Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into dygraph

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/rec_mobilenet_v3.py

@@ -26,8 +26,10 @@ class MobileNetV3(nn.Layer):
                  scale=0.5,
                  large_stride=None,
                  small_stride=None,
+                 disable_se=False,
                  **kwargs):
         super(MobileNetV3, self).__init__()
+        self.disable_se = disable_se
         if small_stride is None:
             small_stride = [2, 2, 2, 2]
         if large_stride is None:
@@ -101,6 +103,7 @@ class MobileNetV3(nn.Layer):
         block_list = []
         inplanes = make_divisible(inplanes * scale)
         for (k, exp, c, se, nl, s) in cfg:
+            se = se and not self.disable_se
             block_list.append(
                 ResidualUnit(
                     in_channels=inplanes,

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

ppocr/modeling/heads/rec_att_head.py

@@ -53,7 +53,6 @@ class AttentionHead(nn.Layer):
                 output_hiddens.append(paddle.unsqueeze(outputs, axis=1))
             output = paddle.concat(output_hiddens, axis=1)
             probs = self.generator(output)
-
         else:
             targets = paddle.zeros(shape=[batch_size], dtype="int32")
             probs = None
@@ -75,6 +74,7 @@ class AttentionHead(nn.Layer):
                             probs_step, axis=1)], axis=1)
                 next_input = probs_step.argmax(axis=1)
                 targets = next_input
+        if not self.training:
             probs = paddle.nn.functional.softmax(probs, axis=2)
         return probs
 

ppocr/modeling/transforms/tps_spatial_transformer.py

@@ -53,7 +53,7 @@ def compute_partial_repr(input_points, control_points):
                                                                          1]
     repr_matrix = 0.5 * pairwise_dist * paddle.log(pairwise_dist)
     # fix numerical error for 0 * log(0), substitute all nan with 0
-    mask = repr_matrix != repr_matrix
+    mask = np.array(repr_matrix != repr_matrix)
     repr_matrix[mask] = 0
     return repr_matrix
 

ppocr/postprocess/east_postprocess.py

@@ -29,6 +29,7 @@ class EASTPostProcess(object):
     """
     The post process for EAST.
     """
+
     def __init__(self,
                  score_thresh=0.8,
                  cover_thresh=0.1,
@@ -38,11 +39,6 @@ class EASTPostProcess(object):
         self.score_thresh = score_thresh
         self.cover_thresh = cover_thresh
         self.nms_thresh = nms_thresh
-        
-        # c++ la-nms is faster, but only support python 3.5
-        self.is_python35 = False
-        if sys.version_info.major == 3 and sys.version_info.minor == 5:
-            self.is_python35 = True
 
     def restore_rectangle_quad(self, origin, geometry):
         """
@@ -64,6 +60,7 @@ class EASTPostProcess(object):
         """
         restore text boxes from score map and geo map
         """
+
         score_map = score_map[0]
         geo_map = np.swapaxes(geo_map, 1, 0)
         geo_map = np.swapaxes(geo_map, 1, 2)
@@ -79,10 +76,14 @@ class EASTPostProcess(object):
         boxes = np.zeros((text_box_restored.shape[0], 9), dtype=np.float32)
         boxes[:, :8] = text_box_restored.reshape((-1, 8))
         boxes[:, 8] = score_map[xy_text[:, 0], xy_text[:, 1]]
-        if self.is_python35:
+
+        try:
             import lanms
             boxes = lanms.merge_quadrangle_n9(boxes, nms_thresh)
-        else:
+        except:
+            print(
+                'you should install lanms by pip3 install lanms-nova to speed up nms_locality'
+            )
             boxes = nms_locality(boxes.astype(np.float64), nms_thresh)
         if boxes.shape[0] == 0:
             return []
@@ -139,4 +140,4 @@ class EASTPostProcess(object):
                         continue
                     boxes_norm.append(box)
             dt_boxes_list.append({'points': np.array(boxes_norm)})
-        return dt_boxes_list
+        return dt_boxes_list
\ No newline at end of file

