Shortcuts

Source code for mmdet.models.backbones.csp_darknet

# Copyright (c) OpenMMLab. All rights reserved.
import math

import torch
import torch.nn as nn
from mmcv.cnn import ConvModule, DepthwiseSeparableConvModule
from mmcv.runner import BaseModule
from torch.nn.modules.batchnorm import _BatchNorm

from ..builder import BACKBONES
from ..utils import CSPLayer


class Focus(nn.Module):
    """Focus width and height information into channel space.

    Args:
        in_channels (int): The input channels of this Module.
        out_channels (int): The output channels of this Module.
        kernel_size (int): The kernel size of the convolution. Default: 1
        stride (int): The stride of the convolution. Default: 1
        conv_cfg (dict): Config dict for convolution layer. Default: None,
            which means using conv2d.
        norm_cfg (dict): Config dict for normalization layer.
            Default: dict(type='BN', momentum=0.03, eps=0.001).
        act_cfg (dict): Config dict for activation layer.
            Default: dict(type='Swish').
    """

    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size=1,
                 stride=1,
                 conv_cfg=None,
                 norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
                 act_cfg=dict(type='Swish')):
        super().__init__()
        self.conv = ConvModule(
            in_channels * 4,
            out_channels,
            kernel_size,
            stride,
            padding=(kernel_size - 1) // 2,
            conv_cfg=conv_cfg,
            norm_cfg=norm_cfg,
            act_cfg=act_cfg)

    def forward(self, x):
        # shape of x (b,c,w,h) -> y(b,4c,w/2,h/2)
        patch_top_left = x[..., ::2, ::2]
        patch_top_right = x[..., ::2, 1::2]
        patch_bot_left = x[..., 1::2, ::2]
        patch_bot_right = x[..., 1::2, 1::2]
        x = torch.cat(
            (
                patch_top_left,
                patch_bot_left,
                patch_top_right,
                patch_bot_right,
            ),
            dim=1,
        )
        return self.conv(x)


class SPPBottleneck(BaseModule):
    """Spatial pyramid pooling layer used in YOLOv3-SPP.

    Args:
        in_channels (int): The input channels of this Module.
        out_channels (int): The output channels of this Module.
        kernel_sizes (tuple[int]): Sequential of kernel sizes of pooling
            layers. Default: (5, 9, 13).
        conv_cfg (dict): Config dict for convolution layer. Default: None,
            which means using conv2d.
        norm_cfg (dict): Config dict for normalization layer.
            Default: dict(type='BN').
        act_cfg (dict): Config dict for activation layer.
            Default: dict(type='Swish').
        init_cfg (dict or list[dict], optional): Initialization config dict.
            Default: None.
    """

    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_sizes=(5, 9, 13),
                 conv_cfg=None,
                 norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
                 act_cfg=dict(type='Swish'),
                 init_cfg=None):
        super().__init__(init_cfg)
        mid_channels = in_channels // 2
        self.conv1 = ConvModule(
            in_channels,
            mid_channels,
            1,
            stride=1,
            conv_cfg=conv_cfg,
            norm_cfg=norm_cfg,
            act_cfg=act_cfg)
        self.poolings = nn.ModuleList([
            nn.MaxPool2d(kernel_size=ks, stride=1, padding=ks // 2)
            for ks in kernel_sizes
        ])
        conv2_channels = mid_channels * (len(kernel_sizes) + 1)
        self.conv2 = ConvModule(
            conv2_channels,
            out_channels,
            1,
            conv_cfg=conv_cfg,
            norm_cfg=norm_cfg,
            act_cfg=act_cfg)

    def forward(self, x):
        x = self.conv1(x)
        x = torch.cat([x] + [pooling(x) for pooling in self.poolings], dim=1)
        x = self.conv2(x)
        return x


