doctra 0.3.3__py3-none-any.whl → 0.4.1__py3-none-any.whl

doctra/third_party/docres/data/MBD/model/deep_lab_model/backbone/drn.py

@@ -0,0 +1,402 @@
+import torch.nn as nn
+import math
+import torch.utils.model_zoo as model_zoo
+from model.deep_lab_model.sync_batchnorm.batchnorm import SynchronizedBatchNorm2d
+
+webroot = 'http://dl.yf.io/drn/'
+
+model_urls = {
+    'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
+    'drn-c-26': webroot + 'drn_c_26-ddedf421.pth',
+    'drn-c-42': webroot + 'drn_c_42-9d336e8c.pth',
+    'drn-c-58': webroot + 'drn_c_58-0a53a92c.pth',
+    'drn-d-22': webroot + 'drn_d_22-4bd2f8ea.pth',
+    'drn-d-38': webroot + 'drn_d_38-eebb45f0.pth',
+    'drn-d-54': webroot + 'drn_d_54-0e0534ff.pth',
+    'drn-d-105': webroot + 'drn_d_105-12b40979.pth'
+}
+
+
+def conv3x3(in_planes, out_planes, stride=1, padding=1, dilation=1):
+    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
+                     padding=padding, bias=False, dilation=dilation)
+
+
+class BasicBlock(nn.Module):
+    expansion = 1
+
+    def __init__(self, inplanes, planes, stride=1, downsample=None,
+                 dilation=(1, 1), residual=True, BatchNorm=None):
+        super(BasicBlock, self).__init__()
+        self.conv1 = conv3x3(inplanes, planes, stride,
+                             padding=dilation[0], dilation=dilation[0])
+        self.bn1 = BatchNorm(planes)
+        self.relu = nn.ReLU(inplace=True)
+        self.conv2 = conv3x3(planes, planes,
+                             padding=dilation[1], dilation=dilation[1])
+        self.bn2 = BatchNorm(planes)
+        self.downsample = downsample
+        self.stride = stride
+        self.residual = residual
+
+    def forward(self, x):
+        residual = x
+
+        out = self.conv1(x)
+        out = self.bn1(out)
+        out = self.relu(out)
+
+        out = self.conv2(out)
+        out = self.bn2(out)
+
+        if self.downsample is not None:
+            residual = self.downsample(x)
+        if self.residual:
+            out += residual
+        out = self.relu(out)
+
+        return out
+
+
+class Bottleneck(nn.Module):
+    expansion = 4
+
+    def __init__(self, inplanes, planes, stride=1, downsample=None,
+                 dilation=(1, 1), residual=True, BatchNorm=None):
+        super(Bottleneck, self).__init__()
+        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
+        self.bn1 = BatchNorm(planes)
+        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
+                               padding=dilation[1], bias=False,
+                               dilation=dilation[1])
+        self.bn2 = BatchNorm(planes)
+        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
+        self.bn3 = BatchNorm(planes * 4)
+        self.relu = nn.ReLU(inplace=True)
+        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)
+        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 DRN(nn.Module):
+
+    def __init__(self, block, layers, arch='D',
+                 channels=(16, 32, 64, 128, 256, 512, 512, 512),
+                 BatchNorm=None):
+        super(DRN, self).__init__()
+        self.inplanes = channels[0]
+        self.out_dim = channels[-1]
+        self.arch = arch
+
+        if arch == 'C':
+            self.conv1 = nn.Conv2d(3, channels[0], kernel_size=7, stride=1,
+                                   padding=3, bias=False)
+            self.bn1 = BatchNorm(channels[0])
+            self.relu = nn.ReLU(inplace=True)
+
+            self.layer1 = self._make_layer(
+                BasicBlock, channels[0], layers[0], stride=1, BatchNorm=BatchNorm)
+            self.layer2 = self._make_layer(
+                BasicBlock, channels[1], layers[1], stride=2, BatchNorm=BatchNorm)
+
+        elif arch == 'D':
+            self.layer0 = nn.Sequential(
+                nn.Conv2d(3, channels[0], kernel_size=7, stride=1, padding=3,
+                          bias=False),