ppocr/utils/save_load.py

@@ -54,14 +54,37 @@ def load_model(config, model, optimizer=None):
     pretrained_model = global_config.get('pretrained_model')
     best_model_dict = {}
     if checkpoints:
-        if checkpoints.endswith('pdparams'):
+        if checkpoints.endswith('.pdparams'):
             checkpoints = checkpoints.replace('.pdparams', '')
-        assert os.path.exists(checkpoints + ".pdopt"), \
-            f"The {checkpoints}.pdopt does not exists!"
-        load_pretrained_params(model, checkpoints)
-        optim_dict = paddle.load(checkpoints + '.pdopt')
+        assert os.path.exists(checkpoints + ".pdparams"), \
+            "The {}.pdparams does not exists!".format(checkpoints)
+
+        # load params from trained model
+        params = paddle.load(checkpoints + '.pdparams')
+        state_dict = model.state_dict()
+        new_state_dict = {}
+        for key, value in state_dict.items():
+            if key not in params:
+                logger.warning("{} not in loaded params {} !".format(
+                    key, params.keys()))
+                continue
+            pre_value = params[key]
+            if list(value.shape) == list(pre_value.shape):
+                new_state_dict[key] = pre_value
+            else:
+                logger.warning(
+                    "The shape of model params {} {} not matched with loaded params shape {} !".
+                    format(key, value.shape, pre_value.shape))
+        model.set_state_dict(new_state_dict)
+
         if optimizer is not None:
-            optimizer.set_state_dict(optim_dict)
+            if os.path.exists(checkpoints + '.pdopt'):
+                optim_dict = paddle.load(checkpoints + '.pdopt')
+                optimizer.set_state_dict(optim_dict)
+            else:
+                logger.warning(
+                    "{}.pdopt is not exists, params of optimizer is not loaded".
+                    format(checkpoints))
 
         if os.path.exists(checkpoints + '.states'):
             with open(checkpoints + '.states', 'rb') as f:
@@ -80,10 +103,10 @@ def load_model(config, model, optimizer=None):
 
 def load_pretrained_params(model, path):
     logger = get_logger()
-    if path.endswith('pdparams'):
+    if path.endswith('.pdparams'):
         path = path.replace('.pdparams', '')
     assert os.path.exists(path + ".pdparams"), \
-        f"The {path}.pdparams does not exists!"
+        "The {}.pdparams does not exists!".format(path)
 
     params = paddle.load(path + '.pdparams')
     state_dict = model.state_dict()
@@ -92,11 +115,11 @@ def load_pretrained_params(model, path):
         if list(state_dict[k1].shape) == list(params[k2].shape):
             new_state_dict[k1] = params[k2]
         else:
-            logger.info(
-                f"The shape of model params {k1} {state_dict[k1].shape} not matched with loaded params {k2} {params[k2].shape} !"
-            )
+            logger.warning(
+                "The shape of model params {} {} not matched with loaded params {} {} !".
+                format(k1, state_dict[k1].shape, k2, params[k2].shape))
     model.set_state_dict(new_state_dict)
-    logger.info(f"load pretrain successful from {path}")
+    logger.info("load pretrain successful from {}".format(path))
     return model
 
 

test_tipc/common_func.sh

@@ -30,6 +30,7 @@ function func_set_params(){
 
 function func_parser_params(){
     strs=$1
+    MODE=$2
     IFS=":"
     array=(${strs})
     key=${array[0]}

test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt

+===========================ch_PP-OCRv2===========================
+model_name:ch_PP-OCRv2
+python:python3.7
+infer_model:./inference/ch_PP-OCRv2_det_infer/
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_system.py
+--use_gpu:False|True
+--enable_mkldnn:False|True
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:False|True
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+--rec_model_dir:./inference/ch_PP-OCRv2_rec_infer/
+--benchmark:True
+null:null
+null:null

