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
牧羊zove
fcos
提交
52f8a2b7
F
fcos
项目概览
牧羊zove
/
fcos
与 Fork 源项目一致
从无法访问的项目Fork
通知
5
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
F
fcos
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
52f8a2b7
编写于
7月 02, 2019
作者:
Z
Zhi Tian
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
update configs
上级
c93ebbbb
变更
6
隐藏空白更改
内联
并排
Showing
6 changed file
with
74 addition
and
1 deletion
+74
-1
README.md
README.md
+9
-0
configs/fcos/fcos_bn_bs16_MNV2_FPN_1x.yaml
configs/fcos/fcos_bn_bs16_MNV2_FPN_1x.yaml
+2
-0
configs/fcos/fcos_syncbn_bs32_MNV2_FPN_1x.yaml
configs/fcos/fcos_syncbn_bs32_MNV2_FPN_1x.yaml
+30
-0
maskrcnn_benchmark/config/defaults.py
maskrcnn_benchmark/config/defaults.py
+1
-0
tools/remove_solver_states.py
tools/remove_solver_states.py
+30
-0
tools/train_net.py
tools/train_net.py
+2
-1
未找到文件。
README.md
浏览文件 @
52f8a2b7
...
...
@@ -55,6 +55,8 @@ Please note that:
For your convenience, we provide the following trained models (more models are coming soon).
**ResNe(x)ts:**
Model | Total training mem (GB) | Multi-scale training | Testing time / im | AP (minival) | AP (test-dev) | Link
--- |:---:|:---:|:---:|:---:|:--:|:---:
FCOS_R_50_FPN_1x | 29.3 | No | 71ms | 37.1 | 37.4 |
[
download
](
https://cloudstor.aarnet.edu.au/plus/s/dDeDPBLEAt19Xrl/download
)
...
...
@@ -62,6 +64,13 @@ FCOS_R_101_FPN_2x | 44.1 | Yes | 74ms | 41.4 | 41.5 | [download](https://cloudst
FCOS_X_101_32x8d_FPN_2x | 72.9 | Yes | 122ms | 42.5 | 42.7 |
[
download
](
https://cloudstor.aarnet.edu.au/plus/s/U5myBfGF7MviZ97/download
)
FCOS_X_101_64x4d_FPN_2x | 77.7 | Yes | 140ms | 43.0 | 43.2 |
[
download
](
https://cloudstor.aarnet.edu.au/plus/s/wpwoCi4S8iajFi9/download
)
*All ResNe(x)t models are trained with 16 images in a mini-batch.*
**MobileNets:**
Model | Training batch size | Multi-scale training | Testing time / im | AP (minival) | Link
--- |:---:|:---:|:---:|:---:|:--:|:---:
FCOS_R_50_FPN_1x | 29.3 | No | 71ms | 37.1 | 37.4 |
[
download
](
https://cloudstor.aarnet.edu.au/plus/s/dDeDPBLEAt19Xrl/download
)
[1]
*1x and 2x mean the model is trained for 90K and 180K iterations, respectively.*
\
[2]
*We report total training memory footprint on all GPUs instead of the memory footprint per GPU as in maskrcnn-benchmark*
.
\
[3]
*All results are obtained with a single model and without any test time data augmentation such as multi-scale, flipping and etc..*
\
...
...
configs/fcos/fcos_MNV2_FPN_1x.yaml
→
configs/fcos/fcos_
bn_bs16_
MNV2_FPN_1x.yaml
浏览文件 @
52f8a2b7
...
...
@@ -5,10 +5,12 @@ MODEL:
FCOS_ON
:
True
BACKBONE
:
CONV_BODY
:
"
MNV2-FPN-RETINANET"
FREEZE_CONV_BODY_AT
:
0
RESNETS
:
BACKBONE_OUT_CHANNELS
:
256
RETINANET
:
USE_C5
:
False
# FCOS uses P5 instead of C5
USE_SYNCBN
:
False
DATASETS
:
TRAIN
:
("coco_2014_train", "coco_2014_valminusminival")
TEST
:
("coco_2014_minival",)
...
