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
s920243400
PaddleDetection
提交
2f0bfdb0
P
PaddleDetection
项目概览
s920243400
/
PaddleDetection
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleDetection
通知
2
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
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
PaddleDetection
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
未验证
提交
2f0bfdb0
编写于
9月 05, 2022
作者:
F
Feng Ni
提交者:
GitHub
9月 05, 2022
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add ppyoloeplus visdrone (#6818)
上级
0a02ef4e
变更
5
显示空白变更内容
内联
并排
Showing
5 changed file
with
67 addition
and
5 deletion
+67
-5
configs/visdrone/README.md
configs/visdrone/README.md
+1
-0
configs/visdrone/ppyoloe_plus_crn_l_largesize_80e_visdrone.yml
...gs/visdrone/ppyoloe_plus_crn_l_largesize_80e_visdrone.yml
+58
-0
deploy/python/infer.py
deploy/python/infer.py
+2
-1
deploy/python/visualize.py
deploy/python/visualize.py
+2
-2
ppdet/data/source/dataset.py
ppdet/data/source/dataset.py
+4
-2
未找到文件。
configs/visdrone/README.md
浏览文件 @
2f0bfdb0
...
@@ -17,6 +17,7 @@ PaddleDetection团队提供了针对VisDrone-DET小目标数航拍场景的基
...
@@ -17,6 +17,7 @@ PaddleDetection团队提供了针对VisDrone-DET小目标数航拍场景的基
|PP-YOLOE-P2-Alpha-l| 30.1 | 48.9 | 24.3 | 40.8 | 28.47 | 48.16 |
[
下载链接
](
https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_p2_alpha_80e_visdrone.pdparams
)
|
[
配置文件
](
./ppyoloe_crn_l_p2_alpha_80e_visdrone.yml
)
|
|PP-YOLOE-P2-Alpha-l| 30.1 | 48.9 | 24.3 | 40.8 | 28.47 | 48.16 |
[
下载链接
](
https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_p2_alpha_80e_visdrone.pdparams
)
|
[
配置文件
](
./ppyoloe_crn_l_p2_alpha_80e_visdrone.yml
)
|
|PP-YOLOE-Alpha-largesize-l| 41.9 | 65.0 | 32.3 | 53.0 | 37.13 | 61.15 |
[
下载链接
](
https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_alpha_largesize_80e_visdrone.pdparams
)
|
[
配置文件
](
./ppyoloe_crn_l_alpha_largesize_80e_visdrone.yml
)
|
|PP-YOLOE-Alpha-largesize-l| 41.9 | 65.0 | 32.3 | 53.0 | 37.13 | 61.15 |
[
下载链接
](
https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_alpha_largesize_80e_visdrone.pdparams
)
|
[
配置文件
](
./ppyoloe_crn_l_alpha_largesize_80e_visdrone.yml
)
|
|PP-YOLOE-P2-Alpha-largesize-l| 41.3 | 64.5 | 32.4 | 53.1 | 37.49 | 51.54 |
[
下载链接
](
https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_p2_alpha_largesize_80e_visdrone.pdparams
)
|
[
配置文件
](
./ppyoloe_crn_l_p2_alpha_largesize_80e_visdrone.yml
)
|
|PP-YOLOE-P2-Alpha-largesize-l| 41.3 | 64.5 | 32.4 | 53.1 | 37.49 | 51.54 |
[
下载链接
](
https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_p2_alpha_largesize_80e_visdrone.pdparams
)
|
[
配置文件
](
./ppyoloe_crn_l_p2_alpha_largesize_80e_visdrone.yml
)
|
|PP-YOLOE-plus-largesize-l | 43.3 | 66.7 | 33.5 | 54.7 | 38.24 | 62.76 |
[
下载链接
](
https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_largesize_80e_visdrone.pdparams
)
|
[
配置文件
](
./ppyoloe_plus_crn_l_largesize_80e_visdrone.yml
)
|
## 原图评估和拼图评估对比:
## 原图评估和拼图评估对比:
...
...
configs/visdrone/ppyoloe_plus_crn_l_largesize_80e_visdrone.yml
0 → 100644
浏览文件 @
2f0bfdb0
_BASE_
:
[
'
ppyoloe_crn_l_80e_visdrone.yml'
,
]
log_iter
:
100
snapshot_epoch
:
10
weights
:
output/ppyoloe_plus_crn_l_largesize_80e_visdrone/model_final
pretrain_weights
:
https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams
CSPResNet
:
use_alpha
:
True
LearningRate
:
base_lr
:
0.0025
worker_num
:
2
eval_height
:
&eval_height
1920
eval_width
:
&eval_width
1920
eval_size
:
&eval_size
[
*eval_height
,
*eval_width
]
TrainReader
:
sample_transforms
:
-
Decode
:
{}
-
RandomDistort
:
{}
-
RandomExpand
:
{
fill_value
:
[
123.675
,
116.28
,
103.53
]}
-
RandomCrop
:
{}
-
RandomFlip
:
{}
batch_transforms
:
-
BatchRandomResize
:
{
target_size
:
[
1024
,
1088
,
1152
,
1216
,
1280
,
1344
,
1408
,
1472
,
1536
,
1600
,
1664
,
1728
,
1792
,
1856
,
1920
],
random_size
:
True
,
random_interp
:
True
,
keep_ratio
:
False
}
-
NormalizeImage
:
{
mean
:
[
0.
