pyxllib 0.3.96__py3-none-any.whl → 0.3.197__py3-none-any.whl

pyxlpr/ppocr/modeling/architectures/base_model.py

@@ -1,88 +0,0 @@
-# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
-#
-# 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
-from paddle import nn
-from pyxlpr.ppocr.modeling.transforms import build_transform
-from pyxlpr.ppocr.modeling.backbones import build_backbone
-from pyxlpr.ppocr.modeling.necks import build_neck
-from pyxlpr.ppocr.modeling.heads import build_head
-
-__all__ = ['BaseModel']
-
-
-class BaseModel(nn.Layer):
-    def __init__(self, config):
-        """
-        the module for OCR.
-        args:
-            config (dict): the super parameters for module.
-        """
-        super(BaseModel, self).__init__()
-        in_channels = config.get('in_channels', 3)
-        model_type = config['model_type']
-        # build transfrom,
-        # for rec, transfrom can be TPS,None
-        # for det and cls, transfrom should be None,
-        # if you make model differently, you can use transfrom in det and cls
-        if 'Transform' not in config or config['Transform'] is None:
-            self.use_transform = False
-        else:
-            self.use_transform = True
-            config['Transform']['in_channels'] = in_channels
-            self.transform = build_transform(config['Transform'])
-            in_channels = self.transform.out_channels
-
-        # build backbone, backbone is needed for det, rec and cls
-        config["Backbone"]['in_channels'] = in_channels
-        self.backbone = build_backbone(config["Backbone"], model_type)
-        in_channels = self.backbone.out_channels
-
-        # build neck
-        # for rec, neck can be cnn,rnn or reshape(None)
-        # for det, neck can be FPN, BIFPN and so on.
-        # for cls, neck should be none
-        if 'Neck' not in config or config['Neck'] is None:
-            self.use_neck = False
-        else:
-            self.use_neck = True
-            config['Neck']['in_channels'] = in_channels
-            self.neck = build_neck(config['Neck'])
-            in_channels = self.neck.out_channels
-
-        # # build head, head is needed for det, rec and cls
-        config["Head"]['in_channels'] = in_channels
-        self.head = build_head(config["Head"])
-
-        self.return_all_feats = config.get("return_all_feats", False)
-
-    def forward(self, x, data=None):
-        y = dict()
-        if self.use_transform:
-            x = self.transform(x)
-        x = self.backbone(x)
-        y["backbone_out"] = x
-        if self.use_neck:
-            x = self.neck(x)
-        y["neck_out"] = x
-        x = self.head(x, targets=data)
-        if isinstance(x, dict):
-            y.update(x)
-        else:
-            y["head_out"] = x
-        if self.return_all_feats:
-            return y
-        else:
-            return x

pyxlpr/ppocr/modeling/architectures/distillation_model.py

@@ -1,60 +0,0 @@
-# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
-#
-# 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
-
-from paddle import nn
-from pyxlpr.ppocr.modeling.transforms import build_transform
-from pyxlpr.ppocr.modeling.backbones import build_backbone
-from pyxlpr.ppocr.modeling.necks import build_neck
-from pyxlpr.ppocr.modeling.heads import build_head
-from .base_model import BaseModel
-from pyxlpr.ppocr.utils.save_load import load_pretrained_params
-
-__all__ = ['DistillationModel']
-
-
-class DistillationModel(nn.Layer):
-    def __init__(self, config):
-        """
-        the module for OCR distillation.
-        args:
-            config (dict): the super parameters for module.
-        """
-        super().__init__()
-        self.model_list = []
-        self.model_name_list = []
-        for key in config["Models"]:
-            model_config = config["Models"][key]
-            freeze_params = False
-            pretrained = None
-            if "freeze_params" in model_config:
-                freeze_params = model_config.pop("freeze_params")
-            if "pretrained" in model_config:
-                pretrained = model_config.pop("pretrained")
-            model = BaseModel(model_config)
-            if pretrained is not None:
-                load_pretrained_params(model, pretrained)
-            if freeze_params:
-                for param in model.parameters():
-                    param.trainable = False
-            self.model_list.append(self.add_sublayer(key, model))
-            self.model_name_list.append(key)
-
-    def forward(self, x):
-        result_dict = dict()
-        for idx, model_name in enumerate(self.model_name_list):
-            result_dict[model_name] = self.model_list[idx](x)
-        return result_dict

pyxlpr/ppocr/modeling/backbones/__init__.py

@@ -1,54 +0,0 @@
-# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
-#
-# 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.
-
-__all__ = ["build_backbone"]
-
-
-def build_backbone(config, model_type):
-    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
-        support_dict = ["MobileNetV3", "ResNet", "ResNet_SAST"]
-    elif model_type == "rec" or model_type == "cls":
-        from .rec_mobilenet_v3 import MobileNetV3
-        from .rec_resnet_vd import ResNet
-        from .rec_resnet_fpn import ResNetFPN
-        from .rec_mv1_enhance import MobileNetV1Enhance
-        from .rec_nrtr_mtb import MTB
-        from .rec_resnet_31 import ResNet31
-        from .rec_resnet_aster import ResNet_ASTER
-        support_dict = [
-            'MobileNetV1Enhance', 'MobileNetV3', 'ResNet', 'ResNetFPN', 'MTB',
-            "ResNet31", "ResNet_ASTER"
-        ]
-    elif model_type == "e2e":
-        from .e2e_resnet_vd_pg import ResNet
-        support_dict = ['ResNet']
-    elif model_type == 'kie':
-        from .kie_unet_sdmgr import Kie_backbone
-        support_dict = ['Kie_backbone']
-    elif model_type == "table":
-        from .table_resnet_vd import ResNet
-        from .table_mobilenet_v3 import MobileNetV3
-        support_dict = ["ResNet", "MobileNetV3"]
-    else:
-        raise NotImplementedError
-
-    module_name = config.pop("name")
-    assert module_name in support_dict, Exception(
-        "when model typs is {}, backbone only support {}".format(model_type,
-                                                                 support_dict))
-    module_class = eval(module_name)(**config)
-    return module_class

pyxlpr/ppocr/modeling/backbones/det_mobilenet_v3.py

@@ -1,268 +0,0 @@
-# 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')
-
-        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))
-            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'))
-        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):
-        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,
-            bias_attr=False)
-
-        self.bn = nn.BatchNorm(num_channels=out_channels, act=None)
-
-    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):
-        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)
-        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)
-        if self.if_se:
-            self.mid_se = SEModule(mid_channels)
-        self.linear_conv = ConvBNLayer(
-            in_channels=mid_channels,
-            out_channels=out_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0,
-            if_act=False,
-            act=None)
-
-    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):
-        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)
-        self.conv2 = nn.Conv2D(
-            in_channels=in_channels // reduction,
-            out_channels=in_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0)
-
-    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