Python torch.nn.Conv2d() Examples

def __init__(self):
        super(Model2, self).__init__()

        # fine tuning the ResNet helped significantly with the accuracy
        base_model = MyResNet(BasicBlock, [2, 2, 2, 2])
        base_model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
        # code needed to deactivate fine tuning of resnet
        #for param in base_model.parameters():
        #    param.requires_grad = False
        self.base_model = base_model
        self.drop0 = nn.Dropout2d(0.05)

        self.conv1 = nn.Conv2d(512, 256, 3, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(256)
        self.drop1 = nn.Dropout2d(0.05)

        self.conv2 = nn.Conv2d(256, 128, 3, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(128)
        self.drop2 = nn.Dropout2d(0.05)

        self.conv3 = nn.Conv2d(128, 1+9, 3, padding=1, bias=False) 

def __init__(self, block, layers, num_classes=1000):
        self.inplanes = 64
        super(MyResNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        # note the increasing dilation
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2, dilation=1)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=1, dilation=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=1, dilation=4)

        # these layers will not be used
        self.avgpool = nn.AvgPool2d(7)
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        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, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_() 

def __init__(self, in_channels, out_channels, dilations=(1, 3, 6, 1)):
        super().__init__()
        assert dilations[-1] == 1
        self.aspp = nn.ModuleList()
        for dilation in dilations:
            kernel_size = 3 if dilation > 1 else 1
            padding = dilation if dilation > 1 else 0
            conv = nn.Conv2d(
                in_channels,
                out_channels,
                kernel_size=kernel_size,
                stride=1,
                dilation=dilation,
                padding=padding,
                bias=True)
            self.aspp.append(conv)
        self.gap = nn.AdaptiveAvgPool2d(1)
        self.init_weights() 

def __init__(self, block, layers, num_classes=1000):
    self.inplanes = 64
    super(ResNet, self).__init__()
    self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                 bias=False)
    self.bn1 = nn.BatchNorm2d(64)
    self.relu = nn.ReLU(inplace=True)
    # maxpool different from pytorch-resnet, to match tf-faster-rcnn
    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)
    self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
    # use stride 1 for the last conv4 layer (same as tf-faster-rcnn)
    self.layer4 = self._make_layer(block, 512, layers[3], stride=1)

    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, nn.BatchNorm2d):
        m.weight.data.fill_(1)
        m.bias.data.zero_() 

def __init__(self, in_planes, cardinality=32, bottleneck_width=4, stride=1):
        super(Block, self).__init__()
        group_width = cardinality * bottleneck_width
        self.conv1 = nn.Conv2d(in_planes, group_width, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(group_width)
        self.conv2 = nn.Conv2d(group_width, group_width, kernel_size=3, stride=stride, padding=1, groups=cardinality, bias=False)
        self.bn2 = nn.BatchNorm2d(group_width)
        self.conv3 = nn.Conv2d(group_width, self.expansion*group_width, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(self.expansion*group_width)

        self.shortcut = nn.Sequential()
        if stride != 1 or in_planes != self.expansion*group_width:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_planes, self.expansion*group_width, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(self.expansion*group_width)
            ) 

def _init_modules(self): 
    self._init_head_tail()

    # rpn
    self.rpn_net = nn.Conv2d(self._net_conv_channels, cfg.RPN_CHANNELS, [3, 3], padding=1)

    self.rpn_cls_score_net = nn.Conv2d(cfg.RPN_CHANNELS, self._num_anchors * 2, [1, 1])
    
    self.rpn_bbox_pred_net = nn.Conv2d(cfg.RPN_CHANNELS, self._num_anchors * 4, [1, 1])

    self.cls_score_net_fast = nn.Linear(self._fc7_channels, self._num_classes+1)
    self.bbox_pred_net_fast = nn.Linear(self._fc7_channels, (self._num_classes+1) * 4)


    self.cls_score_net = nn.Linear(self._fc7_channels, self._num_classes)  # between class
    self.bbox_pred_net = nn.Linear(self._fc7_channels, self._num_classes)  # between boxes

