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
PaddlePaddle
hapi
提交
c54980b9
H
hapi
项目概览
PaddlePaddle
/
hapi
通知
11
Star
2
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
4
列表
看板
标记
里程碑
合并请求
7
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
H
hapi
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
4
Issue
4
列表
看板
标记
里程碑
合并请求
7
合并请求
7
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
c54980b9
编写于
4月 17, 2020
作者:
K
Kaipeng Deng
提交者:
GitHub
4月 17, 2020
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #44 from huangjun12/refine-bmn
refine details of bmn model
上级
434c5c20
c4e9065c
变更
8
隐藏空白更改
内联
并排
Showing
8 changed file
with
155 addition
and
107 deletion
+155
-107
examples/bmn/README.md
examples/bmn/README.md
+13
-19
examples/bmn/bmn.yaml
examples/bmn/bmn.yaml
+1
-10
examples/bmn/bmn_metric.py
examples/bmn/bmn_metric.py
+13
-0
examples/bmn/eval.py
examples/bmn/eval.py
+27
-8
examples/bmn/predict.py
examples/bmn/predict.py
+28
-9
examples/bmn/run.sh
examples/bmn/run.sh
+0
-1
examples/bmn/train.py
examples/bmn/train.py
+25
-24
hapi/vision/models/bmn_model.py
hapi/vision/models/bmn_model.py
+48
-36
未找到文件。
examples/bmn/README.md
浏览文件 @
c54980b9
...
...
@@ -29,7 +29,6 @@ BMN Overview
├── train.py # 训练代码,训练网络
├── eval.py # 评估代码,评估网络性能
├── predict.py # 预测代码,针对任意输入预测结果
├── bmn_model.py # 网络结构与损失函数定义
├── bmn_metric.py # 精度评估方法定义
├── reader.py # 数据reader,构造Dataset和Dataloader
├── bmn_utils.py # 模型细节相关代码
...
...
@@ -41,7 +40,7 @@ BMN Overview
## 数据准备
BMN的训练数据采用ActivityNet1.3提供的数据集,我们提供了处理好的视频特征
,请下载
[
bmn\_feat
](
https://paddlemodels.bj.bcebos.com/video_detection/bmn_feat.tar.gz
)
数据后解压,同时相应的修改bmn.yaml中的特征路径feat
\_
path。对应的标签文件请下载
[
label
](
https://paddlemodels.bj.bcebos.com/video_detection/activitynet_1.3_annotations.json
)
并修改bmn.yaml中的
标签文件路径anno
\_
file。
BMN的训练数据采用ActivityNet1.3提供的数据集,我们提供了处理好的视频特征
和对应的标签文件,请下载特征数据
[
bmn\_feat
](
https://paddlemodels.bj.bcebos.com/video_detection/bmn_feat.tar.gz
)
和标签数据
[
label
](
https://paddlemodels.bj.bcebos.com/video_detection/activitynet_1.3_annotations.json
)
,并相应地修改配置文件bmn.yaml中的特征文件路径feat
\_
path和
标签文件路径anno
\_
file。
## 模型训练
...
...
@@ -52,22 +51,17 @@ BMN的训练数据采用ActivityNet1.3提供的数据集,我们提供了处理
bash run.sh
若使用单卡训练,启动方式如下:
若使用单卡训练,
请将配置文件bmn.yaml中的batch
\_
size调整为16,
启动方式如下:
export CUDA_VISIBLE_DEVICES=0
python train.py
-
代码运行需要先安装pandas
-
从头开始训练,使用上述启动命令行或者脚本程序即可启动训练,不需要用到预训练模型
默认使用静态图训练,若使用动态图训练只需要在运行脚本添加
`-d`
参数即可,如:
-
单卡训练时,请将配置文件中的batch_size调整为16
python train.py -d
**训练策略:**
-
代码运行需要先安装pandas
*
采用Adam优化器,初始learning
\_
rate=0.001
*
权重衰减系数为1e-4
*
学习率在迭代次数达到4200的时候做一次衰减,衰减系数为0.1
-
从头开始训练,使用上述启动命令行或者脚本程序即可启动训练,不需要用到预训练模型
## 模型评估
...
...
