def init_unpickled(self):
super(FullBatchLoader, self).init_unpickled()
self._original_data_ = memory.Array()
self._original_labels_ = []
self._mapped_original_labels_ = memory.Array()
self.sources_["fullbatch_loader"] = {}
self._global_size = None
self._krn_const = numpy.zeros(2, dtype=Loader.LABEL_DTYPE)
def __init__(self, workflow, **kwargs):
super(GDRProp, self).__init__(workflow, **kwargs)
self.initial_learning_rate = 0.01
self.min_learning_rate = 10**-6
self.max_learning_rate = 1
self.increase = 1.05
self.decrease = 0.80
self.weight_lrs = memory.Array()
self.bias_lrs = memory.Array()
def __init__(self, workflow, **kwargs):
kwargs["view_group"] = "LOADER"
self.last_minibatch = Bool()
super(Loader, self).__init__(workflow, **kwargs)
self.verify_interface(ILoader)
self.prng = kwargs.get("prng", random_generator.get())
if not self.testing:
self.shuffle_limit = kwargs.get("shuffle_limit",
numpy.iinfo(numpy.uint32).max)
else:
self.shuffle_limit = 0
self._max_minibatch_size = kwargs.get("minibatch_size", 100)
if self._max_minibatch_size < 1:
raise ValueError("minibatch_size must be greater than zero")
self._class_lengths = [0] * len(CLASS_NAME)
self._class_end_offsets = [0] * len(CLASS_NAME)
self._has_labels = False
self.epoch_ended = Bool()
self.epoch_number = 0
self.train_ended = Bool()
self.test_ended = Bool()
self.samples_served = 0
self._global_offset = 0
self.minibatch_class = 0
self.minibatch_data = memory.Array(shallow_pickle=True)
self.minibatch_indices = memory.Array(shallow_pickle=True)
self.minibatch_labels = memory.Array(shallow_pickle=True)
self._raw_minibatch_labels = []
self._labels_mapping = {}
self._reversed_labels_mapping = []
self._samples_mapping = defaultdict(set)
self.failed_minibatches = []
self._total_failed = 0
self._on_initialized = nothing
self._unique_labels_count = 1 # "None" label
self.shuffled_indices = memory.Array()
self.normalization_type = kwargs.get("normalization_type", "none")
self.normalization_parameters = kwargs.get("normalization_parameters",
{})
self.train_ratio = kwargs.get("train_ratio", self.train_ratio)
def __init__(self, workflow, **kwargs):
super(LoaderMSEMixin, self).__init__(workflow, **kwargs)
self.class_targets = memory.Array()
self._minibatch_targets = memory.Array(shallow_pickle=True)
self._targets_shape = kwargs.get("targets_shape", tuple())
self.target_normalization_type = kwargs.get(
"target_normalization_type",
kwargs.get("normalization_type", "none"))
if "target_normalization_type" in kwargs and \
self.target_normalization_type != self.normalization_type and \
"target_normalization_parameters" not in kwargs:
raise ValueError("You set target_normalization_type in %s which "
"is different from normalization_type but did not"
" set target_normalization_parameters." %
self.target_normalization_type)
self.target_normalization_parameters = kwargs.get(
"target_normalization_parameters",
kwargs.get("normalization_parameters", {}))
def init_unpickled(self):
super(FullBatchLoaderMSEMixin, self).init_unpickled()
self._original_targets_ = memory.Array()
self._kernel_target_ = None
self._global_size_target = None
