class Array(PyBioSchema):
name = fields.String(required=True)
axes = fields.Axes(missing=None)
data_type = fields.String(required=True)
data_range = fields.Tuple((fields.Float(allow_nan=True), fields.Float(allow_nan=True)))
shape: fields.Nested
class ScaleRange(PyBioSchema):
mode = fields.ProcMode(required=True,
valid_modes=("per_dataset", "per_sample"))
axes = fields.Axes(required=True, valid_axes="czyx")
min_percentile = fields.Float(required=True,
validate=validate.Range(
0,
100,
min_inclusive=True,
max_inclusive=True))
max_percentile = fields.Float(
required=True,
validate=validate.Range(1,
100,
min_inclusive=False,
max_inclusive=True)
) # as a precaution 'max_percentile' needs to be greater than 1
@validates_schema
def min_smaller_max(self, data, **kwargs):
min_p = data["min_percentile"]
max_p = data["max_percentile"]
if min_p >= max_p:
raise PyBioValidationException(
f"min_percentile {min_p} >= max_percentile {max_p}")
class ScaleLinear(PyBioSchema):
axes = fields.Axes(required=True, valid_axes="czyx")
gain = fields.Array(fields.Float(), missing=fields.Float(
missing=1.0)) # todo: check if gain match input axes
offset = fields.Array(
fields.Float(), missing=fields.Float(
missing=0.0)) # todo: check if offset match input axes
@validates_schema
def either_gain_or_offset(self, data, **kwargs):
if data["gain"] == 1.0 and data["offset"] == 0:
raise PyBioValidationException(
"Specify gain!=1.0 or offset!=0.0")
class Tensor(PyBioSchema):
name = fields.String(required=True,
validate=validate.Predicate("isidentifier"),
bioimageio_description="Tensor name.")
description = fields.String(missing=None)
axes = fields.Axes(
required=True,
bioimageio_description=
"""Axes identifying characters from: bitczyx. Same length and order as the axes in `shape`.
| character | description |
| --- | --- |
| b | batch (groups multiple samples) |
| i | instance/index/element |
| t | time |
| c | channel |
| z | spatial dimension z |
| y | spatial dimension y |
| x | spatial dimension x |""",
)
data_type = fields.String(
required=True,
bioimageio_description=
"The data type of this tensor. For inputs, only `float32` is allowed and the consumer "
"software needs to ensure that the correct data type is passed here. For outputs can be any of `float32, "
"float64, (u)int8, (u)int16, (u)int32, (u)int64`. The data flow in bioimage.io models is explained "
"[in this diagram.](https://docs.google.com/drawings/d/1FTw8-Rn6a6nXdkZ_SkMumtcjvur9mtIhRqLwnKqZNHM/edit).",
)
data_range = fields.Tuple(
(fields.Float(allow_nan=True), fields.Float(allow_nan=True)),
missing=(None, None),
bioimageio_description=
"Tuple `(minimum, maximum)` specifying the allowed range of the data in this tensor. "
"If not specified, the full data range that can be expressed in `data_type` is allowed.",
)
shape: fields.Union
processing_name: str
@validates_schema
def validate_processing_kwargs(self, data, **kwargs):
axes = data["axes"]
processing_list = data.get(self.processing_name, [])
for processing in processing_list:
name = processing.name
kwargs = processing.kwargs or {}
kwarg_axes = kwargs.get("axes", "")
if any(a not in axes for a in kwarg_axes):
raise PyBioValidationException(
"`kwargs.axes` needs to be subset of axes")
class ZeroMeanUnitVariance(PyBioSchema):
mode = fields.ProcMode(required=True)
axes = fields.Axes(required=True, valid_axes="czyx")
mean = fields.Array(
fields.Float(), missing=None
) # todo: check if means match input axes (for mode 'fixed')
std = fields.Array(fields.Float(), missing=None)
eps = fields.Float(missing=1e-6)
@validates_schema
def mean_and_std_match_mode(self, data, **kwargs):
if data["mode"] == "fixed" and (data["mean"] is None
or data["std"] is None):
raise PyBioValidationException(
"`kwargs` for 'zero_mean_unit_variance' preprocessing with `mode` 'fixed' require additional `kwargs`: `mean` and `std`."
)
elif data["mode"] != "fixed" and (data.get("mean") is not None
or data.get("std") is not None):
raise PyBioValidationException(
"`kwargs`: `mean` and `std` for 'zero_mean_unit_variance' preprocessing are only valid for `mode` 'fixed'."
)
class Clip(PyBioSchema):
min = fields.Float(required=True)
max = fields.Float(required=True)
class Binarize(
Schema
): # do not inherit from PyBioSchema, return only a validated dict, no specific node
threshold = fields.Float(required=True)