RT-ODLab/models/detectors/rtdetr/basic_modules/basic.py

import torch
import torch.nn as nn


# ----------------- CNN modules -----------------
def get_conv2d(c1, c2, k, p, s, d, g, bias=False):
    conv = nn.Conv2d(c1, c2, k, stride=s, padding=p, dilation=d, groups=g, bias=bias)

    return conv

def get_activation(act_type=None):
    if act_type == 'relu':
        return nn.ReLU(inplace=True)
    elif act_type == 'lrelu':
        return nn.LeakyReLU(0.1, inplace=True)
    elif act_type == 'mish':
        return nn.Mish(inplace=True)
    elif act_type == 'silu':
        return nn.SiLU(inplace=True)
    elif act_type is None:
        return nn.Identity()
    else:
        raise NotImplementedError
        
def get_norm(norm_type, dim):
    if norm_type == 'BN':
        return nn.BatchNorm2d(dim)
    elif norm_type == 'GN':
        return nn.GroupNorm(num_groups=32, num_channels=dim)
    elif norm_type is None:
        return nn.Identity()
    else:
        raise NotImplementedError

def conv3x3(in_planes: int, out_planes: int, stride: int = 1, groups: int = 1, dilation: int = 1) -> nn.Conv2d:
    """3x3 convolution with padding"""
    return nn.Conv2d(
        in_planes,
        out_planes,
        kernel_size=3,
        stride=stride,
        padding=dilation,
        groups=groups,
        bias=False,
        dilation=dilation,
    )

def conv1x1(in_planes: int, out_planes: int, stride: int = 1) -> nn.Conv2d:
    """1x1 convolution"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)

class FrozenBatchNorm2d(torch.nn.Module):
    def __init__(self, n):
        super(FrozenBatchNorm2d, self).__init__()
        self.register_buffer("weight", torch.ones(n))
        self.register_buffer("bias", torch.zeros(n))
        self.register_buffer("running_mean", torch.zeros(n))
        self.register_buffer("running_var", torch.ones(n))

    def _load_from_state_dict(self, state_dict, prefix, local_metadata, strict,
                              missing_keys, unexpected_keys, error_msgs):
        num_batches_tracked_key = prefix + 'num_batches_tracked'
        if num_batches_tracked_key in state_dict:
            del state_dict[num_batches_tracked_key]

        super(FrozenBatchNorm2d, self)._load_from_state_dict(
            state_dict, prefix, local_metadata, strict,
            missing_keys, unexpected_keys, error_msgs)

    def forward(self, x):
        # move reshapes to the beginning
        # to make it fuser-friendly
        w = self.weight.reshape(1, -1, 1, 1)
        b = self.bias.reshape(1, -1, 1, 1)
        rv = self.running_var.reshape(1, -1, 1, 1)
        rm = self.running_mean.reshape(1, -1, 1, 1)
        eps = 1e-5
        scale = w * (rv + eps).rsqrt()
        bias = b - rm * scale
        return x * scale + bias
    
class Conv(nn.Module):
    def __init__(self, 
                 c1,                   # in channels
                 c2,                   # out channels 
                 k=1,                  # kernel size 
                 p=0,                  # padding
                 s=1,                  # padding
                 d=1,                  # dilation
                 act_type  :str  = 'lrelu',   # activation
                 norm_type :str  ='BN',       # normalization
                 depthwise :bool =False):
        super(Conv, self).__init__()
        convs = []
        add_bias = False if norm_type else True
        if depthwise:
            convs.append(get_conv2d(c1, c1, k=k, p=p, s=s, d=d, g=c1, bias=add_bias))
            # depthwise conv
            if norm_type:
                convs.append(get_norm(norm_type, c1))
            if act_type:
                convs.append(get_activation(act_type))
            # pointwise conv
            convs.append(get_conv2d(c1, c2, k=1, p=0, s=1, d=d, g=1, bias=add_bias))
            if norm_type:
                convs.append(get_norm(norm_type, c2))
            if act_type:
                convs.append(get_activation(act_type))

        else:
            convs.append(get_conv2d(c1, c2, k=k, p=p, s=s, d=d, g=1, bias=add_bias))
            if norm_type:
                convs.append(get_norm(norm_type, c2))
            if act_type:
                convs.append(get_activation(act_type))
            
        self.convs = nn.Sequential(*convs)


    def forward(self, x):
        return self.convs(x)


# ----------------- Transformer modules -----------------