Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
Stevezhangz
BERT Pytorch
提交
e988f072
B
BERT Pytorch
项目概览
Stevezhangz
/
BERT Pytorch
通知
14
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
DevOps
流水线
流水线任务
计划
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
B
BERT Pytorch
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
DevOps
DevOps
流水线
流水线任务
计划
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
流水线任务
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
e988f072
编写于
4月 23, 2021
作者:
Stevezhangz
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Update train_demo.py
上级
e281f154
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
7 addition
and
12 deletion
+7
-12
train_demo.py
train_demo.py
+7
-12
未找到文件。
train_demo.py
浏览文件 @
e988f072
...
...
@@ -8,7 +8,7 @@ import torch.nn as nn
import
torch.optim
as
optim
from
Config_load
import
*
from
data_process
import
*
import
random
np
.
random
.
seed
(
random_seed
)
...
...
@@ -21,13 +21,8 @@ data=json2list.getdata()
# transform list to token
list2token
=
generate_vocab_normalway
(
data
,
map_dir
=
"words_info.json"
)
sentences
,
token_list
,
idx2word
,
word2idx
,
vocab_size
=
list2token
.
transform
()
batch
=
creat_batch
(
batch_size
,
max_pred
,
maxlen
,
vocab_size
,
word2idx
,
token_list
,
sentences
)
input_ids
,
segment_ids
,
masked_tokens
,
masked_pos
,
isNext
=
zip
(
*
batch
)
input_ids
,
segment_ids
,
masked_tokens
,
masked_pos
,
isNext
=
\
torch
.
LongTensor
(
input_ids
),
torch
.
LongTensor
(
segment_ids
),
torch
.
LongTensor
(
masked_tokens
),
\
torch
.
LongTensor
(
masked_pos
),
torch
.
LongTensor
(
isNext
)
loader
=
Data
.
DataLoader
(
Text_file
(
input_ids
,
segment_ids
,
masked_tokens
,
masked_pos
,
isNext
),
batch_size
,
True
)
batch
=
creat_batch
(
batch_size
,
max_pred
,
maxlen
,
word2idx
,
idx2word
,
token_list
,
0.15
)
loader
=
Data
.
DataLoader
(
Text_file
(
batch
),
batch_size
,
True
)
model
=
Bert
(
n_layers
=
n_layers
,
vocab_size
=
vocab_size
,
...
...
@@ -39,14 +34,14 @@ model=Bert(n_layers=n_layers,
dv
=
d_v
,
n_head
=
n_heads
,
n_class
=
2
,
)
drop
=
drop
)
if
use_gpu
:
with
torch
.
cuda
.
device
(
device
)
as
device
:
model
.
to
(
device
)
criterion
=
nn
.
CrossEntropyLoss
()
optimizer
=
optim
.
Adadelta
(
model
.
parameters
(),
lr
=
lr
)
model
.
Train
(
epoches
=
epoches
,
model
.
Train
_for_mask_guess
(
epoches
=
epoches
,
train_data_loader
=
loader
,
optimizer
=
optimizer
,
criterion
=
criterion
,
...
...
@@ -59,7 +54,7 @@ if use_gpu:
else
:
criterion
=
nn
.
CrossEntropyLoss
()
optimizer
=
optim
.
Adadelta
(
model
.
parameters
(),
lr
=
lr
)
model
.
Train
(
epoches
=
epoches
,
model
.
Train
_for_mask_guess
(
epoches
=
epoches
,
train_data_loader
=
loader
,
optimizer
=
optimizer
,
criterion
=
criterion
,
...
...
@@ -68,4 +63,4 @@ else:
load_dir
=
"checkpoint/checkpoint_199.pth"
,
use_gpu
=
use_gpu
,
device
=
device
)
\ No newline at end of file
)
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录