代码拉取完成，页面将自动刷新
同步操作将从 PaddlePaddle/PaddleOCR 强制同步，此操作会覆盖自 Fork 仓库以来所做的任何修改，且无法恢复！！！
确定后同步将在后台操作，完成时将刷新页面，请耐心等待。
# copyright (c) 2019 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import paddle
from paddle import nn
import paddle.nn.functional as F
from paddle import ParamAttr
import os
import sys
__dir__ = os.path.dirname(os.path.abspath(__file__))
sys.path.append(__dir__)
sys.path.insert(0, os.path.abspath(os.path.join(__dir__, '../../..')))
from ppocr.modeling.backbones.det_mobilenet_v3 import SEModule
class DSConv(nn.Layer):
def __init__(self,
in_channels,
out_channels,
kernel_size,
padding,
stride=1,
groups=None,
if_act=True,
act="relu",
**kwargs):
super(DSConv, self).__init__()
if groups == None:
groups = in_channels
self.if_act = if_act
self.act = act
self.conv1 = nn.Conv2D(
in_channels=in_channels,
out_channels=in_channels,
kernel_size=kernel_size,
stride=stride,
padding=padding,
groups=groups,
bias_attr=False)
self.bn1 = nn.BatchNorm(num_channels=in_channels, act=None)
self.conv2 = nn.Conv2D(
in_channels=in_channels,
out_channels=int(in_channels * 4),
kernel_size=1,
stride=1,
bias_attr=False)
self.bn2 = nn.BatchNorm(num_channels=int(in_channels * 4), act=None)
self.conv3 = nn.Conv2D(
in_channels=int(in_channels * 4),
out_channels=out_channels,
kernel_size=1,
stride=1,
bias_attr=False)
self._c = [in_channels, out_channels]
if in_channels != out_channels:
self.conv_end = nn.Conv2D(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=1,
stride=1,
bias_attr=False)
def forward(self, inputs):
x = self.conv1(inputs)
x = self.bn1(x)
x = self.conv2(x)
x = self.bn2(x)
if self.if_act:
if self.act == "relu":
x = F.relu(x)
elif self.act == "hardswish":
x = F.hardswish(x)
else:
print("The activation function({}) is selected incorrectly.".
format(self.act))
exit()
x = self.conv3(x)
if self._c[0] != self._c[1]:
x = x + self.conv_end(inputs)
return x
class DBFPN(nn.Layer):
def __init__(self, in_channels, out_channels, use_asf=False, **kwargs):
super(DBFPN, self).__init__()
self.out_channels = out_channels
self.use_asf = use_asf
weight_attr = paddle.nn.initializer.KaimingUniform()
self.in2_conv = nn.Conv2D(
in_channels=in_channels[0],
out_channels=self.out_channels,
kernel_size=1,
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False)
self.in3_conv = nn.Conv2D(
in_channels=in_channels[1],
out_channels=self.out_channels,
kernel_size=1,
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False)
self.in4_conv = nn.Conv2D(
in_channels=in_channels[2],
out_channels=self.out_channels,
kernel_size=1,
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False)
self.in5_conv = nn.Conv2D(
in_channels=in_channels[3],
out_channels=self.out_channels,
kernel_size=1,
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False)
self.p5_conv = nn.Conv2D(
in_channels=self.out_channels,
out_channels=self.out_channels // 4,
kernel_size=3,
padding=1,
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False)
self.p4_conv = nn.Conv2D(
in_channels=self.out_channels,
out_channels=self.out_channels // 4,
kernel_size=3,
padding=1,
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False)
self.p3_conv = nn.Conv2D(
in_channels=self.out_channels,
out_channels=self.out_channels // 4,
kernel_size=3,
padding=1,
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False)
self.p2_conv = nn.Conv2D(
in_channels=self.out_channels,
