""" Pytorch Inception-V4 implementation
Sourced from https://github.com/Cadene/tensorflow-model-zoo.torch (MIT License) which is
based upon Google's Tensorflow implementation and pretrained weights (Apache 2.0 License)
"""
import torch
import torch.nn as nn
import torch.nn.functional as F

from .registry import register_model
from .helpers import load_pretrained
from .layers import SelectAdaptivePool2d
from timm.data import IMAGENET_INCEPTION_MEAN, IMAGENET_INCEPTION_STD

__all__ = ['InceptionV4']

default_cfgs = {
    'inception_v4': {
        'url': 'https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-cadene/inceptionv4-8e4777a0.pth',
        'num_classes': 1001, 'input_size': (3, 299, 299), 'pool_size': (8, 8),
        'crop_pct': 0.875, 'interpolation': 'bicubic',
        'mean': IMAGENET_INCEPTION_MEAN, 'std': IMAGENET_INCEPTION_STD,
        'first_conv': 'features.0.conv', 'classifier': 'last_linear',
    }
}


class BasicConv2d(nn.Module):
    def __init__(self, in_planes, out_planes, kernel_size, stride, padding=0):
        super(BasicConv2d, self).__init__()
        self.conv = nn.Conv2d(
            in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding, bias=False)
        self.bn = nn.BatchNorm2d(out_planes, eps=0.001)
        self.relu = nn.ReLU(inplace=True)

    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        x = self.relu(x)
        return x


class Mixed_3a(nn.Module):
    def __init__(self):
        super(Mixed_3a, self).__init__()
        self.maxpool = nn.MaxPool2d(3, stride=2)
        self.conv = BasicConv2d(64, 96, kernel_size=3, stride=2)

    def forward(self, x):
        x0 = self.maxpool(x)
        x1 = self.conv(x)
        out = torch.cat((x0, x1), 1)
        return out


class Mixed_4a(nn.Module):
    def __init__(self):
        super(Mixed_4a, self).__init__()

        self.branch0 = nn.Sequential(
            BasicConv2d(160, 64, kernel_size=1, stride=1),
            BasicConv2d(64, 96, kernel_size=3, stride=1)
        )

        self.branch1 = nn.Sequential(
            BasicConv2d(160, 64, kernel_size=1, stride=1),
            BasicConv2d(64, 64, kernel_size=(1, 7), stride=1, padding=(0, 3)),
            BasicConv2d(64, 64, kernel_size=(7, 1), stride=1, padding=(3, 0)),
            BasicConv2d(64, 96, kernel_size=(3, 3), stride=1)
        )

    def forward(self, x):
        x0 = self.branch0(x)
        x1 = self.branch1(x)
        out = torch.cat((x0, x1), 1)
        return out


class Mixed_5a(nn.Module):
    def __init__(self):
        super(Mixed_5a, self).__init__()
        self.conv = BasicConv2d(192, 192, kernel_size=3, stride=2)
        self.maxpool = nn.MaxPool2d(3, stride=2)

    def forward(self, x):
        x0 = self.conv(x)
        x1 = self.maxpool(x)
        out = torch.cat((x0, x1), 1)
        return out


class Inception_A(nn.Module):
    def __init__(self):
        super(Inception_A, self).__init__()
        self.branch0 = BasicConv2d(384, 96, kernel_size=1, stride=1)

        self.branch1 = nn.Sequential(
            BasicConv2d(384, 64, kernel_size=1, stride=1),
            BasicConv2d(64, 96, kernel_size=3, stride=1, padding=1)
        )

        self.branch2 = nn.Sequential(
            BasicConv2d(384, 64, kernel_size=1, stride=1),
            BasicConv2d(64, 96, kernel_size=3, stride=1, padding=1),
            BasicConv2d(96, 96, kernel_size=3, stride=1, padding=1)
        )

        self.branch3 = nn.Sequential(
            nn.AvgPool2d(3, stride=1, padding=1, count_include_pad=False),
            BasicConv2d(384, 96, kernel_size=1, stride=1)
        )

    def forward(self, x):
        x0 = self.branch0(x)
        x1 = self.branch1(x)
        x2 = self.branch2(x)
        x3 = self.branch3(x)
        out = torch.cat((x0, x1, x2, x3), 1)
        return out


class Reduction_A(nn.Module):
    def __init__(self):
        super(Reduction_A, self).__init__()
        self.branch0 = BasicConv2d(384, 384, kernel_size=3, stride=2)

        self.branch1 = nn.Sequential(
            BasicConv2d(384, 192, kernel_size=1, stride=1),
            BasicConv2d(192, 224, kernel_size=3, stride=1, padding=1),
            BasicConv2d(224, 256, kernel_size=3, stride=2)
        )

        self.branch2 = nn.MaxPool2d(3, stride=2)

    def forward(self, x):
        x0 = self.branch0(x)
        x1 = self.branch1(x)
        x2 = self.branch2(x)
        out = torch.cat((x0, x1, x2), 1)
        return out


class Inception_B(nn.Module):
    def __init__(self):
        super(Inception_B, self).__init__()
        self.branch0 = BasicConv2d(1024, 384, kernel_size=1, stride=1)

        self.branch1 = nn.Sequential(
            BasicConv2d(1024, 192, kernel_size=1, stride=1),
            BasicConv2d(192, 224, kernel_size=(1, 7), stride=1, padding=(0, 3)),
            BasicConv2d(224, 256, kernel_size=(7, 1), stride=1, padding=(3, 0))
        )

