dataeval 0.72.2__tar.gz → 0.73.1__tar.gz

{dataeval-0.72.2 → dataeval-0.73.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dataeval
-Version: 0.72.2
+Version: 0.73.1
 Summary: DataEval provides a simple interface to characterize image data and its impact on model performance across classification and object-detection tasks
 Home-page: https://dataeval.ai/
 License: MIT
@@ -31,8 +31,8 @@ Requires-Dist: pillow (>=10.3.0)
 Requires-Dist: scikit-learn (>=1.5.0)
 Requires-Dist: scipy (>=1.10)
 Requires-Dist: tensorflow (>=2.16,<2.18) ; extra == "tensorflow" or extra == "all"
-Requires-Dist: tensorflow_probability (>=0.24) ; extra == "tensorflow" or extra == "all"
-Requires-Dist: tf-keras (>=2.16) ; extra == "tensorflow" or extra == "all"
+Requires-Dist: tensorflow_probability (>=0.24,<0.25) ; extra == "tensorflow" or extra == "all"
+Requires-Dist: tf-keras (>=2.16,<2.18) ; extra == "tensorflow" or extra == "all"
 Requires-Dist: torch (>=2.2.0) ; extra == "torch" or extra == "all"
 Requires-Dist: torchvision (>=0.17.0) ; extra == "torch" or extra == "all"
 Requires-Dist: tqdm

{dataeval-0.72.2 → dataeval-0.73.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dataeval"
-version = "0.72.2" # dynamic
+version = "0.73.1" # dynamic
 description = "DataEval provides a simple interface to characterize image data and its impact on model performance across classification and object-detection tasks"
 license = "MIT"
 readme = "README.md"
@@ -55,8 +55,8 @@ xxhash = {version = ">=3.3"}
 matplotlib = {version = "*", optional = true}
 markupsafe = {version = "<3.0.2", optional = true}
 tensorflow = {version = ">=2.16,<2.18", optional = true}
-tensorflow_probability = {version = ">=0.24", optional = true}
-tf-keras = {version = ">=2.16", optional = true}
+tensorflow_probability = {version = ">=0.24,<0.25", optional = true}
+tf-keras = {version = ">=2.16,<2.18", optional = true}
 torch = {version = ">=2.2.0", source = "pytorch", optional = true}
 torchvision = {version = ">=0.17.0", source = "pytorch", optional = true}
 
@@ -69,8 +69,7 @@ all = ["matplotlib", "markupsafe", "tensorflow", "tensorflow_probability", "tf-k
 optional = true
 
 [tool.poetry.group.dev.dependencies]
-tox = {version = "*"}
-tox-uv = {version = "*"}
+nox = {version = "*", extras = ["uv"]}
 uv = {version = "*"}
 poetry = {version = "*"}
 poetry-lock-groups-plugin = {version = "*"}
@@ -122,7 +121,6 @@ files = ["src/dataeval/__init__.py"]
 name = "dataeval"
 
 [tool.poetry2conda.dependencies]
-nvidia-cudnn-cu11 = { name = "cudnn" }
 tensorflow_probability = { name = "tensorflow-probability" }
 torch = { name = "pytorch" }
 xxhash = { name = "python-xxhash" }
@@ -142,12 +140,18 @@ concurrency = ["multiprocessing"]
 parallel = true
 
 [tool.coverage.report]
-exclude_also = ["raise NotImplementedError"]
+exclude_also = [
+  "raise NotImplementedError",
+  "if TYPE_CHECKING:",
+  "if _IS_TENSORFLOW_AVAILABLE",
+  "if _IS_TORCH_AVAILABLE",
+  "if _IS_TORCHVISION_AVAILABLE",
+]
 include = ["*/src/dataeval/*"]
 omit = [
   "*/torch/blocks.py",
   "*/torch/utils.py",
-  "*/tensorflow/_internal/pixelcnn.py",
+  "*/tensorflow/_internal/models.py",
 ]
 fail_under = 90
 
@@ -161,6 +165,7 @@ exclude = [
   "*env*",
   "output",
   "_build",
+  ".nox",
   ".tox",
   "prototype",
 ]

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.72.2"
+__version__ = "0.73.1"
 
 from importlib.util import find_spec
 
@@ -12,12 +12,12 @@ from dataeval import detectors, metrics  # noqa: E402
 
 __all__ = ["detectors", "metrics"]
 
-if _IS_TORCH_AVAILABLE:  # pragma: no cover
+if _IS_TORCH_AVAILABLE:
     from dataeval import workflows
 
