Initial commit

benchmark/PaddleOCR_DBNet/models/backbone/__init__.py

+# -*- coding: utf-8 -*-
+# @Time    : 2019/8/23 21:54
+# @Author  : zhoujun
+
+from .resnet import *
+
+__all__ = ["build_backbone"]
+
+support_backbone = [
+    "resnet18",
+    "deformable_resnet18",
+    "deformable_resnet50",
+    "resnet50",
+    "resnet34",
+    "resnet101",
+    "resnet152",
+]
+
+
+def build_backbone(backbone_name, **kwargs):
+    assert (
+        backbone_name in support_backbone
+    ), f"all support backbone is {support_backbone}"
+    backbone = eval(backbone_name)(**kwargs)
+    return backbone

benchmark/PaddleOCR_DBNet/models/backbone/resnet.py

+import math
+import paddle
+from paddle import nn
+
+BatchNorm2d = nn.BatchNorm2D
+
+__all__ = [
+    "ResNet",
+    "resnet18",
+    "resnet34",
+    "resnet50",
+    "resnet101",
+    "deformable_resnet18",
+    "deformable_resnet50",
+    "resnet152",
+]
+
+model_urls = {
+    "resnet18": "https://download.pytorch.org/models/resnet18-5c106cde.pth",
+    "resnet34": "https://download.pytorch.org/models/resnet34-333f7ec4.pth",
+    "resnet50": "https://download.pytorch.org/models/resnet50-19c8e357.pth",
+    "resnet101": "https://download.pytorch.org/models/resnet101-5d3b4d8f.pth",
+    "resnet152": "https://download.pytorch.org/models/resnet152-b121ed2d.pth",
+}
+
+
+def constant_init(module, constant, bias=0):
+    module.weight = paddle.create_parameter(
+        shape=module.weight.shape,
+        dtype="float32",
+        default_initializer=paddle.nn.initializer.Constant(constant),
+    )
+    if hasattr(module, "bias"):
+        module.bias = paddle.create_parameter(
+            shape=module.bias.shape,
+            dtype="float32",
+            default_initializer=paddle.nn.initializer.Constant(bias),
+        )
+
+
+def conv3x3(in_planes, out_planes, stride=1):
+    """3x3 convolution with padding"""
+    return nn.Conv2D(
+        in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias_attr=False
+    )
+
+
+class BasicBlock(nn.Layer):
+    expansion = 1
+
+    def __init__(self, inplanes, planes, stride=1, downsample=None, dcn=None):
+        super(BasicBlock, self).__init__()
+        self.with_dcn = dcn is not None
+        self.conv1 = conv3x3(inplanes, planes, stride)
+        self.bn1 = BatchNorm2d(planes, momentum=0.1)
+        self.relu = nn.ReLU()
+        self.with_modulated_dcn = False
+        if not self.with_dcn:
+            self.conv2 = nn.Conv2D(
+                planes, planes, kernel_size=3, padding=1, bias_attr=False
+            )
+        else:
+            from paddle.vision.ops import DeformConv2D
+
+            deformable_groups = dcn.get("deformable_groups", 1)
+            offset_channels = 18
+            self.conv2_offset = nn.Conv2D(
+                planes, deformable_groups * offset_channels, kernel_size=3, padding=1
+            )
+            self.conv2 = DeformConv2D(
+                planes, planes, kernel_size=3, padding=1, bias_attr=False
+            )
+        self.bn2 = BatchNorm2d(planes, momentum=0.1)
+        self.downsample = downsample
+        self.stride = stride
+
+    def forward(self, x):
+        residual = x
+
+        out = self.conv1(x)
+        out = self.bn1(out)
+        out = self.relu(out)
+
+        # out = self.conv2(out)
+        if not self.with_dcn:
+            out = self.conv2(out)
+        else:
+            offset = self.conv2_offset(out)
+            out = self.conv2(out, offset)
+        out = self.bn2(out)
+
+        if self.downsample is not None:
+            residual = self.downsample(x)
+
+        out += residual
+        out = self.relu(out)
+
+        return out
+
+
+class Bottleneck(nn.Layer):
+    expansion = 4
+
+    def __init__(self, inplanes, planes, stride=1, downsample=None, dcn=None):
+        super(Bottleneck, self).__init__()
+        self.with_dcn = dcn is not None
+        self.conv1 = nn.Conv2D(inplanes, planes, kernel_size=1, bias_attr=False)
+        self.bn1 = BatchNorm2d(planes, momentum=0.1)
+        self.with_modulated_dcn = False
+        if not self.with_dcn:
+            self.conv2 = nn.Conv2D(
+                planes, planes, kernel_size=3, stride=stride, padding=1, bias_attr=False
+            )
+        else:
+            deformable_groups = dcn.get("deformable_groups", 1)
+            from paddle.vision.ops import DeformConv2D
+
+            offset_channels = 18
+            self.conv2_offset = nn.Conv2D(
+                planes,
+                deformable_groups * offset_channels,
+                stride=stride,
+                kernel_size=3,
+                padding=1,
+            )
+            self.conv2 = DeformConv2D(
+                planes, planes, kernel_size=3, padding=1, stride=stride, bias_attr=False
+            )
+        self.bn2 = BatchNorm2d(planes, momentum=0.1)
+        self.conv3 = nn.Conv2D(planes, planes * 4, kernel_size=1, bias_attr=False)
+        self.bn3 = BatchNorm2d(planes * 4, momentum=0.1)
+        self.relu = nn.ReLU()
+        self.downsample = downsample
+        self.stride = stride
+        self.dcn = dcn
+        self.with_dcn = dcn is not None
+
+    def forward(self, x):
+        residual = x
+
+        out = self.conv1(x)
+        out = self.bn1(out)
+        out = self.relu(out)
+
+        # out = self.conv2(out)
+        if not self.with_dcn:
+            out = self.conv2(out)
+        else:
+            offset = self.conv2_offset(out)
+            out = self.conv2(out, offset)
+        out = self.bn2(out)
+        out = self.relu(out)
+
+        out = self.conv3(out)
+        out = self.bn3(out)
+
+        if self.downsample is not None:
+            residual = self.downsample(x)
+
+        out += residual
+        out = self.relu(out)
+
+        return out
+
+
+class ResNet(nn.Layer):
+    def __init__(self, block, layers, in_channels=3, dcn=None):
+        self.dcn = dcn
+        self.inplanes = 64
+        super(ResNet, self).__init__()
+        self.out_channels = []
+        self.conv1 = nn.Conv2D(
+            in_channels, 64, kernel_size=7, stride=2, padding=3, bias_attr=False
+        )
+        self.bn1 = BatchNorm2d(64, momentum=0.1)
+        self.relu = nn.ReLU()
+        self.maxpool = nn.MaxPool2D(kernel_size=3, stride=2, padding=1)
+        self.layer1 = self._make_layer(block, 64, layers[0])
+        self.layer2 = self._make_layer(block, 128, layers[1], stride=2, dcn=dcn)
+        self.layer3 = self._make_layer(block, 256, layers[2], stride=2, dcn=dcn)
+        self.layer4 = self._make_layer(block, 512, layers[3], stride=2, dcn=dcn)
+
+        if self.dcn is not None:
+            for m in self.modules():
+                if isinstance(m, Bottleneck) or isinstance(m, BasicBlock):
+                    if hasattr(m, "conv2_offset"):
+                        constant_init(m.conv2_offset, 0)
+
+    def _make_layer(self, block, planes, blocks, stride=1, dcn=None):