out_channels=self.out_channels // 4,
kernel_size=3,
padding=1,
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False)
if self.use_asf is True:
self.asf = ASFBlock(self.out_channels, self.out_channels // 4)
def forward(self, x):
c2, c3, c4, c5 = x
in5 = self.in5_conv(c5)
in4 = self.in4_conv(c4)
in3 = self.in3_conv(c3)
in2 = self.in2_conv(c2)
out4 = in4 + F.upsample(
in5, scale_factor=2, mode="nearest", align_mode=1) # 1/16
out3 = in3 + F.upsample(
out4, scale_factor=2, mode="nearest", align_mode=1) # 1/8
out2 = in2 + F.upsample(
out3, scale_factor=2, mode="nearest", align_mode=1) # 1/4
p5 = self.p5_conv(in5)
p4 = self.p4_conv(out4)
p3 = self.p3_conv(out3)
p2 = self.p2_conv(out2)
p5 = F.upsample(p5, scale_factor=8, mode="nearest", align_mode=1)
p4 = F.upsample(p4, scale_factor=4, mode="nearest", align_mode=1)
p3 = F.upsample(p3, scale_factor=2, mode="nearest", align_mode=1)
fuse = paddle.concat([p5, p4, p3, p2], axis=1)
if self.use_asf is True:
fuse = self.asf(fuse, [p5, p4, p3, p2])
return fuse
class RSELayer(nn.Layer):
def __init__(self, in_channels, out_channels, kernel_size, shortcut=True):
super(RSELayer, self).__init__()
weight_attr = paddle.nn.initializer.KaimingUniform()
self.out_channels = out_channels
self.in_conv = nn.Conv2D(
in_channels=in_channels,
out_channels=self.out_channels,
kernel_size=kernel_size,
padding=int(kernel_size // 2),
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False)
self.se_block = SEModule(self.out_channels)
self.shortcut = shortcut
def forward(self, ins):
x = self.in_conv(ins)
if self.shortcut:
out = x + self.se_block(x)
else:
out = self.se_block(x)
return out
class RSEFPN(nn.Layer):
def __init__(self, in_channels, out_channels, shortcut=True, **kwargs):
super(RSEFPN, self).__init__()
self.out_channels = out_channels
self.ins_conv = nn.LayerList()
self.inp_conv = nn.LayerList()
for i in range(len(in_channels)):
self.ins_conv.append(
RSELayer(
in_channels[i],
out_channels,
kernel_size=1,
shortcut=shortcut))
self.inp_conv.append(
RSELayer(
out_channels,
out_channels // 4,
kernel_size=3,
shortcut=shortcut))
def forward(self, x):
c2, c3, c4, c5 = x
in5 = self.ins_conv[3](c5)
in4 = self.ins_conv[2](c4)
in3 = self.ins_conv[1](c3)
in2 = self.ins_conv[0](c2)
out4 = in4 + F.upsample(
in5, scale_factor=2, mode="nearest", align_mode=1) # 1/16
out3 = in3 + F.upsample(
out4, scale_factor=2, mode="nearest", align_mode=1) # 1/8
out2 = in2 + F.upsample(
out3, scale_factor=2, mode="nearest", align_mode=1) # 1/4
p5 = self.inp_conv[3](in5)
p4 = self.inp_conv[2](out4)
p3 = self.inp_conv[1](out3)
p2 = self.inp_conv[0](out2)
p5 = F.upsample(p5, scale_factor=8, mode="nearest", align_mode=1)
p4 = F.upsample(p4, scale_factor=4, mode="nearest", align_mode=1)
p3 = F.upsample(p3, scale_factor=2, mode="nearest", align_mode=1)
fuse = paddle.concat([p5, p4, p3, p2], axis=1)
return fuse
class LKPAN(nn.Layer):
def __init__(self, in_channels, out_channels, mode='large', **kwargs):
super(LKPAN, self).__init__()
self.out_channels = out_channels
weight_attr = paddle.nn.initializer.KaimingUniform()
self.ins_conv = nn.LayerList()
self.inp_conv = nn.LayerList()
# pan head
self.pan_head_conv = nn.LayerList()
self.pan_lat_conv = nn.LayerList()
if mode.lower() == 'lite':
p_layer = DSConv
elif mode.lower() == 'large':
p_layer = nn.Conv2D
else:
raise ValueError(
"mode can only be one of ['lite', 'large'], but received {}".