     __all__ += ["workflows"]
 
-if _IS_TENSORFLOW_AVAILABLE or _IS_TORCH_AVAILABLE:  # pragma: no cover
+if _IS_TENSORFLOW_AVAILABLE or _IS_TORCH_AVAILABLE:
     from dataeval import utils
 
     __all__ += ["utils"]

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/detectors/__init__.py

@@ -7,7 +7,7 @@ from dataeval.detectors import drift, linters
 
 __all__ = ["drift", "linters"]
 
-if _IS_TENSORFLOW_AVAILABLE:  # pragma: no cover
+if _IS_TENSORFLOW_AVAILABLE:
     from dataeval.detectors import ood
 
     __all__ += ["ood"]

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/detectors/drift/__init__.py

@@ -10,7 +10,7 @@ from dataeval.detectors.drift.ks import DriftKS
 
 __all__ = ["DriftCVM", "DriftKS", "DriftOutput", "updates"]
 
-if _IS_TORCH_AVAILABLE:  # pragma: no cover
+if _IS_TORCH_AVAILABLE:
     from dataeval.detectors.drift.mmd import DriftMMD, DriftMMDOutput
     from dataeval.detectors.drift.torch import preprocess_drift
     from dataeval.detectors.drift.uncertainty import DriftUncertainty

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/detectors/drift/base.py

@@ -18,7 +18,7 @@ from typing import Any, Callable, Literal, TypeVar
 import numpy as np
 from numpy.typing import ArrayLike, NDArray
 
-from dataeval.interop import as_numpy, to_numpy
+from dataeval.interop import as_numpy
 from dataeval.output import OutputMetadata, set_metadata
 
 R = TypeVar("R")
@@ -196,7 +196,7 @@ class BaseDrift:
         if correction not in ["bonferroni", "fdr"]:
             raise ValueError("`correction` must be `bonferroni` or `fdr`.")
 
-        self._x_ref = to_numpy(x_ref)
+        self._x_ref = as_numpy(x_ref)
         self.x_ref_preprocessed: bool = x_ref_preprocessed
 
         # Other attributes

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/detectors/linters/clusterer.py

@@ -480,7 +480,7 @@ class Clusterer:
             samples = self.clusters[level][cluster_id].samples
             if len(samples) >= self._min_num_samples_per_cluster:
                 duplicates_std.append(self.clusters[level][cluster_id].dist_std)
-        diag_mask = np.ones_like(self._sqdmat, dtype=bool)
+        diag_mask = np.ones_like(self._sqdmat, dtype=np.bool_)
         np.fill_diagonal(diag_mask, 0)
         diag_mask = np.triu(diag_mask)
 

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/detectors/ood/__init__.py

@@ -4,7 +4,7 @@ Out-of-distribution (OOD)` detectors identify data that is different from the da
 
 from dataeval import _IS_TENSORFLOW_AVAILABLE
 
-if _IS_TENSORFLOW_AVAILABLE:  # pragma: no cover
+if _IS_TENSORFLOW_AVAILABLE:
     from dataeval.detectors.ood.ae import OOD_AE
     from dataeval.detectors.ood.aegmm import OOD_AEGMM
     from dataeval.detectors.ood.base import OODOutput, OODScoreOutput

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/detectors/ood/ae.py

@@ -10,18 +10,26 @@ from __future__ import annotations
 
 __all__ = ["OOD_AE"]
 
-from typing import Callable
+from typing import TYPE_CHECKING, Callable
 
 import numpy as np
-import tensorflow as tf
-import tf_keras as keras
 from numpy.typing import ArrayLike
 
 from dataeval.detectors.ood.base import OODBase, OODScoreOutput
 from dataeval.interop import as_numpy
-from dataeval.utils.tensorflow._internal.autoencoder import AE
+from dataeval.utils.lazy import lazyload
 from dataeval.utils.tensorflow._internal.utils import predict_batch
 
