def __init__(self,
probs=None,
seed=None,
dtype=mstype.int32,
name="Categorical"):
param = dict(locals())
param['param_dict'] = {'probs': probs}
valid_dtype = mstype.uint_type + mstype.int_type + mstype.float_type
Validator.check_type_name("dtype", dtype, valid_dtype,
type(self).__name__)
super(Categorical, self).__init__(seed, dtype, name, param)
self._probs = self._add_parameter(probs, 'probs')
if self.probs is not None:
check_rank(self.probs)
check_prob(self.probs)
check_sum_equal_one(probs)
# update is_scalar_batch and broadcast_shape
# drop one dimension
if self.probs.shape[:-1] == ():
self._is_scalar_batch = True
self._broadcast_shape = self._broadcast_shape[:-1]
self.argmax = P.ArgMaxWithValue(axis=-1)
self.broadcast = broadcast_to
self.cast = P.Cast()
self.clip_by_value = C.clip_by_value
self.concat = P.Concat(-1)
self.cumsum = P.CumSum()
self.dtypeop = P.DType()
self.exp = exp_generic
self.expand_dim = P.ExpandDims()
self.fill = P.Fill()
self.gather = P.GatherNd()
self.greater = P.Greater()
self.issubclass = P.IsSubClass()
self.less = P.Less()
self.log = log_generic
self.log_softmax = P.LogSoftmax()
self.logicor = P.LogicalOr()
self.logicand = P.LogicalAnd()
self.multinomial = P.Multinomial(seed=self.seed)
self.reshape = P.Reshape()
self.reduce_sum = P.ReduceSum(keep_dims=True)
self.select = P.Select()
self.shape = P.Shape()
self.softmax = P.Softmax()
self.squeeze = P.Squeeze()
self.squeeze_first_axis = P.Squeeze(0)
self.squeeze_last_axis = P.Squeeze(-1)
self.square = P.Square()
self.transpose = P.Transpose()
self.is_nan = P.IsNan()
self.index_type = mstype.int32
self.nan = np.nan
def __init__(self,
probs=None,
logits=None,
seed=None,
dtype=mstype.int32,
name="Categorical"):
param = dict(locals())
valid_dtype = mstype.int_type
check_type(dtype, valid_dtype, "Categorical")
super(Categorical, self).__init__(seed, dtype, name, param)
if (probs is None) == (logits is None):
raise_probs_logits_error()
self.reduce_sum = P.ReduceSum(keep_dims=True)
self.reduce_sum1 = P.ReduceSum(keep_dims=False)
self.log = P.Log()
self.exp = P.Exp()
self.shape = P.Shape()
self.reshape = P.Reshape()
self.div = P.RealDiv()
self.size = P.Size()
self.mutinomial = P.Multinomial(seed=self.seed)
self.cast = P.Cast()
self.expandim = P.ExpandDims()
self.gather = P.GatherNd()
self.concat = P.Concat(-1)
self.transpose = P.Transpose()
if probs is not None:
self._probs = cast_to_tensor(probs, mstype.float32)
input_sum = self.reduce_sum(self._probs, -1)
self._probs = self.div(self._probs, input_sum)
self._logits = probs_to_logits(self._probs)
self._param = self._probs
else:
self._logits = cast_to_tensor(logits, mstype.float32)
input_sum = self.reduce_sum(self.exp(self._logits), -1)
self._logits = self._logits - self.log(input_sum)
self._probs = logits_to_probs(self._logits)
self._param = self._logits
self._num_events = self.shape(self._param)[-1]
self._param2d = self.reshape(self._param, (-1, self._num_events))
self._batch_shape = self.shape(self._param)[:-1]
self._batch_shape_n = (1, ) * len(self._batch_shape)
def __init__(self,
probs=None,
logits=None,
seed=0,
dtype=mstype.int32,
name="Categorical"):
param = dict(locals())
super(Categorical, self).__init__(seed, dtype, name, param)
if (probs is None) == (logits is None):
raise ValueError(
"Either 'prob' or 'logits' must be specified, but not both.")
self.reduce_sum = P.ReduceSum(keep_dims=True)
self.log = P.Log()
self.exp = P.Exp()
self.shape = P.Shape()
self.reshape = P.Reshape()
self.div = P.RealDiv()
self.size = P.Size()
self.mutinomial = P.Multinomial(seed=seed)
self.cast = P.Cast()
self.expandim = P.ExpandDims()
self.gather = P.GatherNd()
self.concat = P.Concat(-1)
if probs is not None:
self._probs = cast_to_tensor(probs, mstype.float32)
input_sum = self.reduce_sum(self._probs, -1)
self._probs = self.div(self._probs, input_sum)
self._logits = probs_to_logits(self._probs)
self._param = self._probs
else:
self._logits = cast_to_tensor(logits, mstype.float32)
input_sum = self.reduce_sum(self.exp(self._logits), -1)
self._logits = self._logits - self.log(input_sum)
self._probs = logits_to_probs(self._logits)
self._param = self._logits
self._num_events = self.shape(self._param)[-1]
self._param2d = self.reshape(self._param, (-1, self._num_events))
self._batch_shape = self.shape(self._param2d)[0]
def __init__(self,
decoder:Model,
model_config=None,
generate_length:int=1,
tokenizer:Optional[GPT2Tokenizer]=None,
topk_num:int=0,
topp_prob:float=1.0,
temperature:float=1.0,
min_tokens_to_keep:int=1,
early_stop:bool=False,
demo_mode:bool=False,
return_ids:bool=False,
return_last_token_logits:bool=False,
append_eos:bool=False):
assert model_config is not None, 'Config is a must for sampling.'
self.model_config = model_config
self.topk_num = topk_num
self.topp_prob = topp_prob
self.temperature = temperature
self.min_tokens_to_keep = min_tokens_to_keep
self.decoder = decoder
self.tokenizer = tokenizer
self.reshape = P.Reshape()
self.cumsum = P.CumSum()
self.onehot = P.OneHot()
self.generate_length = generate_length
self.seq_length = model_config.seq_length
self.batch_size = model_config.batch_size
self.vocab_size = model_config.vocab_size
self.on_value = Tensor(1.0, mstype.float32)
self.off_value = Tensor(0.0, mstype.float32)
self.cast = P.Cast()
self.concat = P.Concat()
self.early_stop = early_stop
self.demo_mode = demo_mode
self.return_ids = return_ids
self.return_last_token_logits = return_last_token_logits
self.append_eos = append_eos
self.device_target = get_context("device_target")
#different choice of sample function for adjusting several device target types
if self.device_target == "GPU":
self.sample_function = P.Multinomial(seed=1)
elif self.device_target == "Ascend":
self.sample_function = P.RandomCategorical(mstype.int32)
else:
raise NotImplementedError("Device Target {} not supported.".format(self.device_target))
self.filter_distribution = TopKTopP_Filter(self.batch_size,
self.vocab_size,
k=self.topk_num,
p=self.topp_prob,
temperature=self.temperature,
min_tokens_to_keep=self.min_tokens_to_keep)
if self.tokenizer is not None:
self.eos_id = self.tokenizer.eos_token_id
else:
self.eos_id = model_config.vocab_size-1
if self.tokenizer is not None:
self.eos_text = self.tokenizer.eos_token
else:
self.eos_text = "<|endoftext|>"
if self.demo_mode is True:
assert self.batch_size == 1, 'Demo mode requires batchsize euqals to 1, but get batch_size={}'.format(
self.batch_size)