del table backbone (#4802)

ppocr/modeling/backbones/__init__.py

@@ -16,7 +16,7 @@ __all__ = ["build_backbone"]
 
 
 def build_backbone(config, model_type):
-    if model_type == "det":
+    if model_type == "det" or model_type == "table":
         from .det_mobilenet_v3 import MobileNetV3
         from .det_resnet_vd import ResNet
         from .det_resnet_vd_sast import ResNet_SAST
@@ -36,10 +36,6 @@ def build_backbone(config, model_type):
     elif model_type == "e2e":
         from .e2e_resnet_vd_pg import ResNet
         support_dict = ["ResNet"]
-    elif model_type == "table":
-        from .table_resnet_vd import ResNet
-        from .table_mobilenet_v3 import MobileNetV3
-        support_dict = ["ResNet", "MobileNetV3"]
     else:
         raise NotImplementedError
 

ppocr/modeling/backbones/table_mobilenet_v3.py

-# copyright (c) 2020 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
-
-__all__ = ['MobileNetV3']
-
-
-def make_divisible(v, divisor=8, min_value=None):
-    if min_value is None:
-        min_value = divisor
-    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
-    if new_v < 0.9 * v:
-        new_v += divisor
-    return new_v
-
-
-class MobileNetV3(nn.Layer):
-    def __init__(self,
-                 in_channels=3,
-                 model_name='large',
-                 scale=0.5,
-                 disable_se=False,
-                 **kwargs):
-        """
-        the MobilenetV3 backbone network for detection module.
-        Args:
-            params(dict): the super parameters for build network
-        """
-        super(MobileNetV3, self).__init__()
-
-        self.disable_se = disable_se
-
-        if model_name == "large":
-            cfg = [
-                # k, exp, c,  se,     nl,  s,
-                [3, 16, 16, False, 'relu', 1],
-                [3, 64, 24, False, 'relu', 2],
-                [3, 72, 24, False, 'relu', 1],
-                [5, 72, 40, True, 'relu', 2],
-                [5, 120, 40, True, 'relu', 1],
-                [5, 120, 40, True, 'relu', 1],
-                [3, 240, 80, False, 'hardswish', 2],
-                [3, 200, 80, False, 'hardswish', 1],
-                [3, 184, 80, False, 'hardswish', 1],
-                [3, 184, 80, False, 'hardswish', 1],
-                [3, 480, 112, True, 'hardswish', 1],
-                [3, 672, 112, True, 'hardswish', 1],
-                [5, 672, 160, True, 'hardswish', 2],
-                [5, 960, 160, True, 'hardswish', 1],
-                [5, 960, 160, True, 'hardswish', 1],
-            ]
-            cls_ch_squeeze = 960
-        elif model_name == "small":
-            cfg = [
-                # k, exp, c,  se,     nl,  s,
-                [3, 16, 16, True, 'relu', 2],
-                [3, 72, 24, False, 'relu', 2],
-                [3, 88, 24, False, 'relu', 1],
-                [5, 96, 40, True, 'hardswish', 2],
-                [5, 240, 40, True, 'hardswish', 1],
-                [5, 240, 40, True, 'hardswish', 1],
-                [5, 120, 48, True, 'hardswish', 1],
-                [5, 144, 48, True, 'hardswish', 1],
-                [5, 288, 96, True, 'hardswish', 2],
-                [5, 576, 96, True, 'hardswish', 1],
-                [5, 576, 96, True, 'hardswish', 1],
-            ]
-            cls_ch_squeeze = 576
-        else:
-            raise NotImplementedError("mode[" + model_name +
-                                      "_model] is not implemented!")
-
-        supported_scale = [0.35, 0.5, 0.75, 1.0, 1.25]
-        assert scale in supported_scale, \
-            "supported scale are {} but input scale is {}".format(supported_scale, scale)
-        inplanes = 16
-        # conv1
-        self.conv = ConvBNLayer(
-            in_channels=in_channels,
-            out_channels=make_divisible(inplanes * scale),
-            kernel_size=3,
-            stride=2,
-            padding=1,
-            groups=1,
-            if_act=True,
-            act='hardswish',
-            name='conv1')
-
-        self.stages = []
-        self.out_channels = []
-        block_list = []
-        i = 0
-        inplanes = make_divisible(inplanes * scale)
-        for (k, exp, c, se, nl, s) in cfg:
-            se = se and not self.disable_se
-            start_idx = 2 if model_name == 'large' else 0
-            if s == 2 and i > start_idx:
-                self.out_channels.append(inplanes)
-                self.stages.append(nn.Sequential(*block_list))
-                block_list = []
-            block_list.append(
-                ResidualUnit(
-                    in_channels=inplanes,
-                    mid_channels=make_divisible(scale * exp),
-                    out_channels=make_divisible(scale * c),
-                    kernel_size=k,
-                    stride=s,
-                    use_se=se,
-                    act=nl,
-                    name="conv" + str(i + 2)))
