reflectorch 1.3.0__py3-none-any.whl → 1.5.0__py3-none-any.whl

reflectorch/data_generation/priors/__init__.py

@@ -1,60 +1,60 @@
-from reflectorch.data_generation.priors.params import Params
-from reflectorch.data_generation.priors.base import PriorSampler
-from reflectorch.data_generation.priors.no_constraints import BasicPriorSampler
-from reflectorch.data_generation.priors.independent_priors import (
-    SingleParamPrior,
-    SimplePriorSampler,
-    UniformParamPrior,
-    GaussianParamPrior,
-    TruncatedGaussianParamPrior
-)
-
-from reflectorch.data_generation.priors.subprior_sampler import (
-    UniformSubPriorParams,
-    UniformSubPriorSampler,
-    NarrowSldUniformSubPriorSampler,
-)
-from reflectorch.data_generation.priors.exp_subprior_sampler import ExpUniformSubPriorSampler
-from reflectorch.data_generation.priors.multilayer_structures import (
-    SimpleMultilayerSampler,
-    MultilayerStructureParams,
-)
-from reflectorch.data_generation.priors.parametric_models import (
-    ParametricModel,
-    MULTILAYER_MODELS,
-)
-from reflectorch.data_generation.priors.parametric_subpriors import (
-    SubpriorParametricSampler,
-    BasicParams,
-)
-from reflectorch.data_generation.priors.sampler_strategies import (
-    SamplerStrategy,
-    BasicSamplerStrategy,
-    ConstrainedRoughnessSamplerStrategy,
-    ConstrainedRoughnessAndImgSldSamplerStrategy,
-)
-
-__all__ = [
-    "SingleParamPrior",
-    "SimplePriorSampler",
-    "UniformParamPrior",
-    "GaussianParamPrior",
-    "TruncatedGaussianParamPrior",
-    "Params",
-    "PriorSampler",
-    "BasicPriorSampler",
-    "UniformSubPriorParams",
-    "UniformSubPriorSampler",
-    "NarrowSldUniformSubPriorSampler",
-    "ExpUniformSubPriorSampler",
-    "SimpleMultilayerSampler",
-    "MultilayerStructureParams",
-    "SubpriorParametricSampler",
-    "BasicParams",
-    "ParametricModel",
-    "MULTILAYER_MODELS",
-    "SamplerStrategy",
-    "BasicSamplerStrategy",
-    "ConstrainedRoughnessSamplerStrategy",
-    "ConstrainedRoughnessAndImgSldSamplerStrategy",
-]
+from reflectorch.data_generation.priors.params import Params
+from reflectorch.data_generation.priors.base import PriorSampler
+from reflectorch.data_generation.priors.no_constraints import BasicPriorSampler
+from reflectorch.data_generation.priors.independent_priors import (
+    SingleParamPrior,
+    SimplePriorSampler,
+    UniformParamPrior,
+    GaussianParamPrior,
+    TruncatedGaussianParamPrior
+)
+
+from reflectorch.data_generation.priors.subprior_sampler import (
+    UniformSubPriorParams,
+    UniformSubPriorSampler,
+    NarrowSldUniformSubPriorSampler,
+)
+from reflectorch.data_generation.priors.exp_subprior_sampler import ExpUniformSubPriorSampler
+from reflectorch.data_generation.priors.multilayer_structures import (
+    SimpleMultilayerSampler,
+    MultilayerStructureParams,
+)
+from reflectorch.data_generation.priors.parametric_models import (
+    ParametricModel,
+    MULTILAYER_MODELS,
+)
+from reflectorch.data_generation.priors.parametric_subpriors import (
+    SubpriorParametricSampler,
+    BasicParams,
+)
+from reflectorch.data_generation.priors.sampler_strategies import (
+    SamplerStrategy,
+    BasicSamplerStrategy,
+    ConstrainedRoughnessSamplerStrategy,
+    ConstrainedRoughnessAndImgSldSamplerStrategy,
+)
+
+__all__ = [
+    "SingleParamPrior",
+    "SimplePriorSampler",
+    "UniformParamPrior",
+    "GaussianParamPrior",
+    "TruncatedGaussianParamPrior",
+    "Params",
+    "PriorSampler",
+    "BasicPriorSampler",
+    "UniformSubPriorParams",
+    "UniformSubPriorSampler",
+    "NarrowSldUniformSubPriorSampler",
+    "ExpUniformSubPriorSampler",
+    "SimpleMultilayerSampler",
+    "MultilayerStructureParams",
+    "SubpriorParametricSampler",
+    "BasicParams",
+    "ParametricModel",
+    "MULTILAYER_MODELS",
+    "SamplerStrategy",
+    "BasicSamplerStrategy",
+    "ConstrainedRoughnessSamplerStrategy",
+    "ConstrainedRoughnessAndImgSldSamplerStrategy",
+]

