|
|
|
class Labels(enum.IntEnum): |
|
|
Natural = 0 |
|
|
FullySynthesized = 1 |
|
|
LocallyEdited = 2 |
|
|
LocallySynthesized = 3 |
|
|
|
|
|
|
|
|
class LocalizationMask(pydantic.BaseModel): |
|
|
"""A bit mask indicating which pixels are manipulated / synthesized. |
|
|
|
|
|
A bit value of ``1`` means that the model believes the corresponding pixel |
|
|
has been edited or synthesized (i.e., its label would be non-zero). |
|
|
A bit value of ``0`` means that the model believes the pixel is unaltered. |
|
|
|
|
|
The mask ``.width`` and ``.height`` should be the same as the input image. |
|
|
Extra bits at the end of ``.bitsRowMajor`` after the first |
|
|
``width * height`` bits are **ignored**; for simplicity/efficiency, |
|
|
you should encode your bit mask into a byte array and not worry if the |
|
|
final byte isn't "full", then convert the byte array to base64. |
|
|
""" |
|
|
|
|
|
width: int = pydantic.Field( |
|
|
description="The width of the mask." |
|
|
) |
|
|
|
|
|
height: int = pydantic.Field( |
|
|
description="The height of the mask." |
|
|
) |
|
|
|
|
|
bitsRowMajor: str = pydantic.Field( |
|
|
description="A base64 string encoding the bit mask in row-major order.", |
|
|
|
|
|
|
|
|
pattern=r"^(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/][AQgw]==|[A-Za-z0-9+/]{2}[AEIMQUYcgkosw048]=)?$", |
|
|
) |
|
|
|
|
|
|
|
|
class PredictionResponse(pydantic.BaseModel): |
|
|
"""Response model for synthetic image classification results. |
|
|
|
|
|
Detector models will be scored primarily on their ability to classify the |
|
|
entire image into 1 of the 4 label categories:: |
|
|
|
|
|
0: (Natural) The image is natural / unaltered. |
|
|
1: (FullySynthesized) The entire image was synthesized by e.g., a |
|
|
generative image model. |
|
|
2: (LocallyEdited) The image is a natural image where a portion has |
|
|
been edited using traditional photo editing techniques such as |
|
|
splicing. |
|
|
3: (LocallySynthesized) The image is a natural image where a portion |
|
|
has been replaced by synthesized content. |
|
|
""" |
|
|
|
|
|
logprobs: list[float] = pydantic.Field( |
|
|
description="The log-probabilities for each of the 4 possible labels.", |
|
|
min_length=4, |
|
|
max_length=4, |
|
|
) |
|
|
|
|
|
localizationMask: Optional[LocalizationMask] = pydantic.Field( |
|
|
description="A bit mask localizing predicted edits. Models that are" |
|
|
" not capable of localization may omit this field. It may also be" |
|
|
" omitted if the predicted label is ``0`` or ``1``, in which case the" |
|
|
" mask will be assumed to be all 0's or all 1's, as appropriate." |
|
|
) |
