forgetest5
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

rename rec_resnet_fpn

This commit is contained in:
tink2123 2020-08-26 20:14:13 +08:00
parent 97cfef3265
commit 5edb619cdd
2 changed files with 98 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
configs/rec/rec_r50fpn_vd_none_srn.yml
View File

@ -27,7 +27,7 @@ Architecture:
function: ppocr.modeling.architectures.rec_model,RecModel
Backbone:
function: ppocr.modeling.backbones.rec_resnet50_fpn,ResNet
function: ppocr.modeling.backbones.rec_resnet_fpn,ResNet
layers: 50
Head:

107
ppocr/modeling/backbones/rec_resnet50_fpn.py → ppocr/modeling/backbones/rec_resnet_fpn.py
View File

@ -22,12 +22,12 @@ import paddle
import paddle.fluid as fluid
from paddle.fluid.param_attr import ParamAttr
__all__ = ["ResNet", "ResNet18", "ResNet34", "ResNet50", "ResNet101", "ResNet152"]
__all__ = [
"ResNet", "ResNet18", "ResNet34", "ResNet50", "ResNet101", "ResNet152"
]
Trainable = True
w_nolr = fluid.ParamAttr(
trainable = Trainable)
w_nolr = fluid.ParamAttr(trainable=Trainable)
train_parameters = {
"input_size": [3, 224, 224],
"input_mean": [0.485, 0.456, 0.406],
@ -40,12 +40,12 @@ train_parameters = {
}
}
class ResNet():
def __init__(self, params):
self.layers = params['layers']
self.params = train_parameters
def __call__(self, input):
layers = self.layers
supported_layers = [18, 34, 50, 101, 152]
@ -64,7 +64,12 @@ class ResNet():
num_filters = [64, 128, 256, 512]
conv = self.conv_bn_layer(
input=input, num_filters=64, filter_size=7, stride=2, act='relu', name="conv1")
input=input,
num_filters=64,
filter_size=7,
stride=2,
act='relu',
name="conv1")
F = []
if layers >= 50:
for block in range(len(depth)):
@ -79,7 +84,8 @@ class ResNet():
conv = self.bottleneck_block(
input=conv,
num_filters=num_filters[block],
stride=stride_list[block] if i == 0 else 1, name=conv_name)
stride=stride_list[block] if i == 0 else 1,
name=conv_name)
F.append(conv)
else:
for block in range(len(depth)):
@ -105,17 +111,40 @@ class ResNet():
if (w, h) == base.shape[2:]:
base = base
else:
base = fluid.layers.conv2d_transpose( input=base, num_filters=c,filter_size=4, stride=2,
padding=1,act=None,
base = fluid.layers.conv2d_transpose(
input=base,
num_filters=c,
filter_size=4,
stride=2,
padding=1,
act=None,
param_attr=w_nolr,
bias_attr=w_nolr)
base = fluid.layers.batch_norm(base, act = "relu", param_attr=w_nolr, bias_attr=w_nolr)
base = fluid.layers.batch_norm(
base, act="relu", param_attr=w_nolr, bias_attr=w_nolr)
base = fluid.layers.concat([base, F[i]], axis=1)
base = fluid.layers.conv2d(base, num_filters=c, filter_size=1, param_attr=w_nolr, bias_attr=w_nolr)
base = fluid.layers.conv2d(base, num_filters=c, filter_size=3,padding = 1, param_attr=w_nolr, bias_attr=w_nolr)
base = fluid.layers.batch_norm(base, act = "relu", param_attr=w_nolr, bias_attr=w_nolr)
base = fluid.layers.conv2d(
base,
num_filters=c,
filter_size=1,
param_attr=w_nolr,
bias_attr=w_nolr)
base = fluid.layers.conv2d(
base,
num_filters=c,
filter_size=3,
padding=1,
param_attr=w_nolr,
bias_attr=w_nolr)
base = fluid.layers.batch_norm(
base, act="relu", param_attr=w_nolr, bias_attr=w_nolr)
base = fluid.layers.conv2d(base, num_filters=512, filter_size=1,bias_attr=w_nolr,param_attr=w_nolr)
base = fluid.layers.conv2d(
base,
num_filters=512,
filter_size=1,
bias_attr=w_nolr,
param_attr=w_nolr)
return base
@ -136,7 +165,8 @@ class ResNet():
padding=(filter_size - 1) // 2,
groups=groups,
act=None,
param_attr=ParamAttr(name=name + "_weights",trainable = Trainable),
param_attr=ParamAttr(
name=name + "_weights", trainable=Trainable),
bias_attr=False,
name=name + '.conv2d.output.1')
@ -144,11 +174,14 @@ class ResNet():
bn_name = "bn_" + name
else:
bn_name = "bn" + name[3:]
return fluid.layers.batch_norm(input=conv,
return fluid.layers.batch_norm(
input=conv,
act=act,
name=bn_name + '.output.1',
param_attr=ParamAttr(name=bn_name + '_scale',trainable = Trainable),
bias_attr=ParamAttr(bn_name + '_offset',trainable = Trainable),
param_attr=ParamAttr(
name=bn_name + '_scale', trainable=Trainable),
bias_attr=ParamAttr(
bn_name + '_offset', trainable=Trainable),
moving_mean_name=bn_name + '_mean',
moving_variance_name=bn_name + '_variance', )
@ -165,7 +198,11 @@ class ResNet():
def bottleneck_block(self, input, num_filters, stride, name):
conv0 = self.conv_bn_layer(
input=input, num_filters=num_filters, filter_size=1, act='relu', name=name + "_branch2a")
input=input,
num_filters=num_filters,
filter_size=1,
act='relu',
name=name + "_branch2a")
conv1 = self.conv_bn_layer(
input=conv0,
num_filters=num_filters,
@ -174,16 +211,36 @@ class ResNet():
act='relu',
name=name + "_branch2b")
conv2 = self.conv_bn_layer(
input=conv1, num_filters=num_filters * 4, filter_size=1, act=None, name=name + "_branch2c")
input=conv1,
num_filters=num_filters * 4,
filter_size=1,
act=None,
name=name + "_branch2c")
short = self.shortcut(input, num_filters * 4, stride, is_first=False, name=name + "_branch1")
short = self.shortcut(
input,
num_filters * 4,
stride,
is_first=False,
name=name + "_branch1")
return fluid.layers.elementwise_add(x=short, y=conv2, act='relu', name=name + ".add.output.5")
return fluid.layers.elementwise_add(
x=short, y=conv2, act='relu', name=name + ".add.output.5")
def basic_block(self, input, num_filters, stride, is_first, name):
conv0 = self.conv_bn_layer(input=input, num_filters=num_filters, filter_size=3, act='relu', stride=stride,
conv0 = self.conv_bn_layer(
input=input,
num_filters=num_filters,
filter_size=3,
act='relu',
stride=stride,
name=name + "_branch2a")
conv1 = self.conv_bn_layer(input=conv0, num_filters=num_filters, filter_size=3, act=None,
conv1 = self.conv_bn_layer(
input=conv0,
num_filters=num_filters,
filter_size=3,
act=None,
name=name + "_branch2b")
short = self.shortcut(input, num_filters, stride, is_first, name=name + "_branch1")
short = self.shortcut(
input, num_filters, stride, is_first, name=name + "_branch1")
return fluid.layers.elementwise_add(x=short, y=conv1, act='relu')