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
曾经的那一瞬间
Models
提交
48b14968
M
Models
项目概览
曾经的那一瞬间
/
Models
大约 1 年 前同步成功
通知
1
Star
0
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
M
Models
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
48b14968
编写于
2月 25, 2021
作者:
A
A. Unique TensorFlower
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Internal change
PiperOrigin-RevId: 359538508
上级
73ce096c
变更
12
隐藏空白更改
内联
并排
Showing
12 changed file
with
26 addition
and
15 deletion
+26
-15
official/vision/beta/MODEL_GARDEN.md
official/vision/beta/MODEL_GARDEN.md
+15
-15
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs101_i160.yaml
...ments/image_classification/imagenet_resnetrs101_i160.yaml
+1
-0
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs101_i192.yaml
...ments/image_classification/imagenet_resnetrs101_i192.yaml
+1
-0
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs152_i192.yaml
...ments/image_classification/imagenet_resnetrs152_i192.yaml
+1
-0
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs152_i224.yaml
...ments/image_classification/imagenet_resnetrs152_i224.yaml
+1
-0
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs152_i256.yaml
...ments/image_classification/imagenet_resnetrs152_i256.yaml
+1
-0
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs200_i256.yaml
...ments/image_classification/imagenet_resnetrs200_i256.yaml
+1
-0
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs270_i256.yaml
...ments/image_classification/imagenet_resnetrs270_i256.yaml
+1
-0
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs350_i256.yaml
...ments/image_classification/imagenet_resnetrs350_i256.yaml
+1
-0
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs350_i320.yaml
...ments/image_classification/imagenet_resnetrs350_i320.yaml
+1
-0
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs420_i320.yaml
...ments/image_classification/imagenet_resnetrs420_i320.yaml
+1
-0
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs50_i160.yaml
...iments/image_classification/imagenet_resnetrs50_i160.yaml
+1
-0
未找到文件。
official/vision/beta/MODEL_GARDEN.md
浏览文件 @
48b14968
...
...
@@ -13,10 +13,10 @@ TF Vision model garden provides a large collection of baselines and checkpoints
| model | resolution | epochs | Top-1 | Top-5 | download |
| ------------ |:-------------:|--------:|--------:|---------:|---------:|
| ResNet-50 | 224x224 | 90 | 76.1 | 92.9 |
config
|
| ResNet-50 | 224x224 | 200 | 77.1 | 93.5 |
config
|
| ResNet-101 | 224x224 | 200 | 78.3 | 94.2 |
config
|
| ResNet-152 | 224x224 | 200 | 78.7 | 94.3 |
config
|
| ResNet-50 | 224x224 | 90 | 76.1 | 92.9 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnet50_tpu.yaml
)
|
| ResNet-50 | 224x224 | 200 | 77.1 | 93.5 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnet50_tpu.yaml
)
|
| ResNet-101 | 224x224 | 200 | 78.3 | 94.2 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnet101_tpu.yaml
)
|
| ResNet-152 | 224x224 | 200 | 78.7 | 94.3 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnet152_tpu.yaml
)
|
#### ResNet-RS models trained with settings including:
...
...
@@ -25,20 +25,20 @@ TF Vision model garden provides a large collection of baselines and checkpoints
*
Regularization methods including Random Augment, 4e-5 weight decay, stochastic depth, label smoothing and dropout.
*
New training methods including a 350-epoch schedule, cosine learning rate and
EMA.
*
Configs are in this
[
directory
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification
)
*
Configs are in this
[
directory
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification
)
.
model | resolution | params (M) | Top-1 | Top-5 | download
--------- | :--------: | -----: | ----: | ----: | -------:
ResNet-RS-50 | 160x160 | 35.7 | 79.1 | 94.5 |
ResNet-RS-101 | 160x160 | 63.7 | 80.2 | 94.9 |
ResNet-RS-101 | 192x192 | 63.7 | 81.3 | 95.6 |
ResNet-RS-152 | 192x192 | 86.8 | 81.9 | 95.8 |
ResNet-RS-152 | 224x224 | 86.8 | 82.5 | 96.1 |
ResNet-RS-152 | 256x256 | 86.8 | 83.1 | 96.3 |
ResNet-RS-200 | 256x256 | 93.4 | 83.5 | 96.6 |
ResNet-RS-270 | 256x256 | 130.1 | 83.6 | 96.6 |
ResNet-RS-350 | 256x256 | 164.3 | 83.7 | 96.7 |
ResNet-RS-350 | 320x320 | 164.3 | 84.2 | 96.9 |
ResNet-RS-50 | 160x160 | 35.7 | 79.1 | 94.5 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs50_i160.yaml
)
|
ResNet-RS-101 | 160x160 | 63.7 | 80.2 | 94.9 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs101_i160.yaml
)
|
ResNet-RS-101 | 192x192 | 63.7 | 81.3 | 95.6 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs101_i192.yaml
)
|
ResNet-RS-152 | 192x192 | 86.8 | 81.9 | 95.8 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs152_i192.yaml
)
|
ResNet-RS-152 | 224x224 | 86.8 | 82.5 | 96.1 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs152_i224.yaml
)
|
ResNet-RS-152 | 256x256 | 86.8 | 83.1 | 96.3 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs152_i256.yaml
)
|
ResNet-RS-200 | 256x256 | 93.4 | 83.5 | 96.6 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs200_i256.yaml
)
|
ResNet-RS-270 | 256x256 | 130.1 | 83.6 | 96.6 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs270_i256.yaml
)
|
ResNet-RS-350 | 256x256 | 164.3 | 83.7 | 96.7 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs350_i256.yaml
)
|
ResNet-RS-350 | 320x320 | 164.3 | 84.2 | 96.9 |
[
config
](
https://github.com/tensorflow/models/blob/master/official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs420_i256.yaml
)
|
## Object Detection and Instance Segmentation
...
