"""
Implementation of Prof-of-Concept Network: StarNet.

We make StarNet as simple as possible [to show the key contribution of element-wise multiplication]:
    - like NO layer-scale in network design,
    - and NO EMA during training,
    - which would improve the performance further.

Created by: Xu Ma (Email: ma.xu1@northeastern.edu)
Modified Date: Mar/29/2024
"""
import torch
import torch.nn as nn
from timm.models.layers import DropPath, trunc_normal_
from timm.models.registry import register_model

from ultralytics.nn.modules import (Conv, Bottleneck,C2f)





model_urls = {
    "starnet_s1": "https://github.com/ma-xu/Rewrite-the-Stars/releases/download/checkpoints_v1/starnet_s1.pth.tar",
    "starnet_s2": "https://github.com/ma-xu/Rewrite-the-Stars/releases/download/checkpoints_v1/starnet_s2.pth.tar",
    "starnet_s3": "https://github.com/ma-xu/Rewrite-the-Stars/releases/download/checkpoints_v1/starnet_s3.pth.tar",
    "starnet_s4": "https://github.com/ma-xu/Rewrite-the-Stars/releases/download/checkpoints_v1/starnet_s4.pth.tar",
}


class ConvBN(torch.nn.Sequential):
    def __init__(self, in_planes, out_planes, kernel_size=1, stride=1, padding=0, dilation=1, groups=1, with_bn=True):
        super().__init__()
        self.add_module('conv', torch.nn.Conv2d(in_planes, out_planes, kernel_size, stride, padding, dilation, groups))
        if with_bn:
            self.add_module('bn', torch.nn.BatchNorm2d(out_planes))
            torch.nn.init.constant_(self.bn.weight, 1)
            torch.nn.init.constant_(self.bn.bias, 0)


class StarNetBlock(nn.Module):
    def __init__(self, dim, mlp_ratio=3, drop_path=0.):
        super().__init__()
        self.dwconv = ConvBN(dim, dim, 7, 1, (7 - 1) // 2, groups=dim, with_bn=True)
        self.f1 = ConvBN(dim, mlp_ratio * dim, 1, with_bn=False)
        self.f2 = ConvBN(dim, mlp_ratio * dim, 1, with_bn=False)
        self.g = ConvBN(mlp_ratio * dim, dim, 1, with_bn=True)
        self.dwconv2 = ConvBN(dim, dim, 7, 1, (7 - 1) // 2, groups=dim, with_bn=False)
        self.act = nn.ReLU6()
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()

    def forward(self, x):
        input = x
        x = self.dwconv(x)
        x1, x2 = self.f1(x), self.f2(x)
        x = self.act(x1) * x2
        x = self.dwconv2(self.g(x))
        x = input + self.drop_path(x)
        return x