,
0.
,
0.
],
std
:
[
1.
,
1.
,
1.
],
norm_type
:
none
}
-
Permute
:
{}
-
PadGT
:
{}
batch_size
:
2
shuffle
:
true
drop_last
:
true
use_shared_memory
:
true
collate_batch
:
true
EvalReader
:
sample_transforms
:
-
Decode
:
{}
-
Resize
:
{
target_size
:
*eval_size
,
keep_ratio
:
False
,
interp
:
2
}
-
NormalizeImage
:
{
mean
:
[
0.
,
0.
,
0.
],
std
:
[
1.
,
1.
,
1.
],
norm_type
:
none
}
-
Permute
:
{}
batch_size
:
1
TestReader
:
inputs_def
:
image_shape
:
[
3
,
*eval_height
,
*eval_width
]
sample_transforms
:
-
Decode
:
{}
-
Resize
:
{
target_size
:
*eval_size
,
keep_ratio
:
False
,
interp
:
2
}
-
NormalizeImage
:
{
mean
:
[
0.
,
0.
,
0.
],
std
:
[
1.
,
1.
,
1.
],
norm_type
:
none
}
-
Permute
:
{}
batch_size
:
1
fuse_normalize
:
True
deploy/python/infer.py
浏览文件 @
2f0bfdb0
...
@@ -235,7 +235,7 @@ class Detector(object):
...
@@ -235,7 +235,7 @@ class Detector(object):
import
sahi
import
sahi
from
sahi.slicing
import
slice_image
from
sahi.slicing
import
slice_image
except
Exception
as
e
:
except
Exception
as
e
:
logger
.
error
(
print
(
'sahi not found, plaese install sahi. '
'sahi not found, plaese install sahi. '
'for example: `pip install sahi`, see https://github.com/obss/sahi.'
'for example: `pip install sahi`, see https://github.com/obss/sahi.'
)
)
...
@@ -251,6 +251,7 @@ class Detector(object):
...
@@ -251,6 +251,7 @@ class Detector(object):
overlap_width_ratio
=
overlap_ratio
[
1
])
overlap_width_ratio
=
overlap_ratio
[
1
])
sub_img_num
=
len
(
slice_image_result
)
sub_img_num
=
len
(
slice_image_result
)
merged_bboxs
=
[]
merged_bboxs
=
[]
print
(
'sub_img_num'
,
sub_img_num
)
batch_image_list
=
[
batch_image_list
=
[
slice_image_result
.
images
[
_ind
]
for
_ind
in
range
(
sub_img_num
)
slice_image_result
.
images
[
_ind
]
for
_ind
in
range
(
sub_img_num
)
...
...
deploy/python/visualize.py
浏览文件 @
2f0bfdb0
...
@@ -237,7 +237,7 @@ def visualize_pose(imgfile,
...
@@ -237,7 +237,7 @@ def visualize_pose(imgfile,
import
matplotlib
import
matplotlib
plt
.
switch_backend
(
'agg'
)
plt
.
switch_backend
(
'agg'
)
except
Exception
as
e
:
except
Exception
as
e
:
logger
.
error
(
'Matplotlib not found, please install matplotlib.'
print
(
'Matplotlib not found, please install matplotlib.'
'for example: `pip install matplotlib`.'
)
'for example: `pip install matplotlib`.'
)
raise
e
raise
e
skeletons
,
scores
=
results
[
'keypoint'
]
skeletons
,
scores
=
results
[
'keypoint'
]
...
...
ppdet/data/source/dataset.py
浏览文件 @
2f0bfdb0
...
@@ -13,8 +13,8 @@
...
@@ -13,8 +13,8 @@
# limitations under the License.
# limitations under the License.
import
os
import
os
import
copy
import
numpy
as
np
import
numpy
as
np
try
:
try
:
from
collections.abc
import
Sequence
from
collections.abc
import
Sequence
except
Exception
:
except
Exception
:
...
@@ -22,9 +22,11 @@ except Exception:
...
@@ -22,9 +22,11 @@ except Exception:
from
paddle.io
import
Dataset
from
paddle.io
import
Dataset
from
ppdet.core.workspace
import
register
,
serializable
from
ppdet.core.workspace
import
register
,
serializable
from
ppdet.utils.download
import
get_dataset_path
from
ppdet.utils.download
import
get_dataset_path
import
copy
from
ppdet.data
import
source
from
ppdet.data
import
source
from
ppdet.utils.logger
import
setup_logger
logger
=
setup_logger
(
__name__
)
@
serializable
@
serializable
class
DetDataset
(
Dataset
):
class
DetDataset
(
Dataset
):
...
...
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