reflectorch/data_generation/priors/base.py

@@ -1,55 +1,55 @@
-from torch import Tensor
-
-from reflectorch.data_generation.priors.params import Params
-
-__all__ = [
-    "PriorSampler",
-]
-
-
-class PriorSampler(object):
-    """Base class for prior samplers"""
-    
-    PARAM_CLS = Params
-
-    @property
-    def param_dim(self) -> int:
-        """gets the number of parameters (i.e. the parameter dimensionality)"""
-        return self.PARAM_CLS.layers_num2size(self.max_num_layers)
-
-    @property
-    def max_num_layers(self) -> int:
-        """gets the number of layers"""
-        raise NotImplementedError
-
-    def sample(self, batch_size: int) -> Params:
-        """sample a batch of parameters"""
-        raise NotImplementedError
-
-    def scale_params(self, params: Params) -> Tensor:
-        """scale the parameters to a ML-friendly range"""
-        raise NotImplementedError
-
-    def restore_params(self, scaled_params: Tensor) -> Params:
-        """restore the parameters to their original range"""
-        raise NotImplementedError
-
-    def log_prob(self, params: Params) -> Tensor:
-        raise NotImplementedError
-
-    def get_indices_within_domain(self, params: Params) -> Tensor:
-        raise NotImplementedError
-
-    def get_indices_within_bounds(self, params: Params) -> Tensor:
-        raise NotImplementedError
-
-    def filter_params(self, params: Params) -> Params:
-        indices = self.get_indices_within_domain(params)
-        return params[indices]
-
-    def clamp_params(self, params: Params) -> Params:
-        raise NotImplementedError
-
-    def __repr__(self):
-        args = ', '.join(f'{k}={str(v)[:10]}' for k, v in vars(self).items())
-        return f'{self.__class__.__name__}({args})'
+from torch import Tensor
+
+from reflectorch.data_generation.priors.params import Params
+
+__all__ = [
+    "PriorSampler",
+]
+
+
+class PriorSampler(object):
+    """Base class for prior samplers"""
+    
+    PARAM_CLS = Params
+
+    @property
+    def param_dim(self) -> int:
+        """gets the number of parameters (i.e. the parameter dimensionality)"""
+        return self.PARAM_CLS.layers_num2size(self.max_num_layers)
+
+    @property
+    def max_num_layers(self) -> int:
+        """gets the number of layers"""
+        raise NotImplementedError
+
+    def sample(self, batch_size: int) -> Params:
+        """sample a batch of parameters"""
+        raise NotImplementedError
+
+    def scale_params(self, params: Params) -> Tensor:
+        """scale the parameters to a ML-friendly range"""
+        raise NotImplementedError
+
+    def restore_params(self, scaled_params: Tensor) -> Params:
+        """restore the parameters to their original range"""
+        raise NotImplementedError
+
+    def log_prob(self, params: Params) -> Tensor:
+        raise NotImplementedError
+
+    def get_indices_within_domain(self, params: Params) -> Tensor:
+        raise NotImplementedError
+
+    def get_indices_within_bounds(self, params: Params) -> Tensor:
+        raise NotImplementedError
+
+    def filter_params(self, params: Params) -> Params:
+        indices = self.get_indices_within_domain(params)
+        return params[indices]
+
+    def clamp_params(self, params: Params) -> Params:
+        raise NotImplementedError
+
+    def __repr__(self):
+        args = ', '.join(f'{k}={str(v)[:10]}' for k, v in vars(self).items())
+        return f'{self.__class__.__name__}({args})'