07/Label semantic roles#5798
Merged
jacquesqiao merged 15 commits intoPaddlePaddle:developfrom Nov 22, 2017
Merged
Conversation
… label_semantic_roles
… label_semantic_roles
lcy-seso
reviewed
Nov 21, 2017
Contributor
lcy-seso
left a comment
There was a problem hiding this comment.
从网络结构中,除了一些(我)难以理解的超参数设置,我也看不出来为什么CRF计算会溢出。是否可能先简化LSTM的层数,固定初始化,从数值计算一点点来检查。
CRF 输入和转移矩阵计算EXP之后的数值是不是有可能溢出?
| size=[mark_dict_len, mark_dim], | ||
| data_type='float32', | ||
| is_sparse=IS_SPARSE, | ||
| param_attr=std_0) |
Contributor
There was a problem hiding this comment.
这个 embedding 参数是需要学习的,对吗,这里的 std_0 会将参数初始化成全零吗?但book里面似乎也是这样设置,这个好奇怪。
Contributor
There was a problem hiding this comment.
book里的embedding层提供了初始化模型,不用学习~
Member
Author
There was a problem hiding this comment.
嗯,这个正在加,load之前训练好的embedding
| size=hidden_dim, | ||
| candidate_activation='relu', | ||
| gate_activation='sigmoid', | ||
| cell_activation='sigmoid', |
Contributor
| mark_dim = 5 | ||
| hidden_dim = 512 | ||
| depth = 8 | ||
| default_std = 1 / math.sqrt(hidden_dim) / 3.0 |
Member
Author
There was a problem hiding this comment.
先去掉这些奇怪的初始化方式了,默认使用XavierInitializer
| layers.fc(input=input_tmp[1], | ||
| size=label_dict_len, | ||
| bias_attr=std_default, | ||
| param_attr=lstm_para_attr) |
Contributor
There was a problem hiding this comment.
这个参数会被初始化成全零吗,只剩下 bias?看着好奇怪/危险。
| name='label', shape=[1], data_type='int32', main_program=program) | ||
| hidden = layers.fc(input=images, | ||
| size=128, | ||
| act='relu', |
Superjomn
reviewed
Nov 22, 2017
| candidate_activation='relu', | ||
| gate_activation='sigmoid', | ||
| cell_activation='sigmoid', | ||
| is_reverse=((i % 2) == 1), |
Contributor
There was a problem hiding this comment.
change this argument to
is_reversed
or
reversed
better?
@qingqing01
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.

project: #5813
fix: #5691
Tasks