    self.init_weights() 

def _make_layer(self, block, planes, blocks, stride=1, dilation=1):
        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),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, 1, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            # here with dilation
            layers.append(block(self.inplanes, planes, dilation=dilation))

        return nn.Sequential(*layers) 

def _make_layer(self, block, planes, blocks, stride=1):
    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),
        nn.BatchNorm2d(planes * block.expansion),
      )

    layers = []
    layers.append(block(self.inplanes, planes, stride, downsample))
    self.inplanes = planes * block.expansion
    for i in range(1, blocks):
      layers.append(block(self.inplanes, planes))

    return nn.Sequential(*layers) 

def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, 3, padding=1)
        self.bn1 = nn.BatchNorm2d(16)

        self.conv2 = nn.Conv2d(16, 32, 3, padding=1)
        self.bn2 = nn.BatchNorm2d(32)

        self.conv3 = nn.Conv2d(32, 64, 3, padding=1)
        self.bn3 = nn.BatchNorm2d(64)

        self.conv4 = nn.Conv2d(64, 128, 3, padding=1)
        self.bn4 = nn.BatchNorm2d(128)

        self.conv5 = nn.Conv2d(128, 128, 3, dilation=2, padding=2)
        self.bn5 = nn.BatchNorm2d(128)

        self.conv6 = nn.Conv2d(128, 128, 3, dilation=4, padding=4)
        self.bn6 = nn.BatchNorm2d(128)

        self.conv7 = nn.Conv2d(128, 1+9, 3, padding=1) 

def init_weights(self, pretrained=None):
        """Initialize the weights in backbone.

        Args:
            pretrained (str, optional): Path to pre-trained weights.
                Defaults to None.
        """
        if isinstance(pretrained, str):
            logger = get_root_logger()
            load_checkpoint(self, pretrained, strict=False, logger=logger)
        elif pretrained is None:
            for m in self.modules():
                if isinstance(m, nn.Conv2d):
                    kaiming_init(m)
                elif isinstance(m, (_BatchNorm, nn.GroupNorm)):
                    constant_init(m, 1)

            if self.zero_init_residual:
                for m in self.modules():
                    if isinstance(m, Bottleneck):
                        constant_init(m.norm3, 0)
                    elif isinstance(m, BasicBlock):
                        constant_init(m.norm2, 0)
        else:
            raise TypeError('pretrained must be a str or None') 

def init_weights(self, pretrained=None):
        """Initialize the weights in the module.

        Args:
            pretrained (str, optional): Path to pre-trained weights.
                Defaults to None.
        """
        if isinstance(pretrained, str):
            logger = get_root_logger()
            load_checkpoint(self, pretrained, strict=False, logger=logger)
        elif pretrained is None:
            for m in self.modules():
                if isinstance(m, nn.Conv2d):
                    kaiming_init(m)
                elif isinstance(m, nn.BatchNorm2d):
                    constant_init(m, 1)
        else:
            raise TypeError('pretrained must be a str or None') 

def __init__(self,
                 rfp_steps,
                 rfp_backbone,
                 aspp_out_channels,
                 aspp_dilations=(1, 3, 6, 1),
                 **kwargs):
        super().__init__(**kwargs)
        self.rfp_steps = rfp_steps
        self.rfp_modules = nn.ModuleList()
        for rfp_idx in range(1, rfp_steps):
            rfp_module = build_backbone(rfp_backbone)
            self.rfp_modules.append(rfp_module)
        self.rfp_aspp = ASPP(self.out_channels, aspp_out_channels,
                             aspp_dilations)
        self.rfp_weight = nn.Conv2d(
            self.out_channels,
            1,
            kernel_size=1,
            stride=1,
            padding=0,
            bias=True) 

def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size=3,
                 deformable_groups=4):
        super(FeatureAlign, self).__init__()
        offset_channels = kernel_size * kernel_size * 2
        self.conv_offset = nn.Conv2d(
            4, deformable_groups * offset_channels, 1, bias=False)
        self.conv_adaption = DeformConv(
            in_channels,
            out_channels,
            kernel_size=kernel_size,
            padding=(kernel_size - 1) // 2,
            deformable_groups=deformable_groups)
        self.relu = nn.ReLU(inplace=True) 