+                BatchNorm(channels[0]),
+                nn.ReLU(inplace=True)
+            )
+
+            self.layer1 = self._make_conv_layers(
+                channels[0], layers[0], stride=1, BatchNorm=BatchNorm)
+            self.layer2 = self._make_conv_layers(
+                channels[1], layers[1], stride=2, BatchNorm=BatchNorm)
+
+        self.layer3 = self._make_layer(block, channels[2], layers[2], stride=2, BatchNorm=BatchNorm)
+        self.layer4 = self._make_layer(block, channels[3], layers[3], stride=2, BatchNorm=BatchNorm)
+        self.layer5 = self._make_layer(block, channels[4], layers[4],
+                                       dilation=2, new_level=False, BatchNorm=BatchNorm)
+        self.layer6 = None if layers[5] == 0 else \
+            self._make_layer(block, channels[5], layers[5], dilation=4,
+                             new_level=False, BatchNorm=BatchNorm)
+
+        if arch == 'C':
+            self.layer7 = None if layers[6] == 0 else \
+                self._make_layer(BasicBlock, channels[6], layers[6], dilation=2,
+                                 new_level=False, residual=False, BatchNorm=BatchNorm)
+            self.layer8 = None if layers[7] == 0 else \
+                self._make_layer(BasicBlock, channels[7], layers[7], dilation=1,
+                                 new_level=False, residual=False, BatchNorm=BatchNorm)
+        elif arch == 'D':
+            self.layer7 = None if layers[6] == 0 else \
+                self._make_conv_layers(channels[6], layers[6], dilation=2, BatchNorm=BatchNorm)
+            self.layer8 = None if layers[7] == 0 else \
+                self._make_conv_layers(channels[7], layers[7], dilation=1, BatchNorm=BatchNorm)
+
+        self._init_weight()
+
+    def _init_weight(self):
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
+                m.weight.data.normal_(0, math.sqrt(2. / n))
+            elif isinstance(m, SynchronizedBatchNorm2d):
+                m.weight.data.fill_(1)
+                m.bias.data.zero_()
+            elif isinstance(m, nn.BatchNorm2d):
+                m.weight.data.fill_(1)
+                m.bias.data.zero_()
+
+
+    def _make_layer(self, block, planes, blocks, stride=1, dilation=1,
+                    new_level=True, residual=True, BatchNorm=None):
+        assert dilation == 1 or dilation % 2 == 0
+        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=False),
+                BatchNorm(planes * block.expansion),
+            )
+
+        layers = list()
+        layers.append(block(
+            self.inplanes, planes, stride, downsample,
+            dilation=(1, 1) if dilation == 1 else (
+                dilation // 2 if new_level else dilation, dilation),
+            residual=residual, BatchNorm=BatchNorm))
+        self.inplanes = planes * block.expansion
+        for i in range(1, blocks):
+            layers.append(block(self.inplanes, planes, residual=residual,
+                                dilation=(dilation, dilation), BatchNorm=BatchNorm))
+
+        return nn.Sequential(*layers)
+
+    def _make_conv_layers(self, channels, convs, stride=1, dilation=1, BatchNorm=None):
+        modules = []
+        for i in range(convs):
+            modules.extend([
+                nn.Conv2d(self.inplanes, channels, kernel_size=3,
+                          stride=stride if i == 0 else 1,
+                          padding=dilation, bias=False, dilation=dilation),
+                BatchNorm(channels),
+                nn.ReLU(inplace=True)])
+            self.inplanes = channels
+        return nn.Sequential(*modules)
+
+    def forward(self, x):
+        if self.arch == 'C':
+            x = self.conv1(x)
+            x = self.bn1(x)
+            x = self.relu(x)
+        elif self.arch == 'D':
+            x = self.layer0(x)
+
+        x = self.layer1(x)
+        x = self.layer2(x)
+
+        x = self.layer3(x)
+        low_level_feat = x