+if TYPE_CHECKING:
+    import tensorflow as tf
+    import tf_keras as keras
+
+    import dataeval.utils.tensorflow._internal.models as tf_models
+else:
+    tf = lazyload("tensorflow")
+    keras = lazyload("tf_keras")
+    tf_models = lazyload("dataeval.utils.tensorflow._internal.models")
+
 
 class OOD_AE(OODBase):
     """
@@ -33,7 +41,7 @@ class OOD_AE(OODBase):
        An :term:`autoencoder<Autoencoder>` model.
     """
 
-    def __init__(self, model: AE) -> None:
+    def __init__(self, model: tf_models.AE) -> None:
         super().__init__(model)
 
     def fit(
@@ -41,7 +49,7 @@ class OOD_AE(OODBase):
         x_ref: ArrayLike,
         threshold_perc: float = 100.0,
         loss_fn: Callable[..., tf.Tensor] | None = None,
-        optimizer: keras.optimizers.Optimizer = keras.optimizers.Adam,
+        optimizer: keras.optimizers.Optimizer | None = None,
         epochs: int = 20,
         batch_size: int = 64,
         verbose: bool = True,

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/detectors/ood/aegmm.py

@@ -10,19 +10,27 @@ from __future__ import annotations
 
 __all__ = ["OOD_AEGMM"]
 
-from typing import Callable
+from typing import TYPE_CHECKING, Callable
 
-import tensorflow as tf
-import tf_keras as keras
 from numpy.typing import ArrayLike
 
 from dataeval.detectors.ood.base import OODGMMBase, OODScoreOutput
 from dataeval.interop import to_numpy
-from dataeval.utils.tensorflow._internal.autoencoder import AEGMM
+from dataeval.utils.lazy import lazyload
 from dataeval.utils.tensorflow._internal.gmm import gmm_energy
 from dataeval.utils.tensorflow._internal.loss import LossGMM
 from dataeval.utils.tensorflow._internal.utils import predict_batch
 
+if TYPE_CHECKING:
+    import tensorflow as tf
+    import tf_keras as keras
+
+    import dataeval.utils.tensorflow._internal.models as tf_models
+else:
+    tf = lazyload("tensorflow")
+    keras = lazyload("tf_keras")
+    tf_models = lazyload("dataeval.utils.tensorflow._internal.models")
+
 
 class OOD_AEGMM(OODGMMBase):
     """
@@ -34,7 +42,7 @@ class OOD_AEGMM(OODGMMBase):
        An AEGMM model.
     """
 
-    def __init__(self, model: AEGMM) -> None:
+    def __init__(self, model: tf_models.AEGMM) -> None:
         super().__init__(model)
 
     def fit(
@@ -42,7 +50,7 @@ class OOD_AEGMM(OODGMMBase):
         x_ref: ArrayLike,
         threshold_perc: float = 100.0,
         loss_fn: Callable[..., tf.Tensor] | None = None,
-        optimizer: keras.optimizers.Optimizer = keras.optimizers.Adam,
+        optimizer: keras.optimizers.Optimizer | None = None,
         epochs: int = 20,
         batch_size: int = 64,
         verbose: bool = True,

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/detectors/ood/base.py

@@ -12,18 +12,24 @@ __all__ = ["OODOutput", "OODScoreOutput"]
 
 from abc import ABC, abstractmethod
 from dataclasses import dataclass
-from typing import Callable, Literal, cast
+from typing import TYPE_CHECKING, Callable, Literal, cast
 
 import numpy as np
-import tensorflow as tf
-import tf_keras as keras
 from numpy.typing import ArrayLike, NDArray
 
 from dataeval.interop import to_numpy
 from dataeval.output import OutputMetadata, set_metadata
+from dataeval.utils.lazy import lazyload
 from dataeval.utils.tensorflow._internal.gmm import GaussianMixtureModelParams, gmm_params
 from dataeval.utils.tensorflow._internal.trainer import trainer
 
+if TYPE_CHECKING:
+    import tensorflow as tf
+    import tf_keras as keras
+else:
+    tf = lazyload("tensorflow")
+    keras = lazyload("tf_keras")
+
 
 @dataclass(frozen=True)
 class OODOutput(OutputMetadata):