@@ -76,9 +70,9 @@ BMN的训练数据采用ActivityNet1.3提供的数据集,我们提供了处理
python eval.py --weights=$PATH_TO_WEIGHTS
-
进行评估时,可修改命令行中的
`weights`
参数指定需要评估的权重,
如果不设置,将使用默认参数文件checkpoint/final.pdparams
。
-
进行评估时,可修改命令行中的
`weights`
参数指定需要评估的权重,
若未指定,脚本会下载已发布的模型
[
model
](
https://paddlemodels.bj.bcebos.com/hapi/bmn.pdparams
)
进行评估
。
-
上述程序会将运行结果保存在
output/EVAL/BMN
\_
results文件夹下,测试结果保存在evaluate
\_
results/bmn
\_
results
\_
validation.json文件中
。
-
上述程序会将运行结果保存在
`--output_path`
参数指定的文件夹下,默认为output/EVAL/BMN
\_
results;测试结果保存在
`--result_path`
参数指定的文件夹下,默认为evaluate
\_
results
。
-
注:评估时可能会出现loss为nan的情况。这是由于评估时用的是单个样本,可能存在没有iou>0.6的样本,所以为nan,对最终的评估结果没有影响。
...
...
@@ -87,9 +81,9 @@ BMN的训练数据采用ActivityNet1.3提供的数据集,我们提供了处理
-
ActivityNet数据集的具体使用说明可以参考其
[
官方网站
](
http://activity-net.org
)
-
下载指标评估代码,请从
[
ActivityNet Gitub repository
](
https://github.com/activitynet/ActivityNet.git
)
下载,将Evaluation文件夹拷贝至
models/dygraph
/bmn目录下。(注:由于第三方评估代码不支持python3,此处建议使用python2进行评估;若使用python3,print函数需要添加括号,请对Evaluation目录下的.py文件做相应修改。)
-
下载指标评估代码,请从
[
ActivityNet Gitub repository
](
https://github.com/activitynet/ActivityNet.git
)
下载,将Evaluation文件夹拷贝至
hapi/examples
/bmn目录下。(注:由于第三方评估代码不支持python3,此处建议使用python2进行评估;若使用python3,print函数需要添加括号,请对Evaluation目录下的.py文件做相应修改。)
-
请下载
[
activity\_net\_1\_3\_new.json
](
https://paddlemodels.bj.bcebos.com/video_detection/activity_net_1_3_new.json
)
文件,并将其放置在
models/dygraph
/bmn/Evaluation/data目录下,相较于原始的activity
\_
net.v1-3.min.json文件,我们过滤了其中一些失效的视频条目。
-
请下载
[
activity\_net\_1\_3\_new.json
](
https://paddlemodels.bj.bcebos.com/video_detection/activity_net_1_3_new.json
)
文件,并将其放置在
hapi/examples
/bmn/Evaluation/data目录下,相较于原始的activity
\_
net.v1-3.min.json文件,我们过滤了其中一些失效的视频条目。
-
计算精度指标
...
...
@@ -100,7 +94,7 @@ BMN的训练数据采用ActivityNet1.3提供的数据集,我们提供了处理
| AR@1 | AR@5 | AR@10 | AR@100 | AUC |
| :---: | :---: | :---: | :---: | :---: |
| 33.
46 | 49.25 | 56.25 | 75.40
| 67.16% |
| 33.
10 | 49.18 | 56.54 | 75.12
| 67.16% |
## 模型推断
...
...
@@ -110,9 +104,9 @@ BMN的训练数据采用ActivityNet1.3提供的数据集,我们提供了处理
python predict.py --weights=$PATH_TO_WEIGHTS \
--filelist=$FILELIST
-
使用python命令行启动程序时,
`--filelist`
参数指定待推断的文件列表,如果不设置,默认为./infer.list。
`--weights`
参数为训练好的权重参数,
如果不设置,将使用默认参数文件checkpoint/final.pdparams
。
-
使用python命令行启动程序时,
`--filelist`
参数指定待推断的文件列表,如果不设置,默认为./infer.list。
`--weights`
参数为训练好的权重参数,
若未指定,脚本会下载已发布的模型
[
model
](
https://paddlemodels.bj.bcebos.com/hapi/bmn.pdparams
)
进行预测
。
-
上述程序会将运行结果保存在
output/INFER/BMN
\_
results文件夹下,测试结果保存在predict
\_
results/bmn
\_
results
\_
test.json文件中
。
-
上述程序会将运行结果保存在
`--output_path`
参数指定的文件夹下,默认为output/INFER/BMN
\_
results;测试结果保存在
`--result_path`
参数指定的文件夹下,默认为predict
\_
results
。
## 参考论文
...
