mmdetection 選用自定義 backbone訓練

學習率

lr = (base_lr / 8) x num_gpus x (img_per_gpu/2)

其中 base_lr 是源碼中給定的 學習率，這是在 8張GPU上面，每張GPU上面放2張圖片得到的學習率，所以當對應的GPU數目和每張GPU上的圖片數目發生改變時，學習率成正比例變化。

選用新的backbone來訓練

這里選用 res2net_26w_6s 作為backbone;
以cascade_rcnn_r50_fpn_1x.py 作為config文件

• 在 mmdetection-master\mmdet\models\backbones中新建一個 res2net.py文件，並將模型代碼復制進去 https://github.com/Res2Net/Res2Net-PretrainedModels/blob/master/res2net.py

• 由於這里需要多尺度特征圖，可參考 原有的 resnet.py，返回的是stage1,stage2,stage3,stage4組成的list，因此新增的 res2net.py的代碼需要進行修改

  • 1). 源碼：

    class Res2Net(nn.Module):
       def __init__(self, block, layers, baseWidth = 26, scale = 4, num_classes=1000):
  

  修改：添加一個register；需要再import from ..registry import BACKBONES; 同時把block中的參數先寫上默認參數，不然后面的config文件中傳 block名字時比較麻煩

    @BACKBONES.register_module
    class Res2Net(nn.Module):
       def __init__(self, block=Bottle2neck, layers=[3,4,6,3], baseWidth=26, scale=6, num_classes=1000):
  

  • 2). 源碼：class Res2Net下面的 forward

        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)
    
        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
    
        return x
    

    修改：返回stage1, stage2,stage3,stage4

        def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)
    
        x1 = self.layer1(x)
        x2 = self.layer2(x1)
        x3 = self.layer3(x2)
        x4 = self.layer4(x3)
    
        #x = self.avgpool(x)
        #x = x.view(x.size(0), -1)
        #x = self.fc(x)
    
        return [x1,x2,x3,x4]
    

  • 3). 增加一個 init_weights函數(這邊是不添加就報錯，所以就直接從 resnet.py 中復制過來了)，如resnet.py中一樣，修改對應的block名稱

      def init_weights(self, pretrained=None):
        if isinstance(pretrained, str):
            from mmdet.apis import get_root_logger
            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.dcn is not None:
                for m in self.modules():
                    if isinstance(m, Bottle2neck) and hasattr(
                            m, 'conv2_offset'):
                        constant_init(m.conv2_offset, 0)
  
            if self.zero_init_residual:
                for m in self.modules():
                    if isinstance(m, Bottle2neck):
                        constant_init(m.norm3, 0)
                    # elif isinstance(m, BasicBlock):
                    #     constant_init(m.norm2, 0)
        else:
            raise TypeError('pretrained must be a str or None')
  

• 修改 config 文件,cascade_rcnn_r50_fpn_1x.py
  源碼：

# model settings
model = dict(
    type='CascadeRCNN',
    num_stages=3,
    pretrained='torchvision://resnet50',
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        style='pytorch'),

修改：

model = dict(
    type='CascadeRCNN',
    num_stages=3,
    #pretrained='torchvision://resnet50',
    pretrained='/media/mtc/dac70756-6922-445c-9cbe-58847ebdc56f/zql/mmdetection/pretrained_models/res2net50_26w_6s-19041792.pth',
    backbone=dict(
        type='Res2Net',
        layers=[3,4,6,3], baseWidth=26, scale=6, num_classes=1000,
        ),