def __init__(self):
        super(CW2_Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, 3)
        self.bnm1 = nn.BatchNorm2d(32, momentum=0.1)
        self.conv2 = nn.Conv2d(32, 64, 3)
        self.bnm2 = nn.BatchNorm2d(64, momentum=0.1)
        self.conv3 = nn.Conv2d(64, 128, 3)
        self.bnm3 = nn.BatchNorm2d(128, momentum=0.1)
        self.conv4 = nn.Conv2d(128, 128, 3)
        self.bnm4 = nn.BatchNorm2d(128, momentum=0.1)
        self.fc1 = nn.Linear(3200, 256)
        #self.dropout1 = nn.Dropout(p=0.35, inplace=False)
        self.bnm5 = nn.BatchNorm1d(256, momentum=0.1)
        self.fc2 = nn.Linear(256, 256)
        self.bnm6 = nn.BatchNorm1d(256, momentum=0.1)
        self.fc3 = nn.Linear(256, 10)
        #self.dropout2 = nn.Dropout(p=0.35, inplace=False)
        #self.dropout3 = nn.Dropout(p=0.35, inplace=False) 

def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size=3,
                 deformable_groups=4):
        super(FeatureAdaption, self).__init__()
        offset_channels = kernel_size * kernel_size * 2
        self.conv_offset = nn.Conv2d(
            2, deformable_groups * offset_channels, 1, bias=False)
        self.conv_adaption = DeformConv(
            in_channels,
            out_channels,
            kernel_size=kernel_size,
            padding=(kernel_size - 1) // 2,
            deformable_groups=deformable_groups)
        self.relu = nn.ReLU(inplace=True) 

def __init__(self, in_planes, planes, stride=1):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)

        self.shortcut = nn.Sequential()
        if stride != 1 or in_planes != planes:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_planes, planes, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes)
            )

        # SE layers
        self.fc1 = nn.Conv2d(planes, planes//16, kernel_size=1)  # Use nn.Conv2d instead of nn.Linear
        self.fc2 = nn.Conv2d(planes//16, planes, kernel_size=1) 

def __init__(self, last_planes, in_planes, out_planes, dense_depth, stride, first_layer):
        super(Bottleneck, self).__init__()
        self.out_planes = out_planes
        self.dense_depth = dense_depth

        self.conv1 = nn.Conv2d(last_planes, in_planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(in_planes)
        self.conv2 = nn.Conv2d(in_planes, in_planes, kernel_size=3, stride=stride, padding=1, groups=32, bias=False)
        self.bn2 = nn.BatchNorm2d(in_planes)
        self.conv3 = nn.Conv2d(in_planes, out_planes+dense_depth, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(out_planes+dense_depth)

        self.shortcut = nn.Sequential()
        if first_layer:
            self.shortcut = nn.Sequential(
                nn.Conv2d(last_planes, out_planes+dense_depth, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(out_planes+dense_depth)
            ) 

def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10) 

def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=3, stride=2)
        self.conv2 = nn.Conv2d(10, 10, kernel_size=3, stride=2)
        #self.conv3 = nn.Conv2d(10, 10, kernel_size=3, stride=1)
        #self.drop = nn.Dropout2d()
        # self.fc1 = nn.Linear(784, 200)
        self.fc1 = nn.Linear(360, 200)
        self.fc2 = nn.Linear(200, 10) 

def test_conv2d():
    """
    CommandLine:
        xdoctest -m tests/test_wrappers.py test_conv2d
    """

    test_cases = OrderedDict([('in_w', [10, 20]), ('in_h', [10, 20]),
                              ('in_channel', [1, 3]), ('out_channel', [1, 3]),
                              ('kernel_size', [3, 5]), ('stride', [1, 2]),
                              ('padding', [0, 1]), ('dilation', [1, 2])])