...
examples/bmn/bmn.yaml
浏览文件 @
c54980b9
...
...
@@ -12,11 +12,10 @@ MODEL:
TRAIN
:
subset
:
"
train"
epoch
:
9
batch_size
:
4
batch_size
:
4
num_workers
:
4
use_shuffle
:
True
device
:
"
gpu"
num_gpus
:
4
learning_rate
:
0.001
learning_rate_decay
:
0.1
lr_decay_iter
:
4200
...
...
@@ -29,10 +28,6 @@ TEST:
subset
:
"
validation"
batch_size
:
1
num_workers
:
1
use_buffer
:
False
snms_alpha
:
0.001
snms_t1
:
0.5
snms_t2
:
0.9
output_path
:
"
output/EVAL/BMN_results"
result_path
:
"
evaluate_results"
...
...
@@ -40,10 +35,6 @@ INFER:
subset
:
"
test"
batch_size
:
1
num_workers
:
1
use_buffer
:
False
snms_alpha
:
0.4
snms_t1
:
0.5
snms_t2
:
0.9
filelist
:
'
./infer.list'
output_path
:
"
output/INFER/BMN_results"
result_path
:
"
predict_results"
...
...
examples/bmn/bmn_metric.py
浏览文件 @
c54980b9
...
...
@@ -36,8 +36,21 @@ class BmnMetric(Metric):
#get video_dict and video_list
if
self
.
mode
==
'test'
:
self
.
get_test_dataset_dict
()
if
not
os
.
path
.
isdir
(
self
.
cfg
.
TEST
.
output_path
):
os
.
makedirs
(
self
.
cfg
.
TEST
.
output_path
)
if
not
os
.
path
.
isdir
(
self
.
cfg
.
TEST
.
result_path
):
os
.
makedirs
(
self
.
cfg
.
TEST
.
result_path
)
elif
self
.
mode
==
'infer'
:
self
.
get_infer_dataset_dict
()
if
not
os
.
path
.
isdir
(
self
.
cfg
.
INFER
.
output_path
):
os
.
makedirs
(
self
.
cfg
.
INFER
.
output_path
)
if
not
os
.
path
.
isdir
(
self
.
cfg
.
INFER
.
result_path
):
os
.
makedirs
(
self
.
cfg
.
INFER
.
result_path
)
def
add_metric_op
(
self
,
preds
,
label
):
pred_bm
,
pred_start
,
pred_en
=
preds
video_index
=
label
[
-
1
]
return
[
pred_bm
,
pred_start
,
pred_en
,
video_index
]
#return list
def
update
(
self
,
pred_bm
,
pred_start
,
pred_end
,
fid
):
# generate proposals
...
...
examples/bmn/eval.py
浏览文件 @
c54980b9
...
...
@@ -37,7 +37,6 @@ def parse_args():
parser
.
add_argument
(
"-d"
,
"--dynamic"
,
default
=
True
,
action
=
'store_true'
,
help
=
"enable dygraph mode, only support dynamic mode at present time"
)
parser
.
add_argument
(
...
...
@@ -56,6 +55,17 @@ def parse_args():
default
=
None
,
help
=
'weight path, None to automatically download weights provided by Paddle.'
)
parser
.
add_argument
(
'--output_path'
,
type
=
str
,
default
=
"output/EVAL/BMN_results"
,
help
=
'output dir path, default to use output/EVAL/BMN_results'
)
parser
.
add_argument
(
'--result_path'
,
type
=
str
,
default
=
"evaluate_results/"
,
help
=
'output dir path after post processing, default to use ./evaluate_results/'
)
parser
.
add_argument
(
'--log_interval'
,
type
=
int
,
...
...