-            inplanes = make_divisible(scale * c)
-            i += 1
-        block_list.append(
-            ConvBNLayer(
-                in_channels=inplanes,
-                out_channels=make_divisible(scale * cls_ch_squeeze),
-                kernel_size=1,
-                stride=1,
-                padding=0,
-                groups=1,
-                if_act=True,
-                act='hardswish',
-                name='conv_last'))
-        self.stages.append(nn.Sequential(*block_list))
-        self.out_channels.append(make_divisible(scale * cls_ch_squeeze))
-        for i, stage in enumerate(self.stages):
-            self.add_sublayer(sublayer=stage, name="stage{}".format(i))
-
-    def forward(self, x):
-        x = self.conv(x)
-        out_list = []
-        for stage in self.stages:
-            x = stage(x)
-            out_list.append(x)
-        return out_list
-
-
-class ConvBNLayer(nn.Layer):
-    def __init__(self,
-                 in_channels,
-                 out_channels,
-                 kernel_size,
-                 stride,
-                 padding,
-                 groups=1,
-                 if_act=True,
-                 act=None,
-                 name=None):
-        super(ConvBNLayer, self).__init__()
-        self.if_act = if_act
-        self.act = act
-        self.conv = nn.Conv2D(
-            in_channels=in_channels,
-            out_channels=out_channels,
-            kernel_size=kernel_size,
-            stride=stride,
-            padding=padding,
-            groups=groups,
-            weight_attr=ParamAttr(name=name + '_weights'),
-            bias_attr=False)
-
-        self.bn = nn.BatchNorm(
-            num_channels=out_channels,
-            act=None,
-            param_attr=ParamAttr(name=name + "_bn_scale"),
-            bias_attr=ParamAttr(name=name + "_bn_offset"),
-            moving_mean_name=name + "_bn_mean",
-            moving_variance_name=name + "_bn_variance")
-
-    def forward(self, x):
-        x = self.conv(x)
-        x = self.bn(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()
-        return x
-
-
-class ResidualUnit(nn.Layer):
-    def __init__(self,
-                 in_channels,
-                 mid_channels,
-                 out_channels,
-                 kernel_size,
-                 stride,
-                 use_se,
-                 act=None,
-                 name=''):
-        super(ResidualUnit, self).__init__()
-        self.if_shortcut = stride == 1 and in_channels == out_channels
-        self.if_se = use_se
-
-        self.expand_conv = ConvBNLayer(
-            in_channels=in_channels,
-            out_channels=mid_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0,
-            if_act=True,
-            act=act,
-            name=name + "_expand")
-        self.bottleneck_conv = ConvBNLayer(
-            in_channels=mid_channels,
-            out_channels=mid_channels,
-            kernel_size=kernel_size,
-            stride=stride,
-            padding=int((kernel_size - 1) // 2),
-            groups=mid_channels,
-            if_act=True,
-            act=act,
-            name=name + "_depthwise")
-        if self.if_se:
-            self.mid_se = SEModule(mid_channels, name=name + "_se")
-        self.linear_conv = ConvBNLayer(
-            in_channels=mid_channels,
-            out_channels=out_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0,
-            if_act=False,
-            act=None,
-            name=name + "_linear")
-
-    def forward(self, inputs):
-        x = self.expand_conv(inputs)
-        x = self.bottleneck_conv(x)
-        if self.if_se:
-            x = self.mid_se(x)
-        x = self.linear_conv(x)
-        if self.if_shortcut:
-            x = paddle.add(inputs, x)
-        return x
-
-
-class SEModule(nn.Layer):
-    def __init__(self, in_channels, reduction=4, name=""):
-        super(SEModule, self).__init__()
-        self.avg_pool = nn.AdaptiveAvgPool2D(1)
-        self.conv1 = nn.Conv2D(
-            in_channels=in_channels,
-            out_channels=in_channels // reduction,
-            kernel_size=1,
-            stride=1,
-            padding=0,
-            weight_attr=ParamAttr(name=name + "_1_weights"),
-            bias_attr=ParamAttr(name=name + "_1_offset"))
-        self.conv2 = nn.Conv2D(
-            in_channels=in_channels // reduction,
-            out_channels=in_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0,
-            weight_attr=ParamAttr(name + "_2_weights"),
-            bias_attr=ParamAttr(name=name + "_2_offset"))
-
-    def forward(self, inputs):
-        outputs = self.avg_pool(inputs)
-        outputs = self.conv1(outputs)
-        outputs = F.relu(outputs)
-        outputs = self.conv2(outputs)
-        outputs = F.hardsigmoid(outputs, slope=0.2, offset=0.5)
-        return inputs * outputs
\ No newline at end of file

