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
MindSpore
book
提交
2a468ff7
B
book
项目概览
MindSpore
/
book
通知
3
Star
1
Fork
1
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
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
B
book
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
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
提交
Issue看板
前往新版Gitcode,体验更适合开发者的 AI 搜索 >>
提交
2a468ff7
编写于
9月 04, 2020
作者:
W
wanyiming
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Mod_SoftmaxCrossEntropyWithLogits
上级
bacd6196
变更
4
隐藏空白更改
内联
并排
Showing
4 changed file
with
4 addition
and
4 deletion
+4
-4
chapter04/alexnet/main.py
chapter04/alexnet/main.py
+1
-1
chapter05/resnet/resnet_cifar.py
chapter05/resnet/resnet_cifar.py
+1
-1
chapter06/lstm/eval.py
chapter06/lstm/eval.py
+1
-1
chapter06/lstm/train.py
chapter06/lstm/train.py
+1
-1
未找到文件。
chapter04/alexnet/main.py
浏览文件 @
2a468ff7
...
...
@@ -83,7 +83,7 @@ if __name__ == "__main__":
context
.
set_context
(
mode
=
context
.
GRAPH_MODE
,
device_target
=
args
.
device_target
)
network
=
AlexNet
(
cfg
.
num_classes
)
loss
=
nn
.
SoftmaxCrossEntropyWithLogits
(
is_grad
=
False
,
sparse
=
True
,
reduction
=
"mean"
)
loss
=
nn
.
SoftmaxCrossEntropyWithLogits
(
sparse
=
True
,
reduction
=
"mean"
)
repeat_size
=
1
# when batch_size=32, steps is 1562
lr
=
Tensor
(
get_lr
(
0
,
cfg
.
learning_rate
,
cfg
.
epoch_size
,
1562
))
...
...
chapter05/resnet/resnet_cifar.py
浏览文件 @
2a468ff7
...
...
@@ -119,7 +119,7 @@ if __name__ == '__main__':
epoch_size
=
args_opt
.
epoch_size
net
=
resnet50
(
args_opt
.
num_classes
)
ls
=
SoftmaxCrossEntropyWithLogits
(
sparse
=
True
,
is_grad
=
False
,
reduction
=
"mean"
)
ls
=
SoftmaxCrossEntropyWithLogits
(
sparse
=
True
,
reduction
=
"mean"
)
opt
=
Momentum
(
filter
(
lambda
x
:
x
.
requires_grad
,
net
.
get_parameters
()),
0.01
,
0.9
)
model
=
Model
(
net
,
loss_fn
=
ls
,
optimizer
=
opt
,
metrics
=
{
'acc'
})
...
...
chapter06/lstm/eval.py
浏览文件 @
2a468ff7
...
...
@@ -64,7 +64,7 @@ if __name__ == '__main__':
weight
=
Tensor
(
embedding_table
),
batch_size
=
cfg
.
batch_size
)
loss
=
nn
.
SoftmaxCrossEntropyWithLogits
(
is_grad
=
False
,
sparse
=
True
)
loss
=
nn
.
SoftmaxCrossEntropyWithLogits
(
sparse
=
True
,
reduction
=
'mean'
)
opt
=
nn
.
Momentum
(
network
.
trainable_params
(),
cfg
.
learning_rate
,
cfg
.
momentum
)
loss_cb
=
LossMonitor
()
...
...
chapter06/lstm/train.py
浏览文件 @
2a468ff7
...
...
@@ -70,7 +70,7 @@ if __name__ == '__main__':
if
args
.
pre_trained
:
load_param_into_net
(
network
,
load_checkpoint
(
args
.
pre_trained
))
loss
=
nn
.
SoftmaxCrossEntropyWithLogits
(
is_grad
=
False
,
sparse
=
True
)
loss
=
nn
.
SoftmaxCrossEntropyWithLogits
(
sparse
=
True
,
reduction
=
'mean'
)
opt
=
nn
.
Momentum
(
network
.
trainable_params
(),
cfg
.
learning_rate
,
cfg
.
momentum
)
loss_cb
=
LossMonitor
()
...
...
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