@@ -67,17 +77,21 @@ def parse_args():
# Performance Evaluation
def
test_bmn
(
args
):
# only support dynamic mode at present time
device
=
set_device
(
args
.
device
)
fluid
.
enable_dygraph
(
device
)
if
args
.
dynamic
else
None
#config setting
config
=
parse_config
(
args
.
config_file
)
eval_cfg
=
merge_configs
(
config
,
'test'
,
vars
(
args
))
if
not
os
.
path
.
isdir
(
config
.
TEST
.
output_path
):
os
.
makedirs
(
config
.
TEST
.
output_path
)
if
not
os
.
path
.
isdir
(
config
.
TEST
.
result_path
):
os
.
makedirs
(
config
.
TEST
.
result_path
)
feat_dim
=
config
.
MODEL
.
feat_dim
tscale
=
config
.
MODEL
.
tscale
dscale
=
config
.
MODEL
.
dscale
prop_boundary_ratio
=
config
.
MODEL
.
prop_boundary_ratio
num_sample
=
config
.
MODEL
.
num_sample
num_sample_perbin
=
config
.
MODEL
.
num_sample_perbin
#input and video index
inputs
=
[
Input
(
[
None
,
config
.
MODEL
.
feat_dim
,
config
.
MODEL
.
tscale
],
...
...
@@ -97,9 +111,14 @@ def test_bmn(args):
eval_dataset
=
BmnDataset
(
eval_cfg
,
'test'
)
#model
model
=
bmn
(
config
,
pretrained
=
args
.
weights
is
None
)
model
=
bmn
(
tscale
,
dscale
,
prop_boundary_ratio
,
num_sample
,
num_sample_perbin
,
pretrained
=
args
.
weights
is
None
)
model
.
prepare
(
loss_function
=
BmnLoss
(
config
),
loss_function
=
BmnLoss
(
tscale
,
dscale
),
metrics
=
BmnMetric
(
config
,
mode
=
'test'
),
inputs
=
inputs
,
...
...
examples/bmn/predict.py
浏览文件 @
c54980b9
...
...
@@ -37,7 +37,6 @@ def parse_args():
parser
.
add_argument
(
"-d"
,
"--dynamic"
,
default
=
True
,
action
=
'store_true'
,
help
=
"enable dygraph mode, only support dynamic mode at present time"
)
parser
.
add_argument
(
...
...
@@ -54,10 +53,21 @@ def parse_args():
help
=
'weight path, None to automatically download weights provided by Paddle.'
)
parser
.
add_argument
(
'--save_dir'
,
'--filelist'
,
type
=
str
,
default
=
"infer.list"
,
help
=
'infer file list, default to use ./infer.list'
)
parser
.
add_argument
(
'--output_path'
,
type
=
str
,
default
=
"output/INFER/BMN_results"
,
help
=
'output dir path, default to use output/INFER/BMN_results'
)
parser
.
add_argument
(
'--result_path'
,
type
=
str
,
default
=
"predict_results/"
,
help
=
'output dir path, default to use ./predict_results/'
)
help
=
'output dir path after post processing, default to use ./predict_results/'
)
parser
.
add_argument
(
'--log_interval'
,
type
=
int
,
...
...
@@ -69,18 +79,21 @@ def parse_args():
# Prediction
def
infer_bmn
(
args
):
# only support dynamic mode at present time
device
=
set_device
(
args
.
device
)
fluid
.
enable_dygraph
(
device
)
if
args
.
dynamic
else
None
#config setting
config
=
parse_config
(
args
.
config_file
)
infer_cfg
=
merge_configs
(
config
,
'infer'
,
vars
(
args
))
if
not
os
.
path
.
isdir
(
config
.
INFER
.
output_path
):
os
.
makedirs
(
config
.
INFER
.
output_path
)
if
not
os
.
path
.
isdir
(
config
.
INFER
.
result_path
):
os
.
makedirs
(
config
.
INFER
.
result_path
)
feat_dim
=
config
.
MODEL
.
feat_dim
tscale
=
config
.
MODEL
.
tscale
dscale
=
config
.
MODEL
.
dscale
prop_boundary_ratio
=
config
.
MODEL
.
prop_boundary_ratio
num_sample
=
config
.