ppocr/modeling/backbones/table_resnet_vd.py

-# copyright (c) 2020 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 ParamAttr
-import paddle.nn as nn
-import paddle.nn.functional as F
-
-__all__ = ["ResNet"]
-
-
-class ConvBNLayer(nn.Layer):
-    def __init__(
-            self,
-            in_channels,
-            out_channels,
-            kernel_size,
-            stride=1,
-            groups=1,
-            is_vd_mode=False,
-            act=None,
-            name=None, ):
-        super(ConvBNLayer, self).__init__()
-
-        self.is_vd_mode = is_vd_mode
-        self._pool2d_avg = nn.AvgPool2D(
-            kernel_size=2, stride=2, padding=0, ceil_mode=True)
-        self._conv = nn.Conv2D(
-            in_channels=in_channels,
-            out_channels=out_channels,
-            kernel_size=kernel_size,
-            stride=stride,
-            padding=(kernel_size - 1) // 2,
-            groups=groups,
-            weight_attr=ParamAttr(name=name + "_weights"),
-            bias_attr=False)
-        if name == "conv1":
-            bn_name = "bn_" + name
-        else:
-            bn_name = "bn" + name[3:]
-        self._batch_norm = nn.BatchNorm(
-            out_channels,
-            act=act,
-            param_attr=ParamAttr(name=bn_name + '_scale'),
-            bias_attr=ParamAttr(bn_name + '_offset'),
-            moving_mean_name=bn_name + '_mean',
-            moving_variance_name=bn_name + '_variance')
-
-    def forward(self, inputs):
-        if self.is_vd_mode:
-            inputs = self._pool2d_avg(inputs)
-        y = self._conv(inputs)
-        y = self._batch_norm(y)
-        return y
-
-
-class BottleneckBlock(nn.Layer):
-    def __init__(self,
-                 in_channels,
-                 out_channels,
-                 stride,
-                 shortcut=True,
-                 if_first=False,
-                 name=None):
-        super(BottleneckBlock, self).__init__()
-
-        self.conv0 = ConvBNLayer(
-            in_channels=in_channels,
-            out_channels=out_channels,
-            kernel_size=1,
-            act='relu',
-            name=name + "_branch2a")
-        self.conv1 = ConvBNLayer(
-            in_channels=out_channels,
-            out_channels=out_channels,
-            kernel_size=3,
-            stride=stride,
-            act='relu',
-            name=name + "_branch2b")
-        self.conv2 = ConvBNLayer(
-            in_channels=out_channels,
-            out_channels=out_channels * 4,
-            kernel_size=1,
-            act=None,
-            name=name + "_branch2c")
-
-        if not shortcut:
-            self.short = ConvBNLayer(
-                in_channels=in_channels,
-                out_channels=out_channels * 4,
-                kernel_size=1,
-                stride=1,
-                is_vd_mode=False if if_first else True,
-                name=name + "_branch1")
-
-        self.shortcut = shortcut
-
-    def forward(self, inputs):
-        y = self.conv0(inputs)
-        conv1 = self.conv1(y)
-        conv2 = self.conv2(conv1)
-
-        if self.shortcut:
-            short = inputs
-        else:
-            short = self.short(inputs)
-        y = paddle.add(x=short, y=conv2)
-        y = F.relu(y)
-        return y
-
-
-class BasicBlock(nn.Layer):
-    def __init__(self,
-                 in_channels,
-                 out_channels,
-                 stride,
-                 shortcut=True,
-                 if_first=False,
-                 name=None):
-        super(BasicBlock, self).__init__()
-        self.stride = stride
-        self.conv0 = ConvBNLayer(
-            in_channels=in_channels,
-            out_channels=out_channels,
-            kernel_size=3,
-            stride=stride,
-            act='relu',
-            name=name + "_branch2a")
-        self.conv1 = ConvBNLayer(
-            in_channels=out_channels,
-            out_channels=out_channels,
-            kernel_size=3,
-            act=None,
-            name=name + "_branch2b")
-
-        if not shortcut:
-            self.short = ConvBNLayer(
-                in_channels=in_channels,
-                out_channels=out_channels,
-                kernel_size=1,
-                stride=1,
-                is_vd_mode=False if if_first else True,
-                name=name + "_branch1")
-
-        self.shortcut = shortcut
-
-    def forward(self, inputs):
-        y = self.conv0(inputs)
-        conv1 = self.conv1(y)