[docs]@BACKBONES.register_module() class CSPDarknet(BaseModule): """CSP-Darknet backbone used in YOLOv5 and YOLOX. Args: arch (str): Architecture of CSP-Darknet, from {P5, P6}. Default: P5. deepen_factor (float): Depth multiplier, multiply number of blocks in CSP layer by this amount. Default: 1.0. widen_factor (float): Width multiplier, multiply number of channels in each layer by this amount. Default: 1.0. out_indices (Sequence[int]): Output from which stages. Default: (2, 3, 4). frozen_stages (int): Stages to be frozen (stop grad and set eval mode). -1 means not freezing any parameters. Default: -1. use_depthwise (bool): Whether to use depthwise separable convolution. Default: False. arch_ovewrite(list): Overwrite default arch settings. Default: None. spp_kernal_sizes: (tuple[int]): Sequential of kernel sizes of SPP layers. Default: (5, 9, 13). conv_cfg (dict): Config dict for convolution layer. Default: None. norm_cfg (dict): Dictionary to construct and config norm layer. Default: dict(type='BN', requires_grad=True). act_cfg (dict): Config dict for activation layer. Default: dict(type='LeakyReLU', negative_slope=0.1). norm_eval (bool): Whether to set norm layers to eval mode, namely, freeze running stats (mean and var). Note: Effect on Batch Norm and its variants only. init_cfg (dict or list[dict], optional): Initialization config dict. Default: None. Example: >>> from mmdet.models import CSPDarknet >>> import torch >>> self = CSPDarknet(depth=53) >>> self.eval() >>> inputs = torch.rand(1, 3, 416, 416) >>> level_outputs = self.forward(inputs) >>> for level_out in level_outputs: ... print(tuple(level_out.shape)) ... (1, 256, 52, 52) (1, 512, 26, 26) (1, 1024, 13, 13) """ # From left to right: # in_channels, out_channels, num_blocks, add_identity, use_spp arch_settings = { 'P5': [[64, 128, 3, True, False], [128, 256, 9, True, False], [256, 512, 9, True, False], [512, 1024, 3, False, True]], 'P6': [[64, 128, 3, True, False], [128, 256, 9, True, False], [256, 512, 9, True, False], [512, 768, 3, True, False], [768, 1024, 3, False, True]] } def __init__(self, arch='P5', deepen_factor=1.0, widen_factor=1.0, out_indices=(2, 3, 4), frozen_stages=-1, use_depthwise=False, arch_ovewrite=None, spp_kernal_sizes=(5, 9, 13), conv_cfg=None, norm_cfg=dict(type='BN', momentum=0.03, eps=0.001), act_cfg=dict(type='Swish'), norm_eval=False, init_cfg=dict( type='Kaiming', layer='Conv2d', a=math.sqrt(5), distribution='uniform', mode='fan_in', nonlinearity='leaky_relu')): super().__init__(init_cfg) arch_setting = self.arch_settings[arch] if arch_ovewrite: arch_setting = arch_ovewrite assert set(out_indices).issubset( i for i in range(len(arch_setting) + 1)) if frozen_stages not in range(-1, len(arch_setting) + 1): raise ValueError('frozen_stages must be in range(-1, ' 'len(arch_setting) + 1). But received ' f'{frozen_stages}') self.out_indices = out_indices self.frozen_stages = frozen_stages self.use_depthwise = use_depthwise self.norm_eval = norm_eval conv = DepthwiseSeparableConvModule if use_depthwise else ConvModule self.stem = Focus( 3, int(arch_setting[0][0] * widen_factor), kernel_size=3, conv_cfg=conv_cfg, norm_cfg=norm_cfg, act_cfg=act_cfg) self.layers = ['stem'] for i, (in_channels, out_channels, num_blocks, add_identity, use_spp) in enumerate(arch_setting): in_channels = int(in_channels * widen_factor) out_channels = int(out_channels * widen_factor) num_blocks = max(round(num_blocks * deepen_factor), 1) stage = [] conv_layer = conv( in_channels, out_channels, 3, stride=2, padding=1, conv_cfg=conv_cfg, norm_cfg=norm_cfg, act_cfg=act_cfg) stage.append(conv_layer) if use_spp: spp = SPPBottleneck( out_channels, out_channels, kernel_sizes=spp_kernal_sizes, conv_cfg=conv_cfg, norm_cfg=norm_cfg, act_cfg=act_cfg) stage.append(spp) csp_layer = CSPLayer( out_channels, out_channels, num_blocks=num_blocks, add_identity=add_identity, use_depthwise=use_depthwise, conv_cfg=conv_cfg, norm_cfg=norm_cfg, act_cfg=act_cfg) stage.append(csp_layer) self.add_module(f'stage{i + 1}', nn.Sequential(*stage)) self.layers.append(f'stage{i + 1}') def _freeze_stages(self): if self.frozen_stages >= 0: for i in range(self.frozen_stages + 1): m = getattr(self, self.layers[i]) m.eval() for param in m.parameters(): param.requires_grad = False
[docs] def train(self, mode=True): super(CSPDarknet, self).train(mode) self._freeze_stages() if mode and self.norm_eval: for m in self.modules(): if isinstance(m, _BatchNorm): m.eval()
[docs] def forward(self, x): outs = [] for i, layer_name in enumerate(self.layers): layer = getattr(self, layer_name) x = layer(x) if i in self.out_indices: outs.append(x) return tuple(outs)
Read the Docs v: latest
Versions
latest
stable
3.x
v3.0.0rc0
v2.26.0
v2.25.3
v2.25.2
v2.25.1
v2.25.0
v2.24.1
v2.24.0
v2.23.0
v2.22.0
v2.21.0
v2.20.0
v2.19.1
v2.19.0
v2.18.1
v2.18.0
v2.17.0
v2.16.0
v2.15.1
v2.15.0
v2.14.0
v2.13.0
v2.12.0
v2.11.0
v2.10.0
v2.9.0
v2.8.0
v2.7.0
v2.6.0
v2.5.0
v2.4.0
v2.3.0
v2.2.1
v2.2.0
v2.1.0
v2.0.0
v1.2.0
test-3.0.0rc0
dev-3.x
dev
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.