+        downsample = None
+        if stride != 1 or self.inplanes != planes * block.expansion:
+            downsample = nn.Sequential(
+                nn.Conv2D(
+                    self.inplanes,
+                    planes * block.expansion,
+                    kernel_size=1,
+                    stride=stride,
+                    bias_attr=False,
+                ),
+                BatchNorm2d(planes * block.expansion, momentum=0.1),
+            )
+
+        layers = []
+        layers.append(block(self.inplanes, planes, stride, downsample, dcn=dcn))
+        self.inplanes = planes * block.expansion
+        for i in range(1, blocks):
+            layers.append(block(self.inplanes, planes, dcn=dcn))
+        self.out_channels.append(planes * block.expansion)
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        x = self.conv1(x)
+        x = self.bn1(x)
+        x = self.relu(x)
+        x = self.maxpool(x)
+
+        x2 = self.layer1(x)
+        x3 = self.layer2(x2)
+        x4 = self.layer3(x3)
+        x5 = self.layer4(x4)
+
+        return x2, x3, x4, x5
+
+
+def load_torch_params(paddle_model, torch_patams):
+    paddle_params = paddle_model.state_dict()
+
+    fc_names = ["classifier"]
+    for key, torch_value in torch_patams.items():
+        if "num_batches_tracked" in key:
+            continue
+        key = (
+            key.replace("running_var", "_variance")
+            .replace("running_mean", "_mean")
+            .replace("module.", "")
+        )
+        torch_value = torch_value.detach().cpu().numpy()
+        if key in paddle_params:
+            flag = [i in key for i in fc_names]
+            if any(flag) and "weight" in key:  # ignore bias
+                new_shape = [1, 0] + list(range(2, torch_value.ndim))
+                print(
+                    f"name: {key}, ori shape: {torch_value.shape}, new shape: {torch_value.transpose(new_shape).shape}"
+                )
+                torch_value = torch_value.transpose(new_shape)
+            paddle_params[key] = torch_value
+        else:
+            print(f"{key} not in paddle")
+    paddle_model.set_state_dict(paddle_params)
+
+
+def load_models(model, model_name):
+    import torch.utils.model_zoo as model_zoo
+
+    torch_patams = model_zoo.load_url(model_urls[model_name])
+    load_torch_params(model, torch_patams)
+
+
+def resnet18(pretrained=True, **kwargs):
+    """Constructs a ResNet-18 model.
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+    """
+    model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
+    if pretrained:
+        assert (
+            kwargs.get("in_channels", 3) == 3
+        ), "in_channels must be 3 when pretrained is True"
+        print("load from imagenet")
+        load_models(model, "resnet18")
+    return model
+
+
+def deformable_resnet18(pretrained=True, **kwargs):
+    """Constructs a ResNet-18 model.
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+    """
+    model = ResNet(BasicBlock, [2, 2, 2, 2], dcn=dict(deformable_groups=1), **kwargs)
+    if pretrained:
+        assert (
+            kwargs.get("in_channels", 3) == 3
+        ), "in_channels must be 3 when pretrained is True"
+        print("load from imagenet")
+        model.load_state_dict(model_zoo.load_url(model_urls["resnet18"]), strict=False)
+    return model
+
+
+def resnet34(pretrained=True, **kwargs):
+    """Constructs a ResNet-34 model.
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+    """
+    model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
+    if pretrained:
+        assert (
+            kwargs.get("in_channels", 3) == 3
+        ), "in_channels must be 3 when pretrained is True"
+        model.load_state_dict(model_zoo.load_url(model_urls["resnet34"]), strict=False)
+    return model
+
+
+def resnet50(pretrained=True, **kwargs):
+    """Constructs a ResNet-50 model.
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+    """
+    model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
+    if pretrained:
+        assert (
+            kwargs.get("in_channels", 3) == 3
+        ), "in_channels must be 3 when pretrained is True"
+        load_models(model, "resnet50")
+    return model
+
+
+def deformable_resnet50(pretrained=True, **kwargs):
+    """Constructs a ResNet-50 model with deformable conv.
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+    """
+    model = ResNet(Bottleneck, [3, 4, 6, 3], dcn=dict(deformable_groups=1), **kwargs)
+    if pretrained:
+        assert (
+            kwargs.get("in_channels", 3) == 3
+        ), "in_channels must be 3 when pretrained is True"
+        model.load_state_dict(model_zoo.load_url(model_urls["resnet50"]), strict=False)
+    return model
+
+
+def resnet101(pretrained=True, **kwargs):
+    """Constructs a ResNet-101 model.
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+    """
+    model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
+    if pretrained:
+        assert (
+            kwargs.get("in_channels", 3) == 3
+        ), "in_channels must be 3 when pretrained is True"
+        model.load_state_dict(model_zoo.load_url(model_urls["resnet101"]), strict=False)
+    return model
+
+
+def resnet152(pretrained=True, **kwargs):
+    """Constructs a ResNet-152 model.
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+    """
+    model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
+    if pretrained:
+        assert (
+            kwargs.get("in_channels", 3) == 3
+        ), "in_channels must be 3 when pretrained is True"
+        model.load_state_dict(model_zoo.load_url(model_urls["resnet152"]), strict=False)
+    return model
+
+
+if __name__ == "__main__":
+    x = paddle.zeros([2, 3, 640, 640])
+    net = resnet50(pretrained=True)
+    y = net(x)
+    for u in y:
+        print(u.shape)
+
+    print(net.out_channels)

benchmark/PaddleOCR_DBNet/models/basic.py

+# -*- coding: utf-8 -*-
+# @Time    : 2019/12/6 11:19
+# @Author  : zhoujun
+from paddle import nn
+
+
+class ConvBnRelu(nn.Layer):
+    def __init__(
+        self,
+        in_channels,
+        out_channels,
+        kernel_size,
+        stride=1,
+        padding=0,
+        dilation=1,
+        groups=1,
+        bias=True,
+        padding_mode="zeros",
+        inplace=True,
+    ):
+        super().__init__()
+        self.conv = nn.Conv2D(
+            in_channels=in_channels,
+            out_channels=out_channels,
+            kernel_size=kernel_size,
+            stride=stride,
+            padding=padding,
+            dilation=dilation,
+            groups=groups,
+            bias_attr=bias,
+            padding_mode=padding_mode,
+        )
+        self.bn = nn.BatchNorm2D(out_channels)
+        self.relu = nn.ReLU()
+
+    def forward(self, x):
+        x = self.conv(x)
+        x = self.bn(x)
+        x = self.relu(x)
+        return x

