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
溜达小灰鼠
Paddle
提交
c8091ad8
P
Paddle
项目概览
溜达小灰鼠
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1
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
P
Paddle
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
1
Issue
1
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
体验新版 GitCode,发现更多精彩内容 >>
提交
c8091ad8
编写于
11月 09, 2016
作者:
L
liaogang
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Follow comments
上级
4dada9c7
变更
1
显示空白变更内容
内联
并排
Showing
1 changed file
with
123 addition
and
0 deletion
+123
-0
python/paddle/trainer_config_helpers/tests/configs/protostr/test_bilinear_interp.protostr
...pers/tests/configs/protostr/test_bilinear_interp.protostr
+123
-0
未找到文件。
python/paddle/trainer_config_helpers/tests/configs/protostr/test_bilinear_interp.protostr
0 → 100644
浏览文件 @
c8091ad8
type: "nn"
layers {
name: "data"
type: "data"
size: 2304
active_type: ""
}
layers {
name: "__conv_0__"
type: "exconv"
size: 36864
active_type: ""
inputs {
input_layer_name: "data"
input_parameter_name: "___conv_0__.w0"
conv_conf {
filter_size: 3
channels: 1
stride: 1
padding: 1
groups: 1
filter_channels: 1
output_x: 48
img_size: 48
caffe_mode: true
filter_size_y: 3
padding_y: 1
stride_y: 1
}
}
bias_parameter_name: "___conv_0__.wbias"
num_filters: 16
shared_biases: true
}
layers {
name: "__bilinear_interp_layer_0__"
type: "bilinear_interp"
size: 65536
active_type: ""
inputs {
input_layer_name: "__conv_0__"
bilinear_interp_conf {
out_size_x: 64
out_size_y: 64
num_channels: 16
}
}
}
layers {
name: "__pool_0__"
type: "pool"
size: 16384
active_type: ""
inputs {
input_layer_name: "__bilinear_interp_layer_0__"
pool_conf {
pool_type: "max-projection"
channels: 4
size_x: 2
stride: 2
output_x: 64
img_size: 128
padding: 0
size_y: 2
stride_y: 2
output_y: 64
img_size_y: 128
padding_y: 0
}
}
}
layers {
name: "__fc_layer_0__"
type: "fc"
size: 384
active_type: "tanh"
inputs {
input_layer_name: "__pool_0__"
input_parameter_name: "___fc_layer_0__.w0"
}
}
parameters {
name: "___conv_0__.w0"
size: 144
initial_mean: 0.0
initial_std: 0.471404522657
initial_strategy: 0
initial_smart: false
}
parameters {
name: "___conv_0__.wbias"
size: 16
initial_mean: 0.0
initial_std: 0.0
dims: 16
dims: 1
initial_strategy: 0
initial_smart: false
}
parameters {
name: "___fc_layer_0__.w0"
size: 6291456
initial_mean: 0.0
initial_std: 0.0078125
dims: 16384
dims: 384
initial_strategy: 0
initial_smart: true
}
input_layer_names: "data"
output_layer_names: "__fc_layer_0__"
sub_models {
name: "root"
layer_names: "data"
layer_names: "__conv_0__"
layer_names: "__bilinear_interp_layer_0__"
layer_names: "__pool_0__"
layer_names: "__fc_layer_0__"
input_layer_names: "data"
output_layer_names: "__fc_layer_0__"
is_recurrent_layer_group: false
}
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