Skip to content
This repository was archived by the owner on Jan 24, 2024. It is now read-only.

Conversation

@0YuanZhang0
Copy link
Contributor

1、升级sequence_tagging中rnn模型
2、更新Dataloader;
3、新增模型;

test_generator = create_lexnet_data_generator(
args, reader=dataset, file_name=test_path, place=place, mode="test")
feed_list = None if args.dynamic else [
x.forward() for x in inputs + labels
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No need to set feed_list anymore, maybe delete this later.

param_attr=fluid.ParamAttr(
initializer=fluid.initializer.UniformInitializer(
low=-init_bound, high=init_bound),
regularizer=fluid.regularizer.L2DecayRegularizer(
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we make initializer and regularizer optional, maybe we can expose param_attr=None, bias_attr=None as other layers

self.reset()

def add_metric_op(self, *args):
def add_metric_op(self, *args):
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we use fluid.layers.chunk_eval here, is there any specific purpose to wrap a Chunk_eval class

@guoshengCS guoshengCS merged commit 15aef48 into PaddlePaddle:master Apr 26, 2020
jinyuKING pushed a commit to jinyuKING/hapi that referenced this pull request Apr 27, 2020
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants