!11795 fix spell error and add Randperm summary

From: @yanzhenxiang2020
Reviewed-by: @wuxuejian,@liangchenghui
Signed-off-by: @wuxuejian
This commit is contained in:
mindspore-ci-bot 2021-01-30 15:18:31 +08:00 committed by Gitee
commit 988cef426b
2 changed files with 10 additions and 3 deletions

View File

@ -65,7 +65,8 @@ class ScalarCast(PrimitiveWithInfer):
class Randperm(PrimitiveWithInfer): class Randperm(PrimitiveWithInfer):
""" """
Generates random samples from 0 to n-1. Generates n random samples from 0 to n-1 without repeating. If `max_length` > n,
the last `max_length-n` elements will be filled with `pad`.
Args: Args:
max_length (int): Number of items expected to get and the number must be greater than 0. Default: 1. max_length (int): Number of items expected to get and the number must be greater than 0. Default: 1.
@ -119,6 +120,12 @@ class NoRepeatNGram(PrimitiveWithInfer):
""" """
Update log_probs with repeat n-grams. Update log_probs with repeat n-grams.
During beam search, if consecutive `ngram_size` words exist in the generated word sequence,
the consecutive `ngram_size` words will be avoided during subsequent prediction.
For example, when `ngram_size` is 3, the generated word sequence is [1, 2, 3, 2, 3],
the next predicted word will not be 2 and the value of `log_probs` will be replaced with -FLOAT_MAX.
Because 3 consecutive words [2, 3, 2] do not appear twice in the word sequence.
Args: Args:
ngram_size (int): Size of n-grams, must be greater than 0. Default: 1. ngram_size (int): Size of n-grams, must be greater than 0. Default: 1.
@ -211,7 +218,7 @@ class LambApplyOptimizerAssign(PrimitiveWithInfer):
- **epsilon** (Tensor) - Term added to the denominator, has the same type as `beta1`. - **epsilon** (Tensor) - Term added to the denominator, has the same type as `beta1`.
- **steps** (Tensor) - :math:`t` in the updating formula, global step, has the same type as `beta1`. - **steps** (Tensor) - :math:`t` in the updating formula, global step, has the same type as `beta1`.
- **lr** (Tensor) - :math:`l` in the updating formula, learning rate, has the same type as `beta1`. - **lr** (Tensor) - :math:`l` in the updating formula, learning rate, has the same type as `beta1`.
- **decay_flag** (Tensor) -Specify whether param upadte with weight decay, has the same type as `beta1`. - **decay_flag** (Tensor) -Specify whether param update with weight decay, has the same type as `beta1`.
- **weight_decay** (Tensor) - :math:`\lambda` in the updating formula, has the same type as `beta1`. - **weight_decay** (Tensor) - :math:`\lambda` in the updating formula, has the same type as `beta1`.
Outputs: Outputs:

View File

@ -95,6 +95,6 @@ def set_config(args):
"Ascend": config_ascend}) "Ascend": config_ascend})
if args.platform not in config.keys(): if args.platform not in config.keys():
raise ValueError("Unsupport platform.") raise ValueError("Unsupported platform.")
return config[args.platform] return config[args.platform]