benchmark/PaddleOCR_DBNet/models/head/DBHead.py

+# -*- coding: utf-8 -*-
+# @Time    : 2019/12/4 14:54
+# @Author  : zhoujun
+import paddle
+from paddle import nn, ParamAttr
+
+
+class DBHead(nn.Layer):
+    def __init__(self, in_channels, out_channels, k=50):
+        super().__init__()
+        self.k = k
+        self.binarize = nn.Sequential(
+            nn.Conv2D(
+                in_channels,
+                in_channels // 4,
+                3,
+                padding=1,
+                weight_attr=ParamAttr(initializer=nn.initializer.KaimingNormal()),
+            ),
+            nn.BatchNorm2D(
+                in_channels // 4,
+                weight_attr=ParamAttr(initializer=nn.initializer.Constant(1)),
+                bias_attr=ParamAttr(initializer=nn.initializer.Constant(1e-4)),
+            ),
+            nn.ReLU(),
+            nn.Conv2DTranspose(
+                in_channels // 4,
+                in_channels // 4,
+                2,
+                2,
+                weight_attr=ParamAttr(initializer=nn.initializer.KaimingNormal()),
+            ),
+            nn.BatchNorm2D(
+                in_channels // 4,
+                weight_attr=ParamAttr(initializer=nn.initializer.Constant(1)),
+                bias_attr=ParamAttr(initializer=nn.initializer.Constant(1e-4)),
+            ),
+            nn.ReLU(),
+            nn.Conv2DTranspose(
+                in_channels // 4, 1, 2, 2, weight_attr=nn.initializer.KaimingNormal()
+            ),
+            nn.Sigmoid(),
+        )
+
+        self.thresh = self._init_thresh(in_channels)
+
+    def forward(self, x):
+        shrink_maps = self.binarize(x)
+        threshold_maps = self.thresh(x)
+        if self.training:
+            binary_maps = self.step_function(shrink_maps, threshold_maps)
+            y = paddle.concat((shrink_maps, threshold_maps, binary_maps), axis=1)
+        else:
+            y = paddle.concat((shrink_maps, threshold_maps), axis=1)
+        return y
+
+    def _init_thresh(self, inner_channels, serial=False, smooth=False, bias=False):
+        in_channels = inner_channels
+        if serial:
+            in_channels += 1
+        self.thresh = nn.Sequential(
+            nn.Conv2D(
+                in_channels,
+                inner_channels // 4,
+                3,
+                padding=1,
+                bias_attr=bias,
+                weight_attr=ParamAttr(initializer=nn.initializer.KaimingNormal()),
+            ),
+            nn.BatchNorm2D(
+                inner_channels // 4,
+                weight_attr=ParamAttr(initializer=nn.initializer.Constant(1)),
+                bias_attr=ParamAttr(initializer=nn.initializer.Constant(1e-4)),
+            ),
+            nn.ReLU(),
+            self._init_upsample(
+                inner_channels // 4, inner_channels // 4, smooth=smooth, bias=bias
+            ),
+            nn.BatchNorm2D(
+                inner_channels // 4,
+                weight_attr=ParamAttr(initializer=nn.initializer.Constant(1)),
+                bias_attr=ParamAttr(initializer=nn.initializer.Constant(1e-4)),
+            ),
+            nn.ReLU(),
+            self._init_upsample(inner_channels // 4, 1, smooth=smooth, bias=bias),
+            nn.Sigmoid(),
+        )
+        return self.thresh
+
+    def _init_upsample(self, in_channels, out_channels, smooth=False, bias=False):
+        if smooth:
+            inter_out_channels = out_channels
+            if out_channels == 1:
+                inter_out_channels = in_channels
+            module_list = [
+                nn.Upsample(scale_factor=2, mode="nearest"),
+                nn.Conv2D(
+                    in_channels,
+                    inter_out_channels,
+                    3,
+                    1,
+                    1,
+                    bias_attr=bias,
+                    weight_attr=ParamAttr(initializer=nn.initializer.KaimingNormal()),
+                ),
+            ]
+            if out_channels == 1:
+                module_list.append(
+                    nn.Conv2D(
+                        in_channels,
+                        out_channels,
+                        kernel_size=1,
+                        stride=1,
+                        padding=1,
+                        bias_attr=True,
+                        weight_attr=ParamAttr(
+                            initializer=nn.initializer.KaimingNormal()
+                        ),
+                    )
+                )
+            return nn.Sequential(module_list)
+        else:
+            return nn.Conv2DTranspose(
+                in_channels,
+                out_channels,
+                2,
+                2,
+                weight_attr=ParamAttr(initializer=nn.initializer.KaimingNormal()),
+            )
+
+    def step_function(self, x, y):
+        return paddle.reciprocal(1 + paddle.exp(-self.k * (x - y)))

benchmark/PaddleOCR_DBNet/models/head/__init__.py

+# -*- coding: utf-8 -*-
+# @Time    : 2020/6/5 11:35
+# @Author  : zhoujun
+from .DBHead import DBHead
+
+__all__ = ["build_head"]
+support_head = ["DBHead"]
+
+
+def build_head(head_name, **kwargs):
+    assert head_name in support_head, f"all support head is {support_head}"
+    head = eval(head_name)(**kwargs)
+    return head