test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_lite_cpp_arm_cpu.txt

+===========================lite_params===========================
+inference:./ocr_db_crnn system
+runtime_device:ARM_CPU
+det_infer_model:ch_PP-OCRv2_det_infer|ch_PP-OCRv2_det_slim_quant_infer
+rec_infer_model:ch_PP-OCRv2_rec_infer|ch_PP-OCRv2_rec_slim_quant_infer
+cls_infer_model:ch_ppocr_mobile_v2.0_cls_infer|ch_ppocr_mobile_v2.0_cls_slim_infer
+--cpu_threads:1|4
+--det_batch_size:1
+--rec_batch_size:1
+--image_dir:./test_data/icdar2015_lite/text_localization/ch4_test_images/
+--config_dir:./config.txt
+--rec_dict_dir:./ppocr_keys_v1.txt
+--benchmark:True

test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_lite_cpp_arm_gpu_opencl.txt

+===========================lite_params===========================
+inference:./ocr_db_crnn system
+runtime_device:ARM_GPU_OPENCL
+det_infer_model:ch_PP-OCRv2_det_infer|ch_PP-OCRv2_det_slim_quant_infer
+rec_infer_model:ch_PP-OCRv2_rec_infer|ch_PP-OCRv2_rec_slim_quant_infer
+cls_infer_model:ch_ppocr_mobile_v2.0_cls_infer|ch_ppocr_mobile_v2.0_cls_slim_infer
+--cpu_threads:1|4
+--det_batch_size:1
+--rec_batch_size:1
+--image_dir:./test_data/icdar2015_lite/text_localization/ch4_test_images/
+--config_dir:./config.txt
+--rec_dict_dir:./ppocr_keys_v1.txt
+--benchmark:True

test_tipc/configs/ch_PP-OCRv2_det/model_linux_gpu_normal_normal_lite_cpp_arm_cpu.txt

+===========================lite_params===========================
+inference:./ocr_db_crnn det
+runtime_device:ARM_CPU
+det_infer_model:ch_PP-OCRv2_det_infer|ch_PP-OCRv2_det_slim_quant_infer
+null:null
+null:null
+--cpu_threads:1|4
+--det_batch_size:1
+null:null
+--image_dir:./test_data/icdar2015_lite/text_localization/ch4_test_images/
+--config_dir:./config.txt
+null:null
+--benchmark:True
\ No newline at end of file

test_tipc/configs/ch_PP-OCRv2_det/model_linux_gpu_normal_normal_lite_cpp_arm_gpu_opencl.txt

+===========================lite_params===========================
+inference:./ocr_db_crnn det
+runtime_device:ARM_GPU_OPENCL
+det_infer_model:ch_PP-OCRv2_det_infer|ch_PP-OCRv2_det_slim_quant_infer
+null:null
+null:null
+--cpu_threads:1|4
+--det_batch_size:1
+null:null
+--image_dir:./test_data/icdar2015_lite/text_localization/ch4_test_images/
+--config_dir:./config.txt
+null:null
+--benchmark:True

test_tipc/configs/ppocrv2_det_mobile/train_infer_python.txt → test_tipc/configs/ch_PP-OCRv2_det/train_infer_python.txt

 ===========================train_params===========================
-model_name:PPOCRv2_ocr_det
+model_name:ch_PPOCRv2_det
 python:python3.7
 gpu_list:0|0,1
 Global.use_gpu:True|True
 Global.auto_cast:fp32
-Global.epoch_num:lite_train_infer=1|whole_train_infer=500
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
 Global.save_model_dir:./output/
-Train.loader.batch_size_per_card:lite_train_infer=2|whole_train_infer=4
+Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
 Global.pretrained_model:null
 train_model_name:latest
 train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
 null:null
 ##
 trainer:norm_train|pact_train
-norm_train:tools/train.py -c configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml -o 
-pact_train:deploy/slim/quantization/quant.py -c configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml -o
+norm_train:tools/train.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml -o 
+pact_train:deploy/slim/quantization/quant.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml -o
 fpgm_train:null
 distill_train:null
 null:null
@@ -27,8 +27,8 @@ null:null
 ===========================infer_params===========================
 Global.save_inference_dir:./output/
 Global.pretrained_model:
-norm_export:tools/export_model.py -c configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml -o 
-quant_export:deploy/slim/quantization/export_model.py -c configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml -o 
+norm_export:tools/export_model.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml -o 
+quant_export:deploy/slim/quantization/export_model.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml -o 
 fpgm_export: 
 distill_export:null
 export1:null