MODEL
.
num_sample
num_sample_perbin
=
config
.
MODEL
.
num_sample_perbin
#input and video index
inputs
=
[
Input
(
[
None
,
config
.
MODEL
.
feat_dim
,
config
.
MODEL
.
tscale
],
...
...
@@ -92,7 +105,13 @@ def infer_bmn(args):
#data
infer_dataset
=
BmnDataset
(
infer_cfg
,
'infer'
)
model
=
bmn
(
config
,
pretrained
=
args
.
weights
is
None
)
#model
model
=
bmn
(
tscale
,
dscale
,
prop_boundary_ratio
,
num_sample
,
num_sample_perbin
,
pretrained
=
args
.
weights
is
None
)
model
.
prepare
(
metrics
=
BmnMetric
(
config
,
mode
=
'infer'
),
...
...
examples/bmn/run.sh
浏览文件 @
c54980b9
export
CUDA_VISIBLE_DEVICES
=
0,1,2,3
python
-m
paddle.distributed.launch train.py
examples/bmn/train.py
浏览文件 @
c54980b9
...
...
@@ -34,11 +34,7 @@ logger = logging.getLogger(__name__)
def
parse_args
():
parser
=
argparse
.
ArgumentParser
(
"Paddle high level api of BMN."
)
parser
.
add_argument
(
"-d"
,
"--dynamic"
,
default
=
True
,
action
=
'store_true'
,
help
=
"enable dygraph mode"
)
"-d"
,
"--dynamic"
,
action
=
'store_true'
,
help
=
"enable dygraph mode"
)
parser
.
add_argument
(
'--config_file'
,
type
=
str
,
...
...
@@ -48,7 +44,7 @@ def parse_args():
'--batch_size'
,
type
=
int
,
default
=
None
,
help
=
'training batch size. None
to use config file setting
.'
)
help
=
'training batch size. None
for read from config file
.'
)
parser
.
add_argument
(
'--learning_rate'
,
type
=
float
,
...
...
@@ -68,8 +64,8 @@ def parse_args():
parser
.
add_argument
(
'--epoch'
,
type
=
int
,
default
=
9
,
help
=
'epoch number,
0
for read from config file'
)
default
=
None
,
help
=
'epoch number,
None
for read from config file'
)
parser
.
add_argument
(
'--valid_interval'
,
type
=
int
,
...
...
@@ -113,22 +109,23 @@ def train_bmn(args):
if
not
os
.
path
.
isdir
(
args
.
save_dir
):
os
.
makedirs
(
args
.
save_dir
)
#config setting
config
=
parse_config
(
args
.
config_file
)
train_cfg
=
merge_configs
(
config
,
'train'
,
vars
(
args
))
val_cfg
=
merge_configs
(
config
,
'valid'
,
vars
(
args
))
inputs
=
[
Input
(
[
None
,
config
.
MODEL
.
feat_dim
,
config
.
MODEL
.
tscale
],
'float32'
,
name
=
'feat_input'
)
]
gt_iou_map
=
Input
(
[
None
,
config
.
MODEL
.
dscale
,
config
.
MODEL
.
tscale
],
'float32'
,
name
=
'gt_iou_map'
)
gt_start
=
Input
([
None
,
config
.
MODEL
.
tscale
],
'float32'
,
name
=
'gt_start'
)
gt_end
=
Input
([
None
,
config
.
MODEL
.
tscale
],
'float32'
,
name
=
'gt_end'
)
feat_dim
=
config
.
MODEL
.
feat_dim
tscale
=
config
.
MODEL
.
tscale
dscale
=
config
.
MODEL
.
dscale
prop_boundary_ratio
=
config
.
MODEL
.
prop_boundary_ratio
num_sample
=
config
.
MODEL
.
num_sample
num_sample_perbin
=
config
.
MODEL
.
num_sample_perbin
# input and label list
inputs
=
[
Input
([
None
,
feat_dim
,
tscale
],
'float32'
,
name
=
'feat_input'
)]
gt_iou_map
=
Input
([
None
,
dscale
,
tscale
],
'float32'
,
name
=
'gt_iou_map'
)
gt_start
=
Input
([
None
,
tscale
],
'float32'
,
name
=
'gt_start'
)
gt_end
=
Input
([
None
,
tscale
],
'float32'
,
name
=
'gt_end'
)
labels
=
[
gt_iou_map
,
gt_start
,
gt_end
]
# data
...
