def __init__(self,
num_sampled,
num_classes,
num_true=1,
sampled_values=None,
remove_accidental_hits=True,
seed=0,
reduction='none'):
super(SampledSoftmaxLoss, self).__init__()
self.num_sampled = num_sampled
self.num_classes = num_classes
self.num_true = num_true
self.sampled_values = sampled_values
self.remove_accidental_hits = remove_accidental_hits
self.seed = seed
self.sampler = P.UniformCandidateSampler(num_true, num_sampled, True,
num_classes, seed,
remove_accidental_hits)
self.cast = P.Cast()
self.reshape = P.Reshape()
self.shape = P.Shape()
self.exp = P.Exp()
self.log = P.Log()
self.slice_op = P.Slice()
self.matmul = P.MatMul(False, True)
self.gather_v2 = P.GatherV2()
self.reduce_max_true = P.ReduceMax(True)
self.reduce_sum = P.ReduceSum()
self.reduce_sum_true = P.ReduceSum(True)
self.concat_dim0 = P.Concat(0)
self.concat_dim1 = P.Concat(1)
self.ones_like = P.OnesLike()
self.zeros_like = P.ZerosLike()
self.mul = P.Mul()
self.expand_dims = P.ExpandDims()
def __init__(self,
num_sampled,
num_classes,
num_true=1,
sampled_values=None,
remove_accidental_hits=True,
seed=0,
reduction='none'):
super(SampledSoftmaxLoss, self).__init__(reduction)
if num_true < 1:
raise ValueError(f"num_true {num_true} is less than 1.")
if seed < 0:
raise ValueError(f"seed {seed} is less than 0.")
if num_sampled > num_classes:
raise ValueError(
f"num_sampled {num_sampled} is great than num_classes {num_classes}."
)
if num_true > num_classes:
raise ValueError(
f"num_true {num_true} is great than num_classes {num_classes}."
)
if sampled_values is not None:
if not isinstance(sampled_values, (list, tuple)):
raise TypeError(
f"sampled_values {sampled_values} is not a list or tuple.")
if len(sampled_values) != 3:
raise ValueError(
f"sampled_values size {len(sampled_values)} is not 3.")
self.num_sampled = num_sampled
self.num_classes = num_classes
self.num_true = num_true
self.sampled_values = sampled_values
self.remove_accidental_hits = remove_accidental_hits
self.seed = seed
self.sampler = P.UniformCandidateSampler(num_true, num_sampled, True,
num_classes, seed,
remove_accidental_hits)
self.cast = P.Cast()
self.reshape = P.Reshape()
self.shape = P.Shape()
self.exp = P.Exp()
self.log = P.Log()
self.slice_op = P.Slice()
self.matmul = P.MatMul(False, True)
self.gather_v2 = P.Gather()
self.reduce_max_true = P.ReduceMax(True)
self.reduce_sum = P.ReduceSum()
self.reduce_sum_true = P.ReduceSum(True)
self.concat_dim0 = P.Concat(0)
self.concat_dim1 = P.Concat(1)
self.ones_like = P.OnesLike()
self.zeros_like = P.ZerosLike()
self.mul = P.Mul()
self.expand_dims = P.ExpandDims()
self.dtype = P.DType()
def __init__(self, num_true, num_sampled, unique, range_max, seed,
remove_accidental_hits):
super(UniformCandidateSamplerHitNet, self).__init__()
self.sampler = P.UniformCandidateSampler(
num_true,
num_sampled,
unique,
range_max,
seed=seed,
remove_accidental_hits=remove_accidental_hits)
def __init__(self,
mul_weight,
num_true,
num_sampled,
unique,
range_max,
seed,
remove_accidential,
strategy1=None):
super(Net2, self).__init__()
self.sampler = P.UniformCandidateSampler(num_true, num_sampled, unique,
range_max, seed,
remove_accidential)
self.cast = P.Cast()
self.weight = Parameter(mul_weight, "w1")
self.mul = P.Mul()
if strategy1:
self.sampler.shard(strategy1)
def __init__(self,
embedding_weight,
num_true,
num_sampled,
unique,
range_max,
seed,
remove_accidential,
strategy1=None):
super(Net, self).__init__()
self.sampler = P.UniformCandidateSampler(num_true, num_sampled, unique,
range_max, seed,
remove_accidential)
if strategy1:
self.sampler.shard(strategy1)
self.embedding_table = Parameter(embedding_weight, "embedding_weight")
self.gatherv2 = P.Gather()
self.reduce_sum = P.ReduceSum()
self.reduce_sum2 = P.ReduceSum()
self.reduce_sum3 = P.ReduceSum()
def __init__(self, num_true, num_sampled, unique, range_max):
super(UniformCandidateSamplerNet, self).__init__()
self.sampler = P.UniformCandidateSampler(num_true, num_sampled, unique,
range_max)