...
configs/fcos/fcos_syncbn_bs32_MNV2_FPN_1x.yaml
0 → 100644
浏览文件 @
52f8a2b7
MODEL
:
META_ARCHITECTURE
:
"
GeneralizedRCNN"
WEIGHT
:
"
https://cloudstor.aarnet.edu.au/plus/s/xtixKaxLWmbcyf7/download#mobilenet_v2-ecbe2b5.pth"
RPN_ONLY
:
True
FCOS_ON
:
True
BACKBONE
:
CONV_BODY
:
"
MNV2-FPN-RETINANET"
FREEZE_CONV_BODY_AT
:
0
RESNETS
:
BACKBONE_OUT_CHANNELS
:
256
RETINANET
:
USE_C5
:
False
# FCOS uses P5 instead of C5
USE_SYNCBN
:
True
DATASETS
:
TRAIN
:
("coco_2014_train", "coco_2014_valminusminival")
TEST
:
("coco_2014_minival",)
INPUT
:
MIN_SIZE_TRAIN
:
(800,)
MAX_SIZE_TRAIN
:
1333
MIN_SIZE_TEST
:
800
MAX_SIZE_TEST
:
1333
DATALOADER
:
SIZE_DIVISIBILITY
:
32
SOLVER
:
BASE_LR
:
0.01
WEIGHT_DECAY
:
0.0001
STEPS
:
(60000, 80000)
MAX_ITER
:
90000
IMS_PER_BATCH
:
32
WARMUP_METHOD
:
"
constant"
maskrcnn_benchmark/config/defaults.py
浏览文件 @
52f8a2b7
...
...
@@ -34,6 +34,7 @@ _C.MODEL.CLS_AGNOSTIC_BBOX_REG = False
# the path in paths_catalog. Else, it will use it as the specified absolute
# path
_C
.
MODEL
.
WEIGHT
=
""
_C
.
USE_SYNCBN
=
False
# -----------------------------------------------------------------------------
...
...
tools/remove_solver_states.py
0 → 100644
浏览文件 @
52f8a2b7
# Set up custom environment before nearly anything else is imported
# NOTE: this should be the first import (no not reorder)
from
maskrcnn_benchmark.utils.env
import
setup_environment
# noqa F401 isort:skip
import
argparse
import
os
import
torch
def
main
():
parser
=
argparse
.
ArgumentParser
(
description
=
"Remove the solver states stored in a trained model"
)
parser
.
add_argument
(
"model"
,
default
=
"models/FCOS_R_50_FPN_1x.pth"
,
help
=
"path to the input model file"
,
)
args
=
parser
.
parse_args
()
model
=
torch
.
load
(
args
.
model
)
del
model
[
"optimizer"
]
del
model
[
"scheduler"
]
filename_wo_ext
,
ext
=
os
.
path
.
splitext
(
args
.
model
)
output_file
=
filename_wo_ext
+
"_wo_solver_states"
+
ext
torch
.
save
(
model
,
output_file
)
print
(
"Done. The model without solver states is saved to {}"
.
format
(
output_file
))
if
__name__
==
"__main__"
:
main
()
tools/train_net.py
浏览文件 @
52f8a2b7
...
...
@@ -31,7 +31,8 @@ def train(cfg, local_rank, distributed):
device
=
torch
.
device
(
cfg
.
MODEL
.
DEVICE
)
model
.
to
(
device
)
model
=
torch
.
nn
.
SyncBatchNorm
.
convert_sync_batchnorm
(
model
)
if
cfg
.
MODEL
.
USE_SYNCBN
:
model
=
torch
.
nn
.
SyncBatchNorm
.
convert_sync_batchnorm
(
model
)
optimizer
=
make_optimizer
(
cfg
,
model
)
scheduler
=
make_lr_scheduler
(
cfg
,
optimizer
)
...
...
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