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/detectors/ood/llr.py

@@ -11,25 +11,31 @@ from __future__ import annotations
 __all__ = ["OOD_LLR"]
 
 from functools import partial
-from typing import Callable
+from typing import TYPE_CHECKING, Callable
 
 import numpy as np
-import tensorflow as tf
-import tf_keras as keras
 from numpy.typing import ArrayLike, NDArray
-from tf_keras.layers import Input
-from tf_keras.models import Model
 
 from dataeval.detectors.ood.base import OODBase, OODScoreOutput
 from dataeval.interop import to_numpy
-from dataeval.utils.tensorflow._internal.pixelcnn import PixelCNN
+from dataeval.utils.lazy import lazyload
 from dataeval.utils.tensorflow._internal.trainer import trainer
 from dataeval.utils.tensorflow._internal.utils import predict_batch
 
+if TYPE_CHECKING:
+    import tensorflow as tf
+    import tf_keras as keras
+
+    import dataeval.utils.tensorflow._internal.models as tf_models
+else:
+    tf = lazyload("tensorflow")
+    keras = lazyload("tf_keras")
+    tf_models = lazyload("dataeval.utils.tensorflow._internal.models")
+
 
 def _build_model(
-    dist: PixelCNN, input_shape: tuple | None = None, filepath: str | None = None
-) -> tuple[keras.Model, PixelCNN]:
+    dist: tf_models.PixelCNN, input_shape: tuple | None = None, filepath: str | None = None
+) -> tuple[keras.Model, tf_models.PixelCNN]:
     """
     Create keras.Model from TF distribution.
 
@@ -46,9 +52,9 @@ def _build_model(
     -------
     TensorFlow model.
     """
-    x_in = Input(shape=input_shape)
+    x_in = keras.layers.Input(shape=input_shape)
     log_prob = dist.log_prob(x_in)
-    model = Model(inputs=x_in, outputs=log_prob)
+    model = keras.models.Model(inputs=x_in, outputs=log_prob)
     model.add_loss(-tf.reduce_mean(log_prob))
     if isinstance(filepath, str):
         model.load_weights(filepath)
@@ -109,13 +115,13 @@ class OOD_LLR(OODBase):
 
     def __init__(
         self,
-        model: PixelCNN,
-        model_background: PixelCNN | None = None,
+        model: tf_models.PixelCNN,
+        model_background: tf_models.PixelCNN | None = None,
         log_prob: Callable | None = None,
         sequential: bool = False,
     ) -> None:
-        self.dist_s: PixelCNN = model
-        self.dist_b: PixelCNN = (
+        self.dist_s: tf_models.PixelCNN = model
+        self.dist_b: tf_models.PixelCNN = (
             model.copy()
             if hasattr(model, "copy")
             else keras.models.clone_model(model)
@@ -135,7 +141,7 @@ class OOD_LLR(OODBase):
         x_ref: ArrayLike,
         threshold_perc: float = 100.0,
         loss_fn: Callable | None = None,
-        optimizer: keras.optimizers.Optimizer = keras.optimizers.Adam,
+        optimizer: keras.optimizers.Optimizer | None = None,
         epochs: int = 20,
         batch_size: int = 64,
         verbose: bool = True,
@@ -176,7 +182,7 @@ class OOD_LLR(OODBase):
         """
         x_ref = to_numpy(x_ref)
         input_shape = x_ref.shape[1:]
-        optimizer = optimizer() if isinstance(optimizer, type) else optimizer
+        optimizer = keras.optimizers.Adam() if optimizer is None else optimizer
         # Separate into two separate optimizers, one for semantic model and one for background model
         optimizer_s = optimizer
         optimizer_b = optimizer.__class__.from_config(optimizer.get_config())

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/detectors/ood/vae.py

@@ -10,19 +10,27 @@ from __future__ import annotations
 
 __all__ = ["OOD_VAE"]
 
-from typing import Callable
+from typing import TYPE_CHECKING, Callable
 
 import numpy as np
-import tensorflow as tf
-import tf_keras as keras
 from numpy.typing import ArrayLike
 
 from dataeval.detectors.ood.base import OODBase, OODScoreOutput
 from dataeval.interop import to_numpy
-from dataeval.utils.tensorflow._internal.autoencoder import VAE
+from dataeval.utils.lazy import lazyload
 from dataeval.utils.tensorflow._internal.loss import Elbo
 from dataeval.utils.tensorflow._internal.utils import predict_batch
 