...
@@ -136,11 +133,16 @@ def train_bmn(args):
val_dataset
=
BmnDataset
(
val_cfg
,
'valid'
)
# model
model
=
bmn
(
config
,
pretrained
=
False
)
model
=
bmn
(
tscale
,
dscale
,
prop_boundary_ratio
,
num_sample
,
num_sample_perbin
,
pretrained
=
False
)
optim
=
optimizer
(
config
,
parameter_list
=
model
.
parameters
())
model
.
prepare
(
optimizer
=
optim
,
loss_function
=
BmnLoss
(
config
),
loss_function
=
BmnLoss
(
tscale
,
dscale
),
inputs
=
inputs
,
labels
=
labels
,
device
=
device
)
...
...
@@ -148,11 +150,10 @@ def train_bmn(args):
# if resume weights is given, load resume weights directly
if
args
.
resume
is
not
None
:
model
.
load
(
args
.
resume
)
model
.
fit
(
train_data
=
train_dataset
,
eval_data
=
val_dataset
,
batch_size
=
train_cfg
.
TRAIN
.
batch_size
,
epochs
=
args
.
epoch
,
epochs
=
train_cfg
.
TRAIN
.
epoch
,
eval_freq
=
args
.
valid_interval
,
log_freq
=
args
.
log_interval
,
save_dir
=
args
.
save_dir
,
...
...
hapi/vision/models/bmn_model.py
浏览文件 @
c54980b9
...
...
@@ -14,7 +14,6 @@
import
paddle.fluid
as
fluid
from
paddle.fluid
import
ParamAttr
from
paddle.fluid.framework
import
in_dygraph_mode
import
numpy
as
np
import
math
...
...
@@ -27,7 +26,7 @@ DATATYPE = 'float32'
pretrain_infos
=
{
'bmn'
:
(
'https://paddlemodels.bj.bcebos.com/hapi/bmn.pdparams'
,
'9286c821acc4cad46d6613b931ba468c'
)
'9286c821acc4cad46d6613b931ba468c'
)
}
...
...
@@ -131,17 +130,23 @@ class BMN(Model):
`"BMN: Boundary-Matching Network for Temporal Action Proposal Generation" <https://arxiv.org/abs/1907.09702>`_
Args:
cfg (AttrDict): configs for BMN model
tscale (int): sequence length, default 100.
dscale (int): max duration length, default 100.
prop_boundary_ratio (float): ratio of expanded temporal region in proposal boundary, default 0.5.
num_sample (int): number of samples betweent starting boundary and ending boundary of each propoasl, default 32.
num_sample_perbin (int): number of selected points in each sample, default 3.
"""
def
__init__
(
self
,
cfg
):
def
__init__
(
self
,
tscale
,
dscale
,
prop_boundary_ratio
,
num_sample
,
num_sample_perbin
):
super
(
BMN
,
self
).
__init__
()
#init config
self
.
tscale
=
cfg
.
MODEL
.
tscale
self
.
dscale
=
cfg
.
MODEL
.
dscale
self
.
prop_boundary_ratio
=
cfg
.
MODEL
.
prop_boundary_ratio
self
.
num_sample
=
cfg
.
MODEL
.
num_sample
self
.
num_sample_perbin
=
cfg
.
MODEL
.
num_sample_perbin
self
.
tscale
=
tscale
self
.
dscale
=
dscale
self
.
prop_boundary_ratio
=
prop_boundary_ratio
self
.
num_sample
=
num_sample
self
.
num_sample_perbin
=
num_sample_perbin
self
.
hidden_dim_1d
=
256
self
.
hidden_dim_2d
=
128
...
...