test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt

+===========================kl_quant_params===========================
+model_name:PPOCRv2_ocr_det_kl
+python:python3.7
+Global.pretrained_model:null
+Global.save_inference_dir:null
+infer_model:./inference/ch_PP-OCRv2_det_infer/
+infer_export:deploy/slim/quantization/quant_kl.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml -o
+infer_quant:True
+inference:tools/infer/predict_det.py
+--use_gpu:False|True
+--enable_mkldnn:True
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:False|True
+--precision:int8
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+null:null
+null:null

test_tipc/configs/ch_PP-OCRv2_det_PACT/train_infer_python.txt

+===========================train_params===========================
+model_name:PPOCRv2_ocr_det
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
+null:null
+##
+trainer:pact_train
+norm_train:null
+pact_train:deploy/slim/quantization/quant.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml -o
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.pretrained_model:
+norm_export:null
+quant_export:deploy/slim/quantization/export_model.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml -o 
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv2_det_infer/
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_det.py
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:False|True
+--precision:fp32|fp16|int8
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+null:null

test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 800
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_pp-OCRv2_distillation
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_pp-OCRv2_distillation.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Piecewise
+    decay_epochs : [700, 800]
+    values : [0.001, 0.0001]
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 2.0e-05
+
+Architecture:
+  model_type: &model_type "rec"
+  name: DistillationModel
+  algorithm: Distillation
+  Models:
+    Teacher:
+      pretrained:
+      freeze_params: false
+      return_all_feats: true
+      model_type: *model_type
+      algorithm: CRNN
+      Transform:
+      Backbone:
+        name: MobileNetV1Enhance
+        scale: 0.5
+      Neck:
+        name: SequenceEncoder
+        encoder_type: rnn
+        hidden_size: 64
+      Head:
+        name: CTCHead
+        mid_channels: 96
+        fc_decay: 0.00002
+    Student:
+      pretrained:
+      freeze_params: false
+      return_all_feats: true
+      model_type: *model_type
+      algorithm: CRNN
+      Transform:
+      Backbone:
+        name: MobileNetV1Enhance
+        scale: 0.5
+      Neck:
+        name: SequenceEncoder
+        encoder_type: rnn
+        hidden_size: 64
+      Head:
+        name: CTCHead
+        mid_channels: 96
+        fc_decay: 0.00002
+  
+
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationCTCLoss:
+      weight: 1.0
+      model_name_list: ["Student", "Teacher"]
+      key: head_out
+  - DistillationDMLLoss:
+      weight: 1.0
+      act: "softmax"
+      use_log: true
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      key: head_out
+  - DistillationDistanceLoss:
+      weight: 1.0
+      mode: "l2"
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      key: backbone_out
+
+PostProcess:
+  name: DistillationCTCLabelDecode
+  model_name: ["Student", "Teacher"]
+  key: head_out
+
+Metric:
+  name: DistillationMetric
+  base_metric_name: RecMetric
+  main_indicator: acc
+  key: "Student"
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ic15_data/
+    label_file_list:
+    - ./train_data/ic15_data/rec_gt_train.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecAug:
+    - CTCLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 32, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_sections: 1
+    num_workers: 8
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ic15_data
+    label_file_list:
+    - ./train_data/ic15_data/rec_gt_test.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - CTCLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 32, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 8

test_tipc/configs/ch_PP-OCRv2_rec/train_infer_python.txt

+===========================train_params===========================
+model_name:PPOCRv2_ocr_rec
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=300
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml -o 
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.pretrained_model:
+norm_export:tools/export_model.py -c test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml -o 
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv2_rec_infer/
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_rec.py
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1|6
+--use_tensorrt:False|True
+--precision:fp32|fp16|int8
+--rec_model_dir:
+--image_dir:/inference/rec_inference
+null:null
+--benchmark:True
+null:null
+
+