mirrors/PaddleOCR
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/PaddleOCR.git synced 2025-06-03 21:53:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

添加resnet backbone

Browse Source
This commit is contained in:
WenmuZhou 2020-11-09 18:29:33 +08:00
parent 4d775dc98f
commit b2004fe586
2 changed files with 17 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
ppocr/modeling/backbones/det_resnet_vd.py
View File

@ -19,6 +19,7 @@ from __future__ import print_function
import paddle import paddle
from paddle import ParamAttr from paddle import ParamAttr
import paddle.nn as nn import paddle.nn as nn
import paddle.nn.functional as F
__all__ = ["ResNet"] __all__ = ["ResNet"]
@ -37,9 +38,9 @@ class ConvBNLayer(nn.Layer):
super(ConvBNLayer, self).__init__() super(ConvBNLayer, self).__init__()
self.is_vd_mode = is_vd_mode self.is_vd_mode = is_vd_mode
self._pool2d_avg = nn.AvgPool2d( self._pool2d_avg = nn.AvgPool2D(
kernel_size=2, stride=2, padding=0, ceil_mode=True) kernel_size=2, stride=2, padding=0, ceil_mode=True)
self._conv = nn.Conv2d( self._conv = nn.Conv2D(
in_channels=in_channels, in_channels=in_channels,
out_channels=out_channels, out_channels=out_channels,
kernel_size=kernel_size, kernel_size=kernel_size,
@ -118,7 +119,8 @@ class BottleneckBlock(nn.Layer):
short = inputs short = inputs
else: else:
short = self.short(inputs) short = self.short(inputs)
y = paddle.elementwise_add(x=short, y=conv2, act='relu') y = paddle.add(x=short, y=conv2)
y = F.relu(y)
return y return y
@ -165,7 +167,8 @@ class BasicBlock(nn.Layer):
short = inputs short = inputs
else: else:
short = self.short(inputs) short = self.short(inputs)
y = paddle.elementwise_add(x=short, y=conv1, act='relu') y = paddle.add(x=short, y=conv1)
y = F.relu(y)
return y return y
@ -214,7 +217,7 @@ class ResNet(nn.Layer):
stride=1, stride=1,
act='relu', act='relu',
name="conv1_3") name="conv1_3")
self.pool2d_max = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.pool2d_max = nn.MaxPool2D(kernel_size=3, stride=2, padding=1)
self.stages = [] self.stages = []
self.out_channels = [] self.out_channels = []

15
ppocr/modeling/backbones/rec_resnet_vd.py
View File

@ -19,6 +19,7 @@ from __future__ import print_function
import paddle import paddle
from paddle import ParamAttr from paddle import ParamAttr
import paddle.nn as nn import paddle.nn as nn
import paddle.nn.functional as F
__all__ = ["ResNet"] __all__ = ["ResNet"]
@ -37,9 +38,9 @@ class ConvBNLayer(nn.Layer):
super(ConvBNLayer, self).__init__() super(ConvBNLayer, self).__init__()
self.is_vd_mode = is_vd_mode self.is_vd_mode = is_vd_mode
self._pool2d_avg = nn.AvgPool2d( self._pool2d_avg = nn.AvgPool2D(
kernel_size=stride, stride=stride, padding=0, ceil_mode=True) kernel_size=stride, stride=stride, padding=0, ceil_mode=True)
self._conv = nn.Conv2d( self._conv = nn.Conv2D(
in_channels=in_channels, in_channels=in_channels,
out_channels=out_channels, out_channels=out_channels,
kernel_size=kernel_size, kernel_size=kernel_size,
@ -119,7 +120,8 @@ class BottleneckBlock(nn.Layer):
short = inputs short = inputs
else: else:
short = self.short(inputs) short = self.short(inputs)
y = paddle.elementwise_add(x=short, y=conv2, act='relu') y = paddle.add(x=short, y=conv2)
y = F.relu(y)
return y return y
@ -166,7 +168,8 @@ class BasicBlock(nn.Layer):
short = inputs short = inputs
else: else:
short = self.short(inputs) short = self.short(inputs)
y = paddle.elementwise_add(x=short, y=conv1, act='relu') y = paddle.add(x=short, y=conv1)
y = F.relu(y)
return y return y
@ -215,7 +218,7 @@ class ResNet(nn.Layer):
stride=1, stride=1,
act='relu', act='relu',
name="conv1_3") name="conv1_3")
self.pool2d_max = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.pool2d_max = nn.MaxPool2D(kernel_size=3, stride=2, padding=1)
self.block_list = [] self.block_list = []
if layers >= 50: if layers >= 50:
@ -270,7 +273,7 @@ class ResNet(nn.Layer):
shortcut = True shortcut = True
self.block_list.append(basic_block) self.block_list.append(basic_block)
self.out_channels = num_filters[block] self.out_channels = num_filters[block]
self.out_pool = nn.MaxPool2d(kernel_size=2, stride=2, padding=0) self.out_pool = nn.MaxPool2D(kernel_size=2, stride=2, padding=0)
def forward(self, inputs): def forward(self, inputs):
y = self.conv1_1(inputs) y = self.conv1_1(inputs)