benchmark/PaddleOCR_DBNet/models/losses/DB_loss.py

+import paddle
+from models.losses.basic_loss import BalanceCrossEntropyLoss, MaskL1Loss, DiceLoss
+
+
+class DBLoss(paddle.nn.Layer):
+    def __init__(self, alpha=1.0, beta=10, ohem_ratio=3, reduction="mean", eps=1e-06):
+        """
+        Implement PSE Loss.
+        :param alpha: binary_map loss 前面的系数
+        :param beta: threshold_map loss 前面的系数
+        :param ohem_ratio: OHEM的比例
+        :param reduction: 'mean' or 'sum'对 batch里的loss 算均值或求和
+        """
+        super().__init__()
+        assert reduction in ["mean", "sum"], " reduction must in ['mean','sum']"
+        self.alpha = alpha
+        self.beta = beta
+        self.bce_loss = BalanceCrossEntropyLoss(negative_ratio=ohem_ratio)
+        self.dice_loss = DiceLoss(eps=eps)
+        self.l1_loss = MaskL1Loss(eps=eps)
+        self.ohem_ratio = ohem_ratio
+        self.reduction = reduction
+
+    def forward(self, pred, batch):
+        shrink_maps = pred[:, 0, :, :]
+        threshold_maps = pred[:, 1, :, :]
+        binary_maps = pred[:, 2, :, :]
+        loss_shrink_maps = self.bce_loss(
+            shrink_maps, batch["shrink_map"], batch["shrink_mask"]
+        )
+        loss_threshold_maps = self.l1_loss(
+            threshold_maps, batch["threshold_map"], batch["threshold_mask"]
+        )
+        metrics = dict(
+            loss_shrink_maps=loss_shrink_maps, loss_threshold_maps=loss_threshold_maps
+        )
+        if pred.shape[1] > 2:
+            loss_binary_maps = self.dice_loss(
+                binary_maps, batch["shrink_map"], batch["shrink_mask"]
+            )
+            metrics["loss_binary_maps"] = loss_binary_maps
+            loss_all = (
+                self.alpha * loss_shrink_maps
+                + self.beta * loss_threshold_maps
+                + loss_binary_maps
+            )
+            metrics["loss"] = loss_all
+        else:
+            metrics["loss"] = loss_shrink_maps
+        return metrics

benchmark/PaddleOCR_DBNet/models/losses/__init__.py

+# -*- coding: utf-8 -*-
+# @Time    : 2020/6/5 11:36
+# @Author  : zhoujun
+import copy
+from .DB_loss import DBLoss
+
+__all__ = ["build_loss"]
+support_loss = ["DBLoss"]
+
+
+def build_loss(config):
+    copy_config = copy.deepcopy(config)
+    loss_type = copy_config.pop("type")
+    assert loss_type in support_loss, f"all support loss is {support_loss}"
+    criterion = eval(loss_type)(**copy_config)
+    return criterion

benchmark/PaddleOCR_DBNet/models/losses/basic_loss.py

+# -*- coding: utf-8 -*-
+# @Time    : 2019/12/4 14:39
+# @Author  : zhoujun
+import paddle
+import paddle.nn as nn
+
+
+class BalanceCrossEntropyLoss(nn.Layer):
+    """
+    Balanced cross entropy loss.
+    Shape:
+        - Input: :math:`(N, 1, H, W)`
+        - GT: :math:`(N, 1, H, W)`, same shape as the input
+        - Mask: :math:`(N, H, W)`, same spatial shape as the input
+        - Output: scalar.
+
+    """
+
+    def __init__(self, negative_ratio=3.0, eps=1e-6):
+        super(BalanceCrossEntropyLoss, self).__init__()
+        self.negative_ratio = negative_ratio
+        self.eps = eps
+
+    def forward(
+        self,
+        pred: paddle.Tensor,
+        gt: paddle.Tensor,
+        mask: paddle.Tensor,
+        return_origin=False,
+    ):
+        """
+        Args:
+            pred: shape :math:`(N, 1, H, W)`, the prediction of network
+            gt: shape :math:`(N, 1, H, W)`, the target
+            mask: shape :math:`(N, H, W)`, the mask indicates positive regions
+        """
+        positive = gt * mask
+        negative = (1 - gt) * mask
+        positive_count = int(positive.sum())
+        negative_count = min(
+            int(negative.sum()), int(positive_count * self.negative_ratio)
+        )
+        loss = nn.functional.binary_cross_entropy(pred, gt, reduction="none")
+        positive_loss = loss * positive
+        negative_loss = loss * negative
+        negative_loss, _ = negative_loss.reshape([-1]).topk(negative_count)
+
+        balance_loss = (positive_loss.sum() + negative_loss.sum()) / (
+            positive_count + negative_count + self.eps
+        )
+
+        if return_origin:
+            return balance_loss, loss
+        return balance_loss
+
+
+class DiceLoss(nn.Layer):
+    """
+    Loss function from https://arxiv.org/abs/1707.03237,
+    where iou computation is introduced heatmap manner to measure the
+    diversity between tow heatmaps.
+    """
+
+    def __init__(self, eps=1e-6):
+        super(DiceLoss, self).__init__()
+        self.eps = eps
+
+    def forward(self, pred: paddle.Tensor, gt, mask, weights=None):
+        """
+        pred: one or two heatmaps of shape (N, 1, H, W),
+            the losses of tow heatmaps are added together.
+        gt: (N, 1, H, W)
+        mask: (N, H, W)
+        """
+        return self._compute(pred, gt, mask, weights)
+
+    def _compute(self, pred, gt, mask, weights):
+        if len(pred.shape) == 4:
+            pred = pred[:, 0, :, :]
+            gt = gt[:, 0, :, :]
+        assert pred.shape == gt.shape
+        assert pred.shape == mask.shape
+        if weights is not None:
+            assert weights.shape == mask.shape
+            mask = weights * mask
+        intersection = (pred * gt * mask).sum()
+
+        union = (pred * mask).sum() + (gt * mask).sum() + self.eps
+        loss = 1 - 2.0 * intersection / union
+        assert loss <= 1
+        return loss
+
+
+class MaskL1Loss(nn.Layer):
+    def __init__(self, eps=1e-6):
+        super(MaskL1Loss, self).__init__()
+        self.eps = eps
+
+    def forward(self, pred: paddle.Tensor, gt, mask):
+        loss = (paddle.abs(pred - gt) * mask).sum() / (mask.sum() + self.eps)
+        return loss

benchmark/PaddleOCR_DBNet/models/model.py

+# -*- coding: utf-8 -*-
+# @Time    : 2019/8/23 21:57
+# @Author  : zhoujun
+from addict import Dict
+from paddle import nn
+import paddle.nn.functional as F
+
+from models.backbone import build_backbone
+from models.neck import build_neck
+from models.head import build_head
+
+
+class Model(nn.Layer):
+    def __init__(self, model_config: dict):
+        """
+        PANnet
+        :param model_config: 模型配置
+        """
+        super().__init__()
+        model_config = Dict(model_config)
+        backbone_type = model_config.backbone.pop("type")
+        neck_type = model_config.neck.pop("type")
+        head_type = model_config.head.pop("type")
+        self.backbone = build_backbone(backbone_type, **model_config.backbone)
+        self.neck = build_neck(
+            neck_type, in_channels=self.backbone.out_channels, **model_config.neck
+        )
+        self.head = build_head(
+            head_type, in_channels=self.neck.out_channels, **model_config.head
+        )
+        self.name = f"{backbone_type}_{neck_type}_{head_type}"
+
+    def forward(self, x):
+        _, _, H, W = x.shape
+        backbone_out = self.backbone(x)
+        neck_out = self.neck(backbone_out)
+        y = self.head(neck_out)
+        y = F.interpolate(y, size=(H, W), mode="bilinear", align_corners=True)
+        return y