+if TYPE_CHECKING:
+    import tensorflow as tf
+    import tf_keras as keras
+
+    import dataeval.utils.tensorflow._internal.models as tf_models
+else:
+    tf = lazyload("tensorflow")
+    keras = lazyload("tf_keras")
+    tf_models = lazyload("dataeval.utils.tensorflow._internal.models")
+
 
 class OOD_VAE(OODBase):
     """
@@ -51,7 +59,7 @@ class OOD_VAE(OODBase):
     >>> result = metric.predict(dataset, ood_type="feature")
     """
 
-    def __init__(self, model: VAE, samples: int = 10) -> None:
+    def __init__(self, model: tf_models.VAE, samples: int = 10) -> None:
         super().__init__(model)
         self.samples = samples
 
@@ -60,7 +68,7 @@ class OOD_VAE(OODBase):
         x_ref: ArrayLike,
         threshold_perc: float = 100.0,
         loss_fn: Callable[..., tf.Tensor] = Elbo(0.05),
-        optimizer: keras.optimizers.Optimizer = keras.optimizers.Adam,
+        optimizer: keras.optimizers.Optimizer | None = None,
         epochs: int = 20,
         batch_size: int = 64,
         verbose: bool = True,

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/detectors/ood/vaegmm.py

@@ -10,20 +10,28 @@ from __future__ import annotations
 
 __all__ = ["OOD_VAEGMM"]
 
-from typing import Callable
+from typing import TYPE_CHECKING, Callable
 
 import numpy as np
-import tensorflow as tf
-import tf_keras as keras
 from numpy.typing import ArrayLike
 
 from dataeval.detectors.ood.base import OODGMMBase, OODScoreOutput
 from dataeval.interop import to_numpy
-from dataeval.utils.tensorflow._internal.autoencoder import VAEGMM
+from dataeval.utils.lazy import lazyload
 from dataeval.utils.tensorflow._internal.gmm import gmm_energy
 from dataeval.utils.tensorflow._internal.loss import Elbo, LossGMM
 from dataeval.utils.tensorflow._internal.utils import predict_batch
 
+if TYPE_CHECKING:
+    import tensorflow as tf
+    import tf_keras as keras
+
+    import dataeval.utils.tensorflow._internal.models as tf_models
+else:
+    tf = lazyload("tensorflow")
+    keras = lazyload("tf_keras")
+    tf_models = lazyload("dataeval.utils.tensorflow._internal.models")
+
 
 class OOD_VAEGMM(OODGMMBase):
     """
@@ -37,7 +45,7 @@ class OOD_VAEGMM(OODGMMBase):
         Number of samples sampled to evaluate each instance.
     """
 
-    def __init__(self, model: VAEGMM, samples: int = 10) -> None:
+    def __init__(self, model: tf_models.VAEGMM, samples: int = 10) -> None:
         super().__init__(model)
         self.samples = samples
 
@@ -46,7 +54,7 @@ class OOD_VAEGMM(OODGMMBase):
         x_ref: ArrayLike,
         threshold_perc: float = 100.0,
         loss_fn: Callable[..., tf.Tensor] = LossGMM(elbo=Elbo(0.05)),
-        optimizer: keras.optimizers.Optimizer = keras.optimizers.Adam,
+        optimizer: keras.optimizers.Optimizer | None = None,
         epochs: int = 20,
         batch_size: int = 64,
         verbose: bool = True,

{dataeval-0.72.2 → dataeval-0.73.1}/src/dataeval/interop.py

@@ -37,13 +37,15 @@ def to_numpy(array: ArrayLike | None, copy: bool = True) -> NDArray[Any]:
     if isinstance(array, np.ndarray):
         return array.copy() if copy else array
 
-    tf = _try_import("tensorflow")
-    if tf and tf.is_tensor(array):
-        return array.numpy().copy() if copy else array.numpy()  # type: ignore
-
-    torch = _try_import("torch")
-    if torch and isinstance(array, torch.Tensor):
-        return array.detach().cpu().numpy().copy() if copy else array.detach().cpu().numpy()  # type: ignore
+    if array.__class__.__module__.startswith("tensorflow"):
+        tf = _try_import("tensorflow")
+        if tf and tf.is_tensor(array):
+            return array.numpy().copy() if copy else array.numpy()  # type: ignore
+
+    if array.__class__.__module__.startswith("torch"):
+        torch = _try_import("torch")
+        if torch and isinstance(array, torch.Tensor):
+            return array.detach().cpu().numpy().copy() if copy else array.detach().cpu().numpy()  # type: ignore
 
     return np.array(array, copy=copy)