+
+        x = self.layer4(x)
+        x = self.layer5(x)
+
+        if self.layer6 is not None:
+            x = self.layer6(x)
+
+        if self.layer7 is not None:
+            x = self.layer7(x)
+
+        if self.layer8 is not None:
+            x = self.layer8(x)
+
+        return x, low_level_feat
+
+
+class DRN_A(nn.Module):
+
+    def __init__(self, block, layers, BatchNorm=None):
+        self.inplanes = 64
+        super(DRN_A, self).__init__()
+        self.out_dim = 512 * block.expansion
+        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
+                               bias=False)
+        self.bn1 = BatchNorm(64)
+        self.relu = nn.ReLU(inplace=True)
+        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
+        self.layer1 = self._make_layer(block, 64, layers[0], BatchNorm=BatchNorm)
+        self.layer2 = self._make_layer(block, 128, layers[1], stride=2, BatchNorm=BatchNorm)
+        self.layer3 = self._make_layer(block, 256, layers[2], stride=1,
+                                       dilation=2, BatchNorm=BatchNorm)
+        self.layer4 = self._make_layer(block, 512, layers[3], stride=1,
+                                       dilation=4, BatchNorm=BatchNorm)
+
+        self._init_weight()
+
+    def _init_weight(self):
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
+                m.weight.data.normal_(0, math.sqrt(2. / n))
+            elif isinstance(m, SynchronizedBatchNorm2d):
+                m.weight.data.fill_(1)
+                m.bias.data.zero_()
+            elif isinstance(m, nn.BatchNorm2d):
+                m.weight.data.fill_(1)
+                m.bias.data.zero_()
+
+    def _make_layer(self, block, planes, blocks, stride=1, dilation=1, BatchNorm=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=False),
+                BatchNorm(planes * block.expansion),
+            )
+
+        layers = []
+        layers.append(block(self.inplanes, planes, stride, downsample, BatchNorm=BatchNorm))
+        self.inplanes = planes * block.expansion
+        for i in range(1, blocks):
+            layers.append(block(self.inplanes, planes,
+                                dilation=(dilation, dilation, ), BatchNorm=BatchNorm))
+
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        x = self.conv1(x)
+        x = self.bn1(x)
+        x = self.relu(x)
+        x = self.maxpool(x)
+
+        x = self.layer1(x)
+        x = self.layer2(x)
+        x = self.layer3(x)
+        x = self.layer4(x)
+
+        return x
+
+def drn_a_50(BatchNorm, pretrained=True):
+    model = DRN_A(Bottleneck, [3, 4, 6, 3], BatchNorm=BatchNorm)
+    if pretrained:
+        model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
+    return model
+
+
+def drn_c_26(BatchNorm, pretrained=True):
+    model = DRN(BasicBlock, [1, 1, 2, 2, 2, 2, 1, 1], arch='C', BatchNorm=BatchNorm)
+    if pretrained:
+        pretrained = model_zoo.load_url(model_urls['drn-c-26'])
+        del pretrained['fc.weight']
+        del pretrained['fc.bias']
+        model.load_state_dict(pretrained)
+    return model
+
+
+def drn_c_42(BatchNorm, pretrained=True):
+    model = DRN(BasicBlock, [1, 1, 3, 4, 6, 3, 1, 1], arch='C', BatchNorm=BatchNorm)
+    if pretrained:
+        pretrained = model_zoo.load_url(model_urls['drn-c-42'])
+        del pretrained['fc.weight']
+        del pretrained['fc.bias']
+        model.load_state_dict(pretrained)
+    return model
+
+
+def drn_c_58(BatchNorm, pretrained=True):
+    model = DRN(Bottleneck, [1, 1, 3, 4, 6, 3, 1, 1], arch='C', BatchNorm=BatchNorm)
+    if pretrained:
+        pretrained = model_zoo.load_url(model_urls['drn-c-58'])
+        del pretrained['fc.weight']
+        del pretrained['fc.bias']
+        model.load_state_dict(pretrained)
+    return model
+
+
+def drn_d_22(BatchNorm, pretrained=True):
+    model = DRN(BasicBlock, [1, 1, 2, 2, 2, 2, 1, 1], arch='D', BatchNorm=BatchNorm)
+    if pretrained:
+        pretrained = model_zoo.load_url(model_urls['drn-d-22'])
+        del pretrained['fc.weight']
+        del pretrained['fc.bias']
+        model.load_state_dict(pretrained)
+    return model
+
+
+def drn_d_24(BatchNorm, pretrained=True):
+    model = DRN(BasicBlock, [1, 1, 2, 2, 2, 2, 2, 2], arch='D', BatchNorm=BatchNorm)
+    if pretrained:
+        pretrained = model_zoo.load_url(model_urls['drn-d-24'])
+        del pretrained['fc.weight']
+        del pretrained['fc.bias']
+        model.load_state_dict(pretrained)
+    return model
+
+
+def drn_d_38(BatchNorm, pretrained=True):
+    model = DRN(BasicBlock, [1, 1, 3, 4, 6, 3, 1, 1], arch='D', BatchNorm=BatchNorm)
+    if pretrained:
+        pretrained = model_zoo.load_url(model_urls['drn-d-38'])
+        del pretrained['fc.weight']
+        del pretrained['fc.bias']
+        model.load_state_dict(pretrained)
+    return model
+
+
+def drn_d_40(BatchNorm, pretrained=True):
+    model = DRN(BasicBlock, [1, 1, 3, 4, 6, 3, 2, 2], arch='D', BatchNorm=BatchNorm)
+    if pretrained:
+        pretrained = model_zoo.load_url(model_urls['drn-d-40'])
+        del pretrained['fc.weight']
+        del pretrained['fc.bias']
+        model.load_state_dict(pretrained)
+    return model
+
+
+def drn_d_54(BatchNorm, pretrained=True):
+    model = DRN(Bottleneck, [1, 1, 3, 4, 6, 3, 1, 1], arch='D', BatchNorm=BatchNorm)
+    if pretrained:
+        pretrained = model_zoo.load_url(model_urls['drn-d-54'])
+        del pretrained['fc.weight']
+        del pretrained['fc.bias']
+        model.load_state_dict(pretrained)
+    return model
+
+
+def drn_d_105(BatchNorm, pretrained=True):
+    model = DRN(Bottleneck, [1, 1, 3, 4, 23, 3, 1, 1], arch='D', BatchNorm=BatchNorm)
+    if pretrained:
+        pretrained = model_zoo.load_url(model_urls['drn-d-105'])
+        del pretrained['fc.weight']
+        del pretrained['fc.bias']
+        model.load_state_dict(pretrained)
+    return model
+
+if __name__ == "__main__":
+    import torch
+    model = drn_a_50(BatchNorm=nn.BatchNorm2d, pretrained=True)
+    input = torch.rand(1, 3, 512, 512)
+    output, low_level_feat = model(input)
+    print(output.size())
+    print(low_level_feat.size())

doctra/third_party/docres/data/MBD/model/deep_lab_model/backbone/mobilenet.py

@@ -0,0 +1,151 @@
+import torch
+import torch.nn.functional as F
+import torch.nn as nn
+import math
+from model.deep_lab_model.sync_batchnorm.batchnorm import SynchronizedBatchNorm2d
+import torch.utils.model_zoo as model_zoo
+
+def conv_bn(inp, oup, stride, BatchNorm):
+    return nn.Sequential(
+        nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
+        BatchNorm(oup),
+        nn.ReLU6(inplace=True)
+    )
+
+
+def fixed_padding(inputs, kernel_size, dilation):
+    kernel_size_effective = kernel_size + (kernel_size - 1) * (dilation - 1)
+    pad_total = kernel_size_effective - 1
+    pad_beg = pad_total // 2
+    pad_end = pad_total - pad_beg
+    padded_inputs = F.pad(inputs, (pad_beg, pad_end, pad_beg, pad_end))
+    return padded_inputs
+
+
+class InvertedResidual(nn.Module):
+    def __init__(self, inp, oup, stride, dilation, expand_ratio, BatchNorm):
+        super(InvertedResidual, self).__init__()
+        self.stride = stride
+        assert stride in [1, 2]
+
+        hidden_dim = round(inp * expand_ratio)
+        self.use_res_connect = self.stride == 1 and inp == oup
+        self.kernel_size = 3
+        self.dilation = dilation
+
+        if expand_ratio == 1:
+            self.conv = nn.Sequential(
+                # dw
+                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 0, dilation, groups=hidden_dim, bias=False),
+                BatchNorm(hidden_dim),
+                nn.ReLU6(inplace=True),
+                # pw-linear
+                nn.Conv2d(hidden_dim, oup, 1, 1, 0, 1, 1, bias=False),
+                BatchNorm(oup),
+            )
+        else:
+            self.conv = nn.Sequential(
+                # pw
+                nn.Conv2d(inp, hidden_dim, 1, 1, 0, 1, bias=False),
+                BatchNorm(hidden_dim),
+                nn.ReLU6(inplace=True),
+                # dw
+                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 0, dilation, groups=hidden_dim, bias=False),
+                BatchNorm(hidden_dim),
+                nn.ReLU6(inplace=True),
+                # pw-linear
+                nn.Conv2d(hidden_dim, oup, 1, 1, 0, 1, bias=False),
+                BatchNorm(oup),
+            )
+
+    def forward(self, x):
+        x_pad = fixed_padding(x, self.kernel_size, dilation=self.dilation)
+        if self.use_res_connect:
+            x = x + self.conv(x_pad)
+        else:
+            x = self.conv(x_pad)
+        return x
+
+
+class MobileNetV2(nn.Module):
+    def __init__(self, output_stride=8, BatchNorm=None, width_mult=1., pretrained=True):
+        super(MobileNetV2, self).__init__()
+        block = InvertedResidual
+        input_channel = 32
+        current_stride = 1
+        rate = 1
+        interverted_residual_setting = [
+            # t, c, n, s
+            [1, 16, 1, 1],
+            [6, 24, 2, 2],
+            [6, 32, 3, 2],
+            [6, 64, 4, 2],
+            [6, 96, 3, 1],
+            [6, 160, 3, 2],
+            [6, 320, 1, 1],
+        ]
+
+        # building first layer
+        input_channel = int(input_channel * width_mult)
+        self.features = [conv_bn(3, input_channel, 2, BatchNorm)]
+        current_stride *= 2
+        # building inverted residual blocks
+        for t, c, n, s in interverted_residual_setting:
+            if current_stride == output_stride:
+                stride = 1
+                dilation = rate
+                rate *= s
+            else:
+                stride = s
+                dilation = 1
+                current_stride *= s
+            output_channel = int(c * width_mult)
+            for i in range(n):
+                if i == 0:
+                    self.features.append(block(input_channel, output_channel, stride, dilation, t, BatchNorm))
+                else:
+                    self.features.append(block(input_channel, output_channel, 1, dilation, t, BatchNorm))
+                input_channel = output_channel
+        self.features = nn.Sequential(*self.features)
+        self._initialize_weights()
+
+        if pretrained:
+            self._load_pretrained_model()
+
+        self.low_level_features = self.features[0:4]
+        self.high_level_features = self.features[4:]
+
+    def forward(self, x):
+        low_level_feat = self.low_level_features(x)
+        x = self.high_level_features(low_level_feat)
+        return x, low_level_feat
+
+    def _load_pretrained_model(self):
+        pretrain_dict = model_zoo.load_url('http://jeff95.me/models/mobilenet_v2-6a65762b.pth')
+        model_dict = {}
+        state_dict = self.state_dict()
+        for k, v in pretrain_dict.items():
+            if k in state_dict:
+                model_dict[k] = v
+        state_dict.update(model_dict)
+        self.load_state_dict(state_dict)
+
+    def _initialize_weights(self):
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                # n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
+                # m.weight.data.normal_(0, math.sqrt(2. / n))
+                torch.nn.init.kaiming_normal_(m.weight)
+            elif isinstance(m, SynchronizedBatchNorm2d):
+                m.weight.data.fill_(1)
+                m.bias.data.zero_()
+            elif isinstance(m, nn.BatchNorm2d):
+                m.weight.data.fill_(1)
+                m.bias.data.zero_()
+
+if __name__ == "__main__":
+    input = torch.rand(1, 3, 512, 512)
+    model = MobileNetV2(output_stride=16, BatchNorm=nn.BatchNorm2d)
+    output, low_level_feat = model(input)
+    print(output.size())
+    print(low_level_feat.size())