-
-        if self.shortcut:
-            short = inputs
-        else:
-            short = self.short(inputs)
-        y = paddle.add(x=short, y=conv1)
-        y = F.relu(y)
-        return y
-
-
-class ResNet(nn.Layer):
-    def __init__(self, in_channels=3, layers=50, **kwargs):
-        super(ResNet, self).__init__()
-        
-        self.layers = layers
-        supported_layers = [18, 34, 50, 101, 152, 200]
-        assert layers in supported_layers, \
-            "supported layers are {} but input layer is {}".format(
-                supported_layers, layers)
-
-        if layers == 18:
-            depth = [2, 2, 2, 2]
-        elif layers == 34 or layers == 50:
-            depth = [3, 4, 6, 3]
-        elif layers == 101:
-            depth = [3, 4, 23, 3]
-        elif layers == 152:
-            depth = [3, 8, 36, 3]
-        elif layers == 200:
-            depth = [3, 12, 48, 3]
-        num_channels = [64, 256, 512,
-                        1024] if layers >= 50 else [64, 64, 128, 256]
-        num_filters = [64, 128, 256, 512]
-
-        self.conv1_1 = ConvBNLayer(
-            in_channels=in_channels,
-            out_channels=32,
-            kernel_size=3,
-            stride=2,
-            act='relu',
-            name="conv1_1")
-        self.conv1_2 = ConvBNLayer(
-            in_channels=32,
-            out_channels=32,
-            kernel_size=3,
-            stride=1,
-            act='relu',
-            name="conv1_2")
-        self.conv1_3 = ConvBNLayer(
-            in_channels=32,
-            out_channels=64,
-            kernel_size=3,
-            stride=1,
-            act='relu',
-            name="conv1_3")
-        self.pool2d_max = nn.MaxPool2D(kernel_size=3, stride=2, padding=1)
-
-        self.stages = []
-        self.out_channels = []
-        if layers >= 50:
-            for block in range(len(depth)):
-                block_list = []
-                shortcut = False
-                for i in range(depth[block]):
-                    if layers in [101, 152] and block == 2:
-                        if i == 0:
-                            conv_name = "res" + str(block + 2) + "a"
-                        else:
-                            conv_name = "res" + str(block + 2) + "b" + str(i)
-                    else:
-                        conv_name = "res" + str(block + 2) + chr(97 + i)
-                    bottleneck_block = self.add_sublayer(
-                        'bb_%d_%d' % (block, i),
-                        BottleneckBlock(
-                            in_channels=num_channels[block]
-                            if i == 0 else num_filters[block] * 4,
-                            out_channels=num_filters[block],
-                            stride=2 if i == 0 and block != 0 else 1,
-                            shortcut=shortcut,
-                            if_first=block == i == 0,
-                            name=conv_name))
-                    shortcut = True
-                    block_list.append(bottleneck_block)
-                self.out_channels.append(num_filters[block] * 4)
-                self.stages.append(nn.Sequential(*block_list))
-        else:
-            for block in range(len(depth)):
-                block_list = []
-                shortcut = False
-                for i in range(depth[block]):
-                    conv_name = "res" + str(block + 2) + chr(97 + i)
-                    basic_block = self.add_sublayer(
-                        'bb_%d_%d' % (block, i),
-                        BasicBlock(
-                            in_channels=num_channels[block]
-                            if i == 0 else num_filters[block],
-                            out_channels=num_filters[block],
-                            stride=2 if i == 0 and block != 0 else 1,
-                            shortcut=shortcut,
-                            if_first=block == i == 0,
-                            name=conv_name))
-                    shortcut = True
-                    block_list.append(basic_block)
-                self.out_channels.append(num_filters[block])
-                self.stages.append(nn.Sequential(*block_list))
-
-    def forward(self, inputs):
-        y = self.conv1_1(inputs)
-        y = self.conv1_2(y)
-        y = self.conv1_3(y)
-        y = self.pool2d_max(y)
-        out = []
-        for block in self.stages:
-            y = block(y)
-            out.append(y)
-        return out