    # train mode
    for in_h, in_w, in_cha, out_cha, k, s, p, d in product(
            *list(test_cases.values())):
        # wrapper op with 0-dim input
        x_empty = torch.randn(0, in_cha, in_h, in_w)
        torch.manual_seed(0)
        wrapper = Conv2d(in_cha, out_cha, k, stride=s, padding=p, dilation=d)
        wrapper_out = wrapper(x_empty)

        # torch op with 3-dim input as shape reference
        x_normal = torch.randn(3, in_cha, in_h, in_w).requires_grad_(True)
        torch.manual_seed(0)
        ref = nn.Conv2d(in_cha, out_cha, k, stride=s, padding=p, dilation=d)
        ref_out = ref(x_normal)

        assert wrapper_out.shape[0] == 0
        assert wrapper_out.shape[1:] == ref_out.shape[1:]

        wrapper_out.sum().backward()
        assert wrapper.weight.grad is not None
        assert wrapper.weight.grad.shape == wrapper.weight.shape

        assert torch.equal(wrapper(x_normal), ref_out)

    # eval mode
    x_empty = torch.randn(0, in_cha, in_h, in_w)
    wrapper = Conv2d(in_cha, out_cha, k, stride=s, padding=p, dilation=d)
    wrapper.eval()
    wrapper(x_empty) 

def __init__(self):
        super(Very_Small_Net, self).__init__()
        #self.conv1 = nn.Conv2d(1, 10, kernel_size=3, stride=2)
        #self.conv2 = nn.Conv2d(10, 10, kernel_size=3, stride=2)
        #self.conv3 = nn.Conv2d(10, 10, kernel_size=3, stride=1)
        #self.drop = nn.Dropout2d()
        # self.fc1 = nn.Linear(784, 200)
        self.fc1 = nn.Linear(784, 200)
        self.fc2 = nn.Linear(200, 10) 

def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size,
                 stride=1,
                 padding=0,
                 dilation=1,
                 groups=1,
                 deformable_groups=1,
                 bias=True):
        super(ModulatedDeformConv, self).__init__()
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.kernel_size = _pair(kernel_size)
        self.stride = stride
        self.padding = padding
        self.dilation = dilation
        self.groups = groups
        self.deformable_groups = deformable_groups
        self.with_bias = bias
        # enable compatibility with nn.Conv2d
        self.transposed = False
        self.output_padding = _single(0)

        self.weight = nn.Parameter(
            torch.Tensor(out_channels, in_channels // groups,
                         *self.kernel_size))
        if bias:
            self.bias = nn.Parameter(torch.Tensor(out_channels))
        else:
            self.register_parameter('bias', None)
        self.init_weights() 

def fuse_module(m):
    last_conv = None
    last_conv_name = None

    for name, child in m.named_children():
        if isinstance(child, (nn.BatchNorm2d, nn.SyncBatchNorm)):
            if last_conv is None:  # only fuse BN that is after Conv
                continue
            fused_conv = fuse_conv_bn(last_conv, child)
            m._modules[last_conv_name] = fused_conv
            # To reduce changes, set BN as Identity instead of deleting it.
            m._modules[name] = nn.Identity()
            last_conv = None
        elif isinstance(child, nn.Conv2d):
            last_conv = child
            last_conv_name = name
        else:
            fuse_module(child)
    return m 

def __init__(self, *args, **kwargs):
        super(ModulatedDeformConvPack, self).__init__(*args, **kwargs)

        self.conv_offset = nn.Conv2d(
            self.in_channels,
            self.deformable_groups * 3 * self.kernel_size[0] *
            self.kernel_size[1],
            kernel_size=self.kernel_size,
            stride=_pair(self.stride),
            padding=_pair(self.padding),
            dilation=_pair(self.dilation),
            bias=True)
        self.init_weights() 

def __init__(self, *args, **kwargs):
        super(DeformConvPack, self).__init__(*args, **kwargs)

        self.conv_offset = nn.Conv2d(
            self.in_channels,
            self.deformable_groups * 2 * self.kernel_size[0] *
            self.kernel_size[1],
            kernel_size=self.kernel_size,
            stride=_pair(self.stride),
            padding=_pair(self.padding),
            dilation=_pair(self.dilation),
            bias=True)
        self.init_offset() 