benchmark/PaddleOCR_DBNet/models/neck/FPN.py

+# -*- coding: utf-8 -*-
+# @Time    : 2019/9/13 10:29
+# @Author  : zhoujun
+import paddle
+import paddle.nn.functional as F
+from paddle import nn
+
+from models.basic import ConvBnRelu
+
+
+class FPN(nn.Layer):
+    def __init__(self, in_channels, inner_channels=256, **kwargs):
+        """
+        :param in_channels: 基础网络输出的维度
+        :param kwargs:
+        """
+        super().__init__()
+        inplace = True
+        self.conv_out = inner_channels
+        inner_channels = inner_channels // 4
+        # reduce layers
+        self.reduce_conv_c2 = ConvBnRelu(
+            in_channels[0], inner_channels, kernel_size=1, inplace=inplace
+        )
+        self.reduce_conv_c3 = ConvBnRelu(
+            in_channels[1], inner_channels, kernel_size=1, inplace=inplace
+        )
+        self.reduce_conv_c4 = ConvBnRelu(
+            in_channels[2], inner_channels, kernel_size=1, inplace=inplace
+        )
+        self.reduce_conv_c5 = ConvBnRelu(
+            in_channels[3], inner_channels, kernel_size=1, inplace=inplace
+        )
+        # Smooth layers
+        self.smooth_p4 = ConvBnRelu(
+            inner_channels, inner_channels, kernel_size=3, padding=1, inplace=inplace
+        )
+        self.smooth_p3 = ConvBnRelu(
+            inner_channels, inner_channels, kernel_size=3, padding=1, inplace=inplace
+        )
+        self.smooth_p2 = ConvBnRelu(
+            inner_channels, inner_channels, kernel_size=3, padding=1, inplace=inplace
+        )
+
+        self.conv = nn.Sequential(
+            nn.Conv2D(self.conv_out, self.conv_out, kernel_size=3, padding=1, stride=1),
+            nn.BatchNorm2D(self.conv_out),
+            nn.ReLU(),
+        )
+        self.out_channels = self.conv_out
+
+    def forward(self, x):
+        c2, c3, c4, c5 = x
+        # Top-down
+        p5 = self.reduce_conv_c5(c5)
+        p4 = self._upsample_add(p5, self.reduce_conv_c4(c4))
+        p4 = self.smooth_p4(p4)
+        p3 = self._upsample_add(p4, self.reduce_conv_c3(c3))
+        p3 = self.smooth_p3(p3)
+        p2 = self._upsample_add(p3, self.reduce_conv_c2(c2))
+        p2 = self.smooth_p2(p2)
+
+        x = self._upsample_cat(p2, p3, p4, p5)
+        x = self.conv(x)
+        return x
+
+    def _upsample_add(self, x, y):
+        return F.interpolate(x, size=y.shape[2:]) + y
+
+    def _upsample_cat(self, p2, p3, p4, p5):
+        h, w = p2.shape[2:]
+        p3 = F.interpolate(p3, size=(h, w))
+        p4 = F.interpolate(p4, size=(h, w))
+        p5 = F.interpolate(p5, size=(h, w))
+        return paddle.concat([p2, p3, p4, p5], axis=1)

benchmark/PaddleOCR_DBNet/models/neck/__init__.py

+# -*- coding: utf-8 -*-
+# @Time    : 2020/6/5 11:34
+# @Author  : zhoujun
+from .FPN import FPN
+
+__all__ = ["build_neck"]
+support_neck = ["FPN"]
+
+
+def build_neck(neck_name, **kwargs):
+    assert neck_name in support_neck, f"all support neck is {support_neck}"
+    neck = eval(neck_name)(**kwargs)
+    return neck

benchmark/PaddleOCR_DBNet/multi_gpu_train.sh

+# export NCCL_P2P_DISABLE=1
+CUDA_VISIBLE_DEVICES=0,1,2,3 python3 -m paddle.distributed.launch tools/train.py --config_file "config/icdar2015_resnet50_FPN_DBhead_polyLR.yaml"

benchmark/PaddleOCR_DBNet/post_processing/__init__.py

+# -*- coding: utf-8 -*-
+# @Time    : 2019/12/5 15:17
+# @Author  : zhoujun
+
+from .seg_detector_representer import SegDetectorRepresenter
+
+
+def get_post_processing(config):
+    try:
+        cls = eval(config["type"])(**config["args"])
+        return cls
+    except:
+        return None