@@ -192,23 +197,17 @@ class BMN(Model):
padding
=
1
,
act
=
"relu"
)
#
init to speed up
#
get sample mask
sample_mask_array
=
get_interp1d_mask
(
self
.
tscale
,
self
.
dscale
,
self
.
prop_boundary_ratio
,
self
.
num_sample
,
self
.
num_sample_perbin
)
if
in_dygraph_mode
():
self
.
sample_mask
=
fluid
.
dygraph
.
base
.
to_variable
(
sample_mask_array
)
else
:
# static
self
.
sample_mask
=
fluid
.
layers
.
create_parameter
(
shape
=
[
self
.
tscale
,
self
.
num_sample
*
self
.
dscale
*
self
.
tscale
],
dtype
=
DATATYPE
,
attr
=
fluid
.
ParamAttr
(
name
=
"sample_mask"
,
trainable
=
False
),
default_initializer
=
fluid
.
initializer
.
NumpyArrayInitializer
(
sample_mask_array
))
self
.
sample_mask
=
fluid
.
layers
.
create_parameter
(
shape
=
[
self
.
tscale
,
self
.
num_sample
*
self
.
dscale
*
self
.
tscale
],
dtype
=
DATATYPE
,
attr
=
fluid
.
ParamAttr
(
name
=
"sample_mask"
,
trainable
=
False
),
default_initializer
=
fluid
.
initializer
.
NumpyArrayInitializer
(
sample_mask_array
))
self
.
sample_mask
.
stop_gradient
=
True
...
...
@@ -292,23 +291,27 @@ class BmnLoss(Loss):
"""Loss for BMN model
Args:
cfg (AttrDict): configs for BMN model
tscale (int): sequence length, default 100.
dscale (int): max duration length, default 100.
"""
def
__init__
(
self
,
cfg
):
def
__init__
(
self
,
tscale
,
dscale
):
super
(
BmnLoss
,
self
).
__init__
()
self
.
cfg
=
cfg
self
.
tscale
=
tscale
self
.
dscale
=
dscale
def
_get_mask
(
self
):
dscale
=
self
.
cfg
.
MODEL
.
dscale
tscale
=
self
.
cfg
.
MODEL
.
tscale
bm_mask
=
[]
for
idx
in
range
(
dscale
):
mask_vector
=
[
1
for
i
in
range
(
tscale
-
idx
)
for
idx
in
range
(
self
.
dscale
):
mask_vector
=
[
1
for
i
in
range
(
self
.
tscale
-
idx
)
]
+
[
0
for
i
in
range
(
idx
)]
bm_mask
.
append
(
mask_vector
)
bm_mask
=
np
.
array
(
bm_mask
,
dtype
=
np
.
float32
)
self_bm_mask
=
fluid
.
layers
.
create_global_var
(
shape
=
[
dscale
,
tscale
],
value
=
0
,
dtype
=
DATATYPE
,
persistable
=
True
)
shape
=
[
self
.
dscale
,
self
.
tscale
],
value
=
0
,
dtype
=
DATATYPE
,
persistable
=
True
)
fluid
.
layers
.
assign
(
bm_mask
,
self_bm_mask
)
self_bm_mask
.
stop_gradient
=
True
return
self_bm_mask
...
...
@@ -437,15 +440,24 @@ class BmnLoss(Loss):
return
loss
def
bmn
(
cfg
,
pretrained
=
True
):
def
bmn
(
tscale
,
dscale
,
prop_boundary_ratio
,
num_sample
,
num_sample_perbin
,
pretrained
=
True
):
"""BMN model
Args:
cfg (AttrDict): configs for BMN model
pretrained (bool): If True, returns a model with pre-trained model
on COCO, default True
tscale (int): sequence length, default 100.
dscale (int): max duration length, default 100.
prop_boundary_ratio (float): ratio of expanded temporal region in proposal boundary, default 0.5.
num_sample (int): number of samples betweent starting boundary and ending boundary of each propoasl, default 32.
num_sample_perbin (int): number of selected points in each sample, default 3.
pretrained (bool): If True, returns a model with pre-trained model, default True.
"""
model
=
BMN
(
cfg
)
model
=
BMN
(
tscale
,
dscale
,
prop_boundary_ratio
,
num_sample
,
num_sample_perbin
)
if
pretrained
:
weight_path
=
get_weights_path
(
*
(
pretrain_infos
[
'bmn'
]))
assert
weight_path
.
endswith
(
'.pdparams'
),
\
...
...
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