def __init__(self):
        super(LeNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(400, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10) 

def __init__(self, in_planes, n1x1, n3x3red, n3x3, n5x5red, n5x5, pool_planes):
        super(Inception, self).__init__()
        # 1x1 conv branch
        self.b1 = nn.Sequential(
            nn.Conv2d(in_planes, n1x1, kernel_size=1),
            nn.BatchNorm2d(n1x1),
            nn.ReLU(True),
        )

        # 1x1 conv -> 3x3 conv branch
        self.b2 = nn.Sequential(
            nn.Conv2d(in_planes, n3x3red, kernel_size=1),
            nn.BatchNorm2d(n3x3red),
            nn.ReLU(True),
            nn.Conv2d(n3x3red, n3x3, kernel_size=3, padding=1),
            nn.BatchNorm2d(n3x3),
            nn.ReLU(True),
        )

        # 1x1 conv -> 5x5 conv branch
        self.b3 = nn.Sequential(
            nn.Conv2d(in_planes, n5x5red, kernel_size=1),
            nn.BatchNorm2d(n5x5red),
            nn.ReLU(True),
            nn.Conv2d(n5x5red, n5x5, kernel_size=3, padding=1),
            nn.BatchNorm2d(n5x5),
            nn.ReLU(True),
            nn.Conv2d(n5x5, n5x5, kernel_size=3, padding=1),
            nn.BatchNorm2d(n5x5),
            nn.ReLU(True),
        )

        # 3x3 pool -> 1x1 conv branch
        self.b4 = nn.Sequential(
            nn.MaxPool2d(3, stride=1, padding=1),
            nn.Conv2d(in_planes, pool_planes, kernel_size=1),
            nn.BatchNorm2d(pool_planes),
            nn.ReLU(True),
        ) 

def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size,
                 stride=1,
                 padding=0,
                 dilation=1,
                 groups=1,
                 deformable_groups=1,
                 bias=False):
        super(DeformConv, self).__init__()

        assert not bias
        assert in_channels % groups == 0, \
            f'in_channels {in_channels} is not divisible by groups {groups}'
        assert out_channels % groups == 0, \
            f'out_channels {out_channels} is not divisible ' \
            f'by groups {groups}'

        self.in_channels = in_channels
        self.out_channels = out_channels
        self.kernel_size = _pair(kernel_size)
        self.stride = _pair(stride)
        self.padding = _pair(padding)
        self.dilation = _pair(dilation)
        self.groups = groups
        self.deformable_groups = deformable_groups
        # enable compatibility with nn.Conv2d
        self.transposed = False
        self.output_padding = _single(0)

        self.weight = nn.Parameter(
            torch.Tensor(out_channels, in_channels // self.groups,
                         *self.kernel_size))

        self.reset_parameters() 

def __init__(self, num_blocks, cardinality, bottleneck_width, num_classes=10):
        super(ResNeXt, self).__init__()
        self.cardinality = cardinality
        self.bottleneck_width = bottleneck_width
        self.in_planes = 64

        self.conv1 = nn.Conv2d(3, 64, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.layer1 = self._make_layer(num_blocks[0], 1)
        self.layer2 = self._make_layer(num_blocks[1], 2)
        self.layer3 = self._make_layer(num_blocks[2], 2)
        # self.layer4 = self._make_layer(num_blocks[3], 2)
        self.linear = nn.Linear(cardinality*bottleneck_width*8, num_classes) 

def __init__(self):
        super(CW_Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, 3)
        self.conv2 = nn.Conv2d(32, 32, 3)
        self.conv3 = nn.Conv2d(32, 64, 3)
        self.conv4 = nn.Conv2d(64, 64, 3)
        self.fc1 = nn.Linear(1600, 200)
        self.fc2 = nn.Linear(200, 200)
        self.fc3 = nn.Linear(200, 2) # Change to 10, 2 is just dummy!!!!