benchmark/PaddleOCR_DBNet/post_processing/seg_detector_representer.py

+import cv2
+import numpy as np
+import pyclipper
+import paddle
+from shapely.geometry import Polygon
+
+
+class SegDetectorRepresenter:
+    def __init__(
+        self, thresh=0.3, box_thresh=0.7, max_candidates=1000, unclip_ratio=1.5
+    ):
+        self.min_size = 3
+        self.thresh = thresh
+        self.box_thresh = box_thresh
+        self.max_candidates = max_candidates
+        self.unclip_ratio = unclip_ratio
+
+    def __call__(self, batch, pred, is_output_polygon=False):
+        """
+        batch: (image, polygons, ignore_tags
+        batch: a dict produced by dataloaders.
+            image: tensor of shape (N, C, H, W).
+            polygons: tensor of shape (N, K, 4, 2), the polygons of objective regions.
+            ignore_tags: tensor of shape (N, K), indicates whether a region is ignorable or not.
+            shape: the original shape of images.
+            filename: the original filenames of images.
+        pred:
+            binary: text region segmentation map, with shape (N, H, W)
+            thresh: [if exists] thresh hold prediction with shape (N, H, W)
+            thresh_binary: [if exists] binarized with threshold, (N, H, W)
+        """
+        if isinstance(pred, paddle.Tensor):
+            pred = pred.numpy()
+        pred = pred[:, 0, :, :]
+        segmentation = self.binarize(pred)
+        boxes_batch = []
+        scores_batch = []
+        for batch_index in range(pred.shape[0]):
+            height, width = batch["shape"][batch_index]
+            if is_output_polygon:
+                boxes, scores = self.polygons_from_bitmap(
+                    pred[batch_index], segmentation[batch_index], width, height
+                )
+            else:
+                boxes, scores = self.boxes_from_bitmap(
+                    pred[batch_index], segmentation[batch_index], width, height
+                )
+            boxes_batch.append(boxes)
+            scores_batch.append(scores)
+        return boxes_batch, scores_batch
+
+    def binarize(self, pred):
+        return pred > self.thresh
+
+    def polygons_from_bitmap(self, pred, _bitmap, dest_width, dest_height):
+        """
+        _bitmap: single map with shape (H, W),
+            whose values are binarized as {0, 1}
+        """
+
+        assert len(_bitmap.shape) == 2
+        bitmap = _bitmap  # The first channel
+        height, width = bitmap.shape
+        boxes = []
+        scores = []
+
+        contours, _ = cv2.findContours(
+            (bitmap * 255).astype(np.uint8), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE
+        )
+
+        for contour in contours[: self.max_candidates]:
+            epsilon = 0.005 * cv2.arcLength(contour, True)
+            approx = cv2.approxPolyDP(contour, epsilon, True)
+            points = approx.reshape((-1, 2))
+            if points.shape[0] < 4:
+                continue
+            # _, sside = self.get_mini_boxes(contour)
+            # if sside < self.min_size:
+            #     continue
+            score = self.box_score_fast(pred, contour.squeeze(1))
+            if self.box_thresh > score:
+                continue
+
+            if points.shape[0] > 2:
+                box = self.unclip(points, unclip_ratio=self.unclip_ratio)
+                if len(box) > 1:
+                    continue
+            else:
+                continue
+            box = box.reshape(-1, 2)
+            _, sside = self.get_mini_boxes(box.reshape((-1, 1, 2)))
+            if sside < self.min_size + 2:
+                continue
+
+            if not isinstance(dest_width, int):
+                dest_width = dest_width.item()
+                dest_height = dest_height.item()
+
+            box[:, 0] = np.clip(np.round(box[:, 0] / width * dest_width), 0, dest_width)
+            box[:, 1] = np.clip(
+                np.round(box[:, 1] / height * dest_height), 0, dest_height
+            )
+            boxes.append(box)
+            scores.append(score)
+        return boxes, scores
+
+    def boxes_from_bitmap(self, pred, _bitmap, dest_width, dest_height):
+        """
+        _bitmap: single map with shape (H, W),
+            whose values are binarized as {0, 1}
+        """
+
+        assert len(_bitmap.shape) == 2
+        bitmap = _bitmap  # The first channel
+        height, width = bitmap.shape
+        contours, _ = cv2.findContours(
+            (bitmap * 255).astype(np.uint8), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE
+        )
+        num_contours = min(len(contours), self.max_candidates)
+        boxes = np.zeros((num_contours, 4, 2), dtype=np.int16)
+        scores = np.zeros((num_contours,), dtype=np.float32)
+
+        for index in range(num_contours):
+            contour = contours[index].squeeze(1)
+            points, sside = self.get_mini_boxes(contour)
+            if sside < self.min_size:
+                continue
+            points = np.array(points)
+            score = self.box_score_fast(pred, contour)
+            if self.box_thresh > score:
+                continue
+
+            box = self.unclip(points, unclip_ratio=self.unclip_ratio).reshape(-1, 1, 2)
+            box, sside = self.get_mini_boxes(box)
+            if sside < self.min_size + 2:
+                continue
+            box = np.array(box)
+            if not isinstance(dest_width, int):
+                dest_width = dest_width.item()
+                dest_height = dest_height.item()
+
+            box[:, 0] = np.clip(np.round(box[:, 0] / width * dest_width), 0, dest_width)
+            box[:, 1] = np.clip(
+                np.round(box[:, 1] / height * dest_height), 0, dest_height
+            )
+            boxes[index, :, :] = box.astype(np.int16)
+            scores[index] = score
+        return boxes, scores
+
+    def unclip(self, box, unclip_ratio=1.5):
+        poly = Polygon(box)
+        distance = poly.area * unclip_ratio / poly.length
+        offset = pyclipper.PyclipperOffset()
+        offset.AddPath(box, pyclipper.JT_ROUND, pyclipper.ET_CLOSEDPOLYGON)
+        expanded = np.array(offset.Execute(distance))
+        return expanded
+
+    def get_mini_boxes(self, contour):
+        bounding_box = cv2.minAreaRect(contour)
+        points = sorted(list(cv2.boxPoints(bounding_box)), key=lambda x: x[0])
+
+        index_1, index_2, index_3, index_4 = 0, 1, 2, 3
+        if points[1][1] > points[0][1]:
+            index_1 = 0
+            index_4 = 1
+        else:
+            index_1 = 1
+            index_4 = 0
+        if points[3][1] > points[2][1]:
+            index_2 = 2
+            index_3 = 3
+        else:
+            index_2 = 3
+            index_3 = 2
+
+        box = [points[index_1], points[index_2], points[index_3], points[index_4]]
+        return box, min(bounding_box[1])
+
+    def box_score_fast(self, bitmap, _box):
+        h, w = bitmap.shape[:2]
+        box = _box.copy()
+        xmin = np.clip(np.floor(box[:, 0].min()).astype(np.int32), 0, w - 1)
+        xmax = np.clip(np.ceil(box[:, 0].max()).astype(np.int32), 0, w - 1)
+        ymin = np.clip(np.floor(box[:, 1].min()).astype(np.int32), 0, h - 1)
+        ymax = np.clip(np.ceil(box[:, 1].max()).astype(np.int32), 0, h - 1)
+
+        mask = np.zeros((ymax - ymin + 1, xmax - xmin + 1), dtype=np.uint8)
+        box[:, 0] = box[:, 0] - xmin
+        box[:, 1] = box[:, 1] - ymin
+        cv2.fillPoly(mask, box.reshape(1, -1, 2).astype(np.int32), 1)
+        return cv2.mean(bitmap[ymin : ymax + 1, xmin : xmax + 1], mask)[0]

benchmark/PaddleOCR_DBNet/predict.sh

+CUDA_VISIBLE_DEVICES=0 python tools/predict.py --model_path model_best.pth --input_folder ./input --output_folder ./output --thre 0.7 --polygon --show --save_result

benchmark/PaddleOCR_DBNet/requirement.txt

+anyconfig
+future
+imgaug
+matplotlib
+numpy
+opencv-python
+Polygon3
+pyclipper
+PyYAML
+scikit-image
+Shapely
+tqdm
+addict
+visualdl

benchmark/PaddleOCR_DBNet/single_gpu_train.sh

+CUDA_VISIBLE_DEVICES=0 python3 tools/train.py --config_file "config/icdar2015_resnet50_FPN_DBhead_polyLR.yaml" 

benchmark/PaddleOCR_DBNet/test/README.MD

+Place the images that you want to detect here. You better named them as such:
+img_10.jpg
+img_11.jpg
+img_{img_id}.jpg
+
+For predicting single images, you can change the `img_path` in the `/tools/predict.py` to your image number.
+
+The result will be saved in the output_folder(default is test/output) you give in predict.sh

benchmark/PaddleOCR_DBNet/test_tipc/benchmark_train.sh

+#!/bin/bash
+source test_tipc/common_func.sh
+
+# run benchmark sh 
+# Usage:
+# bash run_benchmark_train.sh config.txt params
+# or 
+# bash run_benchmark_train.sh config.txt
+
+function func_parser_params(){
+    strs=$1
+    IFS="="
+    array=(${strs})
+    tmp=${array[1]}
+    echo ${tmp}
+}
+
+function set_dynamic_epoch(){
+    string=$1
+    num=$2
+    _str=${string:1:6}
+    IFS="C"
+    arr=(${_str})
+    M=${arr[0]}
+    P=${arr[1]}
+    ep=`expr $num \* $M \* $P`
+    echo $ep
+}
+
+function func_sed_params(){
+    filename=$1
+    line=$2
+    param_value=$3
+    params=`sed -n "${line}p" $filename`
+    IFS=":"
+    array=(${params})
+    key=${array[0]}
+    value=${array[1]}
+
+    new_params="${key}:${param_value}"
+    IFS=";"
+    cmd="sed -i '${line}s/.*/${new_params}/' '${filename}'"
+    eval $cmd
+}
+
+function set_gpu_id(){
+    string=$1
+    _str=${string:1:6}
+    IFS="C"
+    arr=(${_str})
+    M=${arr[0]}
+    P=${arr[1]}
+    gn=`expr $P - 1`
+    gpu_num=`expr $gn / $M`
+    seq=`seq -s "," 0 $gpu_num`
+    echo $seq
+}
+
+function get_repo_name(){
+    IFS=";"
+    cur_dir=$(pwd)
+    IFS="/"
+    arr=(${cur_dir})
+    echo ${arr[-1]}
+}
+
+FILENAME=$1
+# copy FILENAME as new
+new_filename="./test_tipc/benchmark_train.txt"
+cmd=`yes|cp $FILENAME $new_filename`
+FILENAME=$new_filename
+# MODE must be one of ['benchmark_train']
+MODE=$2
+PARAMS=$3
+
+to_static=""
+# parse "to_static" options and modify trainer into "to_static_trainer"
+if [[ $PARAMS =~ "dynamicTostatic" ]] ;then
+   to_static="d2sT_"
+   sed -i 's/trainer:norm_train/trainer:to_static_train/g' $FILENAME
+   # clear PARAM contents
+   if [ $PARAMS = "to_static" ] ;then
+    PARAMS=""
+   fi
+fi
+# bash test_tipc/benchmark_train.sh test_tipc/configs/det_mv3_db_v2_0/train_benchmark.txt  benchmark_train dynamic_bs8_fp32_DP_N1C8
+# bash test_tipc/benchmark_train.sh test_tipc/configs/det_mv3_db_v2_0/train_benchmark.txt  benchmark_train dynamicTostatic_bs8_fp32_DP_N1C8
+# bash test_tipc/benchmark_train.sh test_tipc/configs/det_mv3_db_v2_0/train_benchmark.txt  benchmark_train dynamic_bs8_null_DP_N1C1
+IFS=$'\n'
+# parser params from train_benchmark.txt
+dataline=`cat $FILENAME`
+# parser params
+IFS=$'\n'
+lines=(${dataline})
+model_name=$(func_parser_value "${lines[1]}")
+python_name=$(func_parser_value "${lines[2]}")
+
+# set env
+python=${python_name}
+export str_tmp=$(echo `pip list|grep paddlepaddle-gpu|awk -F ' ' '{print $2}'`)
+export frame_version=${str_tmp%%.post*}
+export frame_commit=$(echo `${python} -c "import paddle;print(paddle.version.commit)"`)
+
+# 获取benchmark_params所在的行数
+line_num=`grep -n -w "train_benchmark_params" $FILENAME  | cut -d ":" -f 1`
+# for train log parser
+batch_size=$(func_parser_value "${lines[line_num]}")
+line_num=`expr $line_num + 1`
+fp_items=$(func_parser_value "${lines[line_num]}")
+line_num=`expr $line_num + 1`
+epoch=$(func_parser_value "${lines[line_num]}")
+
+line_num=`expr $line_num + 1`
+profile_option_key=$(func_parser_key "${lines[line_num]}")
+profile_option_params=$(func_parser_value "${lines[line_num]}")
+profile_option="${profile_option_key}:${profile_option_params}"
+
+line_num=`expr $line_num + 1`
+flags_value=$(func_parser_value "${lines[line_num]}")
+# set flags
+IFS=";"
+flags_list=(${flags_value})
+for _flag in ${flags_list[*]}; do
+    cmd="export ${_flag}"
+    eval $cmd
+done
+
+# set log_name
+repo_name=$(get_repo_name )
+SAVE_LOG=${BENCHMARK_LOG_DIR:-$(pwd)}   # */benchmark_log
+mkdir -p "${SAVE_LOG}/benchmark_log/"
+status_log="${SAVE_LOG}/benchmark_log/results.log"
+
+# The number of lines in which train params can be replaced.
+line_python=3
+line_gpuid=4
+line_precision=6
+line_epoch=7
+line_batchsize=9
+line_profile=13
+line_eval_py=24
+line_export_py=30
+
+func_sed_params "$FILENAME" "${line_eval_py}" "null"
+func_sed_params "$FILENAME" "${line_export_py}" "null"
+func_sed_params "$FILENAME" "${line_python}"  "$python"
+
+# if params
+if  [ ! -n "$PARAMS" ] ;then
+    # PARAMS input is not a word.
+    IFS="|"
+    batch_size_list=(${batch_size})
+    fp_items_list=(${fp_items})
+    device_num_list=(N1C4)
+    run_mode="DP"
+elif [[ ${PARAMS} = "dynamicTostatic" ]];then
+    IFS="|"
+    model_type=$PARAMS
+    batch_size_list=(${batch_size})
+    fp_items_list=(${fp_items})
+    device_num_list=(N1C4)
+    run_mode="DP"
+else
+    # parser params from input: modeltype_bs${bs_item}_${fp_item}_${run_mode}_${device_num}
+    IFS="_"
+    params_list=(${PARAMS})
+    model_type=${params_list[0]}
+    batch_size=${params_list[1]}
+    batch_size=`echo  ${batch_size} | tr -cd "[0-9]" `
+    precision=${params_list[2]}
+    run_mode=${params_list[3]}
+    device_num=${params_list[4]}
+    IFS=";"
+
+    if [ ${precision} = "fp16" ];then
+        precision="amp"
+    fi
+
+    epoch=$(set_dynamic_epoch $device_num $epoch)
+    fp_items_list=($precision)
+    batch_size_list=($batch_size)
+    device_num_list=($device_num)
+fi
+
+IFS="|"
+for batch_size in ${batch_size_list[*]}; do 
+    for train_precision in ${fp_items_list[*]}; do
+        for device_num in ${device_num_list[*]}; do
+            # sed batchsize and precision
+            if [ ${train_precision} = "amp" ];then
+                precision="fp16"
+            else
+                precision="fp32"
+            fi
+
+            func_sed_params "$FILENAME" "${line_precision}" "$train_precision"
+            func_sed_params "$FILENAME" "${line_batchsize}" "$MODE=$batch_size"
+            func_sed_params "$FILENAME" "${line_epoch}" "$MODE=$epoch"
+            gpu_id=$(set_gpu_id $device_num)
+
+            if [ ${#gpu_id} -le 1 ];then
+                log_path="$SAVE_LOG/profiling_log"
+                mkdir -p $log_path
+                log_name="${repo_name}_${model_name}_bs${batch_size}_${precision}_${run_mode}_${device_num}_${to_static}profiling"
+                func_sed_params "$FILENAME" "${line_gpuid}" "0"  # sed used gpu_id 
+                # set profile_option params
+                tmp=`sed -i "${line_profile}s/.*/${profile_option}/" "${FILENAME}"`
+
+                # run test_train_inference_python.sh
+                cmd="bash test_tipc/test_train_inference_python.sh ${FILENAME} benchmark_train > ${log_path}/${log_name} 2>&1 "
+                echo $cmd
+                eval $cmd
+                eval "cat ${log_path}/${log_name}"
+
+                # without profile
+                log_path="$SAVE_LOG/train_log"
+                speed_log_path="$SAVE_LOG/index"
+                mkdir -p $log_path
+                mkdir -p $speed_log_path
+                log_name="${repo_name}_${model_name}_bs${batch_size}_${precision}_${run_mode}_${device_num}_${to_static}log"
+                speed_log_name="${repo_name}_${model_name}_bs${batch_size}_${precision}_${run_mode}_${device_num}_${to_static}speed"
+                func_sed_params "$FILENAME" "${line_profile}" "null"  # sed profile_id as null
+                cmd="bash test_tipc/test_train_inference_python.sh ${FILENAME} benchmark_train > ${log_path}/${log_name} 2>&1 "
+                echo $cmd
+                job_bt=`date '+%Y%m%d%H%M%S'`
+                eval $cmd
+                job_et=`date '+%Y%m%d%H%M%S'`
+                export model_run_time=$((${job_et}-${job_bt}))
+                eval "cat ${log_path}/${log_name}"
+
+                # parser log
+                _model_name="${model_name}_bs${batch_size}_${precision}_${run_mode}"
+                cmd="${python} ${BENCHMARK_ROOT}/scripts/analysis.py --filename ${log_path}/${log_name} \
+                        --speed_log_file '${speed_log_path}/${speed_log_name}' \
+                        --model_name ${_model_name} \
+                        --base_batch_size ${batch_size} \
+                        --run_mode ${run_mode} \
+                        --fp_item ${precision} \
+                        --keyword ips: \
+                        --skip_steps 2 \
+                        --device_num ${device_num} \
+                        --speed_unit samples/s \
+                        --convergence_key loss: "
+                echo $cmd
+                eval $cmd
+                last_status=${PIPESTATUS[0]}
+                status_check $last_status "${cmd}" "${status_log}"
+            else
+                IFS=";"
+                unset_env=`unset CUDA_VISIBLE_DEVICES`
+                log_path="$SAVE_LOG/train_log"
+                speed_log_path="$SAVE_LOG/index"
+                mkdir -p $log_path
+                mkdir -p $speed_log_path
+                log_name="${repo_name}_${model_name}_bs${batch_size}_${precision}_${run_mode}_${device_num}_${to_static}log"
+                speed_log_name="${repo_name}_${model_name}_bs${batch_size}_${precision}_${run_mode}_${device_num}_${to_static}speed"
+                func_sed_params "$FILENAME" "${line_gpuid}" "$gpu_id"  # sed used gpu_id 
+                func_sed_params "$FILENAME" "${line_profile}" "null"  # sed --profile_option as null
+                cmd="bash test_tipc/test_train_inference_python.sh ${FILENAME} benchmark_train > ${log_path}/${log_name} 2>&1 "
+                echo $cmd
+                job_bt=`date '+%Y%m%d%H%M%S'`
+                eval $cmd
+                job_et=`date '+%Y%m%d%H%M%S'`
+                export model_run_time=$((${job_et}-${job_bt}))
+                eval "cat ${log_path}/${log_name}"
+                # parser log
+                _model_name="${model_name}_bs${batch_size}_${precision}_${run_mode}"
+                
+                cmd="${python} ${BENCHMARK_ROOT}/scripts/analysis.py --filename ${log_path}/${log_name} \
+                        --speed_log_file '${speed_log_path}/${speed_log_name}' \
+                        --model_name ${_model_name} \
+                        --base_batch_size ${batch_size} \
+                        --run_mode ${run_mode} \
+                        --fp_item ${precision} \
+                        --keyword ips: \
+                        --skip_steps 2 \
+                        --device_num ${device_num} \
+                        --speed_unit images/s \
+                        --convergence_key loss: "
+                echo $cmd
+                eval $cmd
+                last_status=${PIPESTATUS[0]}
+                status_check $last_status "${cmd}" "${status_log}"
+            fi
+        done
+    done
+done

benchmark/PaddleOCR_DBNet/test_tipc/common_func.sh

+#!/bin/bash
+
+function func_parser_key(){
+    strs=$1
+    IFS=":"
+    array=(${strs})
+    tmp=${array[0]}
+    echo ${tmp}
+}
+
+function func_parser_value(){
+    strs=$1
+    IFS=":"
+    array=(${strs})
+    tmp=${array[1]}
+    echo ${tmp}
+}
+
+function func_set_params(){
+    key=$1
+    value=$2
+    if [ ${key}x = "null"x ];then
+        echo " "
+    elif [[ ${value} = "null" ]] || [[ ${value} = " " ]] || [ ${#value} -le 0 ];then
+        echo " "
+    else 
+        echo "${key}=${value}"
+    fi
+}
+
+function func_parser_params(){
+    strs=$1
+    MODE=$2
+    IFS=":"
+    array=(${strs})
+    key=${array[0]}
+    tmp=${array[1]}
+    IFS="|"
+    res=""
+    for _params in ${tmp[*]}; do
+        IFS="="
+        array=(${_params})
+        mode=${array[0]}
+        value=${array[1]}
+        if [[ ${mode} = ${MODE} ]]; then
+            IFS="|"
+            #echo $(func_set_params "${mode}" "${value}")
+            echo $value
+            break
+        fi
+        IFS="|"
+    done
+    echo ${res}
+}
+
+function status_check(){
+    last_status=$1   # the exit code
+    run_command=$2
+    run_log=$3
+    model_name=$4
+    log_path=$5
+    if [ $last_status -eq 0 ]; then
+        echo -e "\033[33m Run successfully with command - ${model_name} - ${run_command} - ${log_path} \033[0m" | tee -a ${run_log}
+    else
+        echo -e "\033[33m Run failed with command - ${model_name} - ${run_command} - ${log_path} \033[0m" | tee -a ${run_log}
+    fi
+}