        self.branch2 = nn.Sequential(
            BasicConv2d(1024, 192, kernel_size=1, stride=1),
            BasicConv2d(192, 192, kernel_size=(7, 1), stride=1, padding=(3, 0)),
            BasicConv2d(192, 224, kernel_size=(1, 7), stride=1, padding=(0, 3)),
            BasicConv2d(224, 224, kernel_size=(7, 1), stride=1, padding=(3, 0)),
            BasicConv2d(224, 256, kernel_size=(1, 7), stride=1, padding=(0, 3))
        )

        self.branch3 = nn.Sequential(
            nn.AvgPool2d(3, stride=1, padding=1, count_include_pad=False),
            BasicConv2d(1024, 128, kernel_size=1, stride=1)
        )

    def forward(self, x):
        x0 = self.branch0(x)
        x1 = self.branch1(x)
        x2 = self.branch2(x)
        x3 = self.branch3(x)
        out = torch.cat((x0, x1, x2, x3), 1)
        return out


class Reduction_B(nn.Module):
    def __init__(self):
        super(Reduction_B, self).__init__()

        self.branch0 = nn.Sequential(
            BasicConv2d(1024, 192, kernel_size=1, stride=1),
            BasicConv2d(192, 192, kernel_size=3, stride=2)
        )

        self.branch1 = nn.Sequential(
            BasicConv2d(1024, 256, kernel_size=1, stride=1),
            BasicConv2d(256, 256, kernel_size=(1, 7), stride=1, padding=(0, 3)),
            BasicConv2d(256, 320, kernel_size=(7, 1), stride=1, padding=(3, 0)),
            BasicConv2d(320, 320, kernel_size=3, stride=2)
        )

        self.branch2 = nn.MaxPool2d(3, stride=2)

    def forward(self, x):
        x0 = self.branch0(x)
        x1 = self.branch1(x)
        x2 = self.branch2(x)
        out = torch.cat((x0, x1, x2), 1)
        return out


class Inception_C(nn.Module):
    def __init__(self):
        super(Inception_C, self).__init__()

        self.branch0 = BasicConv2d(1536, 256, kernel_size=1, stride=1)

        self.branch1_0 = BasicConv2d(1536, 384, kernel_size=1, stride=1)
        self.branch1_1a = BasicConv2d(384, 256, kernel_size=(1, 3), stride=1, padding=(0, 1))
        self.branch1_1b = BasicConv2d(384, 256, kernel_size=(3, 1), stride=1, padding=(1, 0))

        self.branch2_0 = BasicConv2d(1536, 384, kernel_size=1, stride=1)
        self.branch2_1 = BasicConv2d(384, 448, kernel_size=(3, 1), stride=1, padding=(1, 0))
        self.branch2_2 = BasicConv2d(448, 512, kernel_size=(1, 3), stride=1, padding=(0, 1))
        self.branch2_3a = BasicConv2d(512, 256, kernel_size=(1, 3), stride=1, padding=(0, 1))
        self.branch2_3b = BasicConv2d(512, 256, kernel_size=(3, 1), stride=1, padding=(1, 0))

        self.branch3 = nn.Sequential(
            nn.AvgPool2d(3, stride=1, padding=1, count_include_pad=False),
            BasicConv2d(1536, 256, kernel_size=1, stride=1)
        )

    def forward(self, x):
        x0 = self.branch0(x)

        x1_0 = self.branch1_0(x)
        x1_1a = self.branch1_1a(x1_0)
        x1_1b = self.branch1_1b(x1_0)
        x1 = torch.cat((x1_1a, x1_1b), 1)

        x2_0 = self.branch2_0(x)
        x2_1 = self.branch2_1(x2_0)
        x2_2 = self.branch2_2(x2_1)
        x2_3a = self.branch2_3a(x2_2)
        x2_3b = self.branch2_3b(x2_2)
        x2 = torch.cat((x2_3a, x2_3b), 1)

        x3 = self.branch3(x)

        out = torch.cat((x0, x1, x2, x3), 1)
        return out


class InceptionV4(nn.Module):
    def __init__(self, num_classes=1001, in_chans=3, drop_rate=0., global_pool='avg'):
        super(InceptionV4, self).__init__()
        self.drop_rate = drop_rate
        self.num_classes = num_classes
        self.num_features = 1536

        self.features = nn.Sequential(
            BasicConv2d(in_chans, 32, kernel_size=3, stride=2),
            BasicConv2d(32, 32, kernel_size=3, stride=1),
            BasicConv2d(32, 64, kernel_size=3, stride=1, padding=1),
            Mixed_3a(),
            Mixed_4a(),
            Mixed_5a(),
            Inception_A(),
            Inception_A(),
            Inception_A(),
            Inception_A(),
            Reduction_A(),  # Mixed_6a
            Inception_B(),
            Inception_B(),
            Inception_B(),
            Inception_B(),
            Inception_B(),
            Inception_B(),
            Inception_B(),
            Reduction_B(),  # Mixed_7a
            Inception_C(),
            Inception_C(),
            Inception_C(),
        )
        self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
        self.last_linear = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes)

    def get_classifier(self):
        return self.last_linear

    def reset_classifier(self, num_classes, global_pool='avg'):
        self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
        self.num_classes = num_classes
        self.last_linear = nn.Linear(
            self.num_features * self.global_pool.feat_mult(), num_classes) if num_classes else None

    def forward_features(self, x):
        return self.features(x)

    def forward(self, x):
        x = self.forward_features(x)
        x = self.global_pool(x).flatten(1)
        if self.drop_rate > 0:
            x = F.dropout(x, p=self.drop_rate, training=self.training)
        x = self.last_linear(x)
        return x


@register_model
def inception_v4(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
    default_cfg = default_cfgs['inception_v4']
    model = InceptionV4(num_classes=num_classes, in_chans=in_chans, **kwargs)
    model.default_cfg = default_cfg
    if pretrained:
        load_pretrained(model, default_cfg, num_classes, in_chans)
    return model