# Ultralytics YOLO 🚀, AGPL-3.0 license
"""
Block modules
"""

import torch
import torch.nn as nn
from timm.models.layers import DropPath

from .conv import Conv
# from .transformer import TransformerBlock

__all__ = ('C2f', 'Bottleneck',)

class C2f(nn.Module):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, drop_path=None):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        if drop_path is None:
            drop_path = [0.0] * n

        self.c = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv((2 + n) * self.c, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0, drop_path=drop_path[i]) for i in range(n))

    def forward(self, x):
        """Forward pass through C2f layer."""
        y = list(self.cv1(x).chunk(2, 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))

    def forward_split(self, x):
        """Forward pass using split() instead of chunk()."""
        y = list(self.cv1(x).split((self.c, self.c), 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))


class Bottleneck(nn.Module):
    """Standard bottleneck."""

    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5, drop_path=0.0):  # ch_in, ch_out, shortcut, groups, kernels, expand
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = Conv(c_, c2, k[1], 1, g=g)
        self.add = shortcut and c1 == c2
        self.drop_path1 = DropPath(drop_path) if drop_path > 0. else nn.Identity()

    def forward(self, x):
        """'forward()' applies the YOLOv5 FPN to input data."""
        return x + self.drop_path1(self.cv2(self.cv1(x))) if self.add else self.cv2(self.cv1(x))