...
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs101_i160.yaml
浏览文件 @
48b14968
...
...
@@ -19,6 +19,7 @@ task:
activation
:
'
swish'
norm_momentum
:
0.0
use_sync_bn
:
false
dropout_rate
:
0.25
losses
:
l2_weight_decay
:
0.00004
one_hot
:
true
...
...
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs101_i192.yaml
浏览文件 @
48b14968
...
...
@@ -19,6 +19,7 @@ task:
activation
:
'
swish'
norm_momentum
:
0.0
use_sync_bn
:
false
dropout_rate
:
0.25
losses
:
l2_weight_decay
:
0.00004
one_hot
:
true
...
...
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs152_i192.yaml
浏览文件 @
48b14968
...
...
@@ -19,6 +19,7 @@ task:
activation
:
'
swish'
norm_momentum
:
0.0
use_sync_bn
:
false
dropout_rate
:
0.25
losses
:
l2_weight_decay
:
0.00004
one_hot
:
true
...
...
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs152_i224.yaml
浏览文件 @
48b14968
...
...
@@ -19,6 +19,7 @@ task:
activation
:
'
swish'
norm_momentum
:
0.0
use_sync_bn
:
false
dropout_rate
:
0.25
losses
:
l2_weight_decay
:
0.00004
one_hot
:
true
...
...
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs152_i256.yaml
浏览文件 @
48b14968
...
...
@@ -19,6 +19,7 @@ task:
activation
:
'
swish'
norm_momentum
:
0.0
use_sync_bn
:
false
dropout_rate
:
0.25
losses
:
l2_weight_decay
:
0.00004
one_hot
:
true
...
...
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs200_i256.yaml
浏览文件 @
48b14968
...
...
@@ -19,6 +19,7 @@ task:
activation
:
'
swish'
norm_momentum
:
0.0
use_sync_bn
:
false
dropout_rate
:
0.25
losses
:
l2_weight_decay
:
0.00004
one_hot
:
true
...
...
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs270_i256.yaml
浏览文件 @
48b14968
...
...
@@ -19,6 +19,7 @@ task:
activation
:
'
swish'
norm_momentum
:
0.0
use_sync_bn
:
false
dropout_rate
:
0.25
losses
:
l2_weight_decay
:
0.00004
one_hot
:
true
...
...
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs350_i256.yaml
浏览文件 @
48b14968
...
...
@@ -19,6 +19,7 @@ task:
activation
:
'
swish'
norm_momentum
:
0.0
use_sync_bn
:
false
dropout_rate
:
0.25
losses
:
l2_weight_decay
:
0.00004
one_hot
:
true
...
...
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs350_i320.yaml
浏览文件 @
48b14968
...
...
@@ -19,6 +19,7 @@ task:
activation
:
'
swish'
norm_momentum
:
0.0
use_sync_bn
:
false
dropout_rate
:
0.4
losses
:
l2_weight_decay
:
0.00004
one_hot
:
true
...
...
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs420_i320.yaml
浏览文件 @
48b14968
...
...
@@ -18,6 +18,7 @@ task:
activation
:
'
swish'
norm_momentum
:
0.0
use_sync_bn
:
false
dropout_rate
:
0.4
losses
:
l2_weight_decay
:
0.00004
one_hot
:
true
...
...
official/vision/beta/configs/experiments/image_classification/imagenet_resnetrs50_i160.yaml
浏览文件 @
48b14968
...
...
@@ -19,6 +19,7 @@ task:
activation
:
'
swish'
norm_momentum
:
0.0
use_sync_bn
:
false
dropout_rate
:
0.25
losses
:
l2_weight_decay
:
0.00004
one_hot
:
true
...
...
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