format(mode))
for i in range(len(in_channels)):
self.ins_conv.append(
nn.Conv2D(
in_channels=in_channels[i],
out_channels=self.out_channels,
kernel_size=1,
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False))
self.inp_conv.append(
p_layer(
in_channels=self.out_channels,
out_channels=self.out_channels // 4,
kernel_size=9,
padding=4,
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False))
if i > 0:
self.pan_head_conv.append(
nn.Conv2D(
in_channels=self.out_channels // 4,
out_channels=self.out_channels // 4,
kernel_size=3,
padding=1,
stride=2,
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False))
self.pan_lat_conv.append(
p_layer(
in_channels=self.out_channels // 4,
out_channels=self.out_channels // 4,
kernel_size=9,
padding=4,
weight_attr=ParamAttr(initializer=weight_attr),
bias_attr=False))
def forward(self, x):
c2, c3, c4, c5 = x
in5 = self.ins_conv[3](c5)
in4 = self.ins_conv[2](c4)
in3 = self.ins_conv[1](c3)
in2 = self.ins_conv[0](c2)
out4 = in4 + F.upsample(
in5, scale_factor=2, mode="nearest", align_mode=1) # 1/16
out3 = in3 + F.upsample(
out4, scale_factor=2, mode="nearest", align_mode=1) # 1/8
out2 = in2 + F.upsample(
out3, scale_factor=2, mode="nearest", align_mode=1) # 1/4
f5 = self.inp_conv[3](in5)
f4 = self.inp_conv[2](out4)
f3 = self.inp_conv[1](out3)
f2 = self.inp_conv[0](out2)
pan3 = f3 + self.pan_head_conv[0](f2)
pan4 = f4 + self.pan_head_conv[1](pan3)
pan5 = f5 + self.pan_head_conv[2](pan4)
p2 = self.pan_lat_conv[0](f2)
p3 = self.pan_lat_conv[1](pan3)
p4 = self.pan_lat_conv[2](pan4)
p5 = self.pan_lat_conv[3](pan5)
p5 = F.upsample(p5, scale_factor=8, mode="nearest", align_mode=1)
p4 = F.upsample(p4, scale_factor=4, mode="nearest", align_mode=1)
p3 = F.upsample(p3, scale_factor=2, mode="nearest", align_mode=1)
fuse = paddle.concat([p5, p4, p3, p2], axis=1)
return fuse
class ASFBlock(nn.Layer):
"""
This code is refered from:
https://github.com/MhLiao/DB/blob/master/decoders/feature_attention.py
"""
def __init__(self, in_channels, inter_channels, out_features_num=4):
"""
Adaptive Scale Fusion (ASF) block of DBNet++
Args:
in_channels: the number of channels in the input data
inter_channels: the number of middle channels
out_features_num: the number of fused stages
"""
super(ASFBlock, self).__init__()
weight_attr = paddle.nn.initializer.KaimingUniform()
self.in_channels = in_channels
self.inter_channels = inter_channels
self.out_features_num = out_features_num
self.conv = nn.Conv2D(in_channels, inter_channels, 3, padding=1)
self.spatial_scale = nn.Sequential(
#Nx1xHxW
nn.Conv2D(
in_channels=1,
out_channels=1,
kernel_size=3,
bias_attr=False,
padding=1,
weight_attr=ParamAttr(initializer=weight_attr)),
nn.ReLU(),
nn.Conv2D(
in_channels=1,
out_channels=1,
kernel_size=1,
bias_attr=False,
weight_attr=ParamAttr(initializer=weight_attr)),
nn.Sigmoid())
self.channel_scale = nn.Sequential(
nn.Conv2D(
in_channels=inter_channels,
out_channels=out_features_num,
kernel_size=1,
bias_attr=False,
weight_attr=ParamAttr(initializer=weight_attr)),
nn.Sigmoid())
def forward(self, fuse_features, features_list):
fuse_features = self.conv(fuse_features)
spatial_x = paddle.mean(fuse_features, axis=1, keepdim=True)
attention_scores = self.spatial_scale(spatial_x) + fuse_features
attention_scores = self.channel_scale(attention_scores)
assert len(features_list) == self.out_features_num
out_list = []
for i in range(self.out_features_num):
out_list.append(attention_scores[:, i:i + 1] * features_list[i])
return paddle.concat(out_list, axis=1)
此处可能存在不合适展示的内容，页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容，可点击提交进